Aims. To identify variables independently associated with same-day discharge (SDD) of patients following revision total knee arthroplasty (rTKA) and to develop machine learning algorithms to predict suitable candidates for outpatient rTKA. Methods. Data were obtained from the American College of Surgeons National Quality Improvement Programme (ACS-NSQIP) database from the years 2018 to 2020. Patients with elective, unilateral rTKA procedures and a total hospital length of stay between zero and four days were included. Demographic, preoperative, and intraoperative variables were analyzed. A multivariable logistic regression (MLR) model and various machine learning techniques were compared using area under the curve (AUC), calibration, and decision curve analysis. Important and significant variables were identified from the models. Results. Of the 5,600 patients included in this study, 342 (6.1%) underwent SDD. The random forest (RF) model performed the best overall, with an internally validated AUC of 0.810. The ten crucial factors favoring SDD in the RF model include operating time, anaesthesia type, age, BMI, American Society of Anesthesiologists grade, race, history of diabetes, rTKA type, sex, and smoking status. Eight of these variables were also found to be significant in the MLR model. Conclusion. The RF model displayed excellent accuracy and identified clinically important variables for determining candidates for SDD following rTKA. Machine learning techniques such as RF will allow clinicians to accurately risk-stratify their patients preoperatively, in order to optimize resources and improve patient outcomes. Cite this article: Bone Jt Open 2023;4(6):399–407

This annotation briefly reviews the history of artificial intelligence and machine learning in health care and orthopaedics, and considers the role it will have in the future, particularly with reference to statistical analyses involving large datasets. Cite this article: Bone Joint J 2019;101-B:1476–1478

Aims. The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments. Methods. Based on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data. Results. With an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings. Conclusion. The presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision

Degenerative lumbar spondylolisthesis (DLS) is a common condition with many available treatment options. The Degenerative Spondylolisthesis Instability Classification (DSIC) scheme, based on a systematic review of best available evidence, was proposed by Simmonds et al. in 2015. This classification scheme proposes that the stability of the patient's pathology be determined by a surgeon based on quantitative and qualitative clinical and radiographic parameters. The purpose of the study is to utilise machine learning to classify DLS patients according to the DSIC scheme, offering a novel approach in which an objectively consistent system is employed. The patient data was collected by CSORN between 2015 and 2018 and included 224 DLS surgery cases. The data was cleaned by two methods, firstly, by deleting all patient entries with missing data, and secondly, by imputing the missing data using a maximum likelihood function. Five machine learning algorithms were used: logistic regression, boosted trees, random forests, support vector machines, and decision trees. The models were built using Python-based libraries and trained and tested using sklearn and pandas librairies. The algorithms were trained and tested using the two data sets (deletion and imputation cleaning methods). The matplotlib library was used to graph the ROC curves, including the area under the curve. The machine learning models were all able to predict the DSIC grade. Of all the models, the support vector machine model performed best, achieving an area under the curve score of 0.82. This model achieved an accuracy of 63% and an F1 score of 0.58. Between the two data cleaning methods, the imputation method was better, achieving higher areas under the curve than the deletion method. The accuracy, recall, precision, and F1 scores were similar for both data cleaning methods. The machine learning models were able to effectively predict physician decision making and score patients based on the DSIC scheme. The support vector machine model was able to achieve an area under the curve of 0.82 in comparison to physician classification. Since the data set was relatively small, the results could be improved with training on a larger data set. The use of machine learning models in DLS classification could prove to be an efficient approach to reduce human bias and error. Further efforts are necessary to test the inter- and intra-observer reliability of the DSIC scheme, as well as to determine if the surgeons using the scheme are following DLS treatment recommendations

Femoroacetabular Impingement (FAI) syndrome, characterised by abnormal hip contact causing symptoms and osteoarthritis, is measured using the International Hip Outcome Tool (iHOT). This study uses machine learning to predict patient outcomes post-treatment for FAI, focusing on achieving a minimally clinically important difference (MCID) at 52 weeks. A retrospective analysis of 6133 patients from the NAHR who underwent hip arthroscopic treatment for FAI between November 2013 and March 2022 was conducted. MCID was defined as half a standard deviation (13.61) from the mean change in iHOT score at 12 months. SKLearn Maximum Absolute Scaler and Logistic Regression were applied to predict achieving MCID, using baseline and 6-month follow-up data. The model's performance was evaluated by accuracy, area under the curve, and recall, using pre-operative and up to 6-month postoperative variables. A total of 23.1% (1422) of patients completed both baseline and 1-year follow-up iHOT surveys. The best results were obtained using both pre and postoperative variables. The machine learning model achieved 88.1% balanced accuracy, 89.6% recall, and 92.3% AUC. Sensitivity was 83.7% and specificity 93.5%. Key variables determining outcomes included MCID achievement at 6 months, baseline iHOT score, 6-month iHOT scores for pain, and difficulty in walking or using stairs. The study confirmed the utility of machine learning in predicting long-term outcomes following arthroscopic treatment for FAI. MCID, based on the iHOT 12 tools, indicates meaningful clinical changes. Machine learning demonstrated high accuracy and recall in distinguishing between patients achieving MCID and those who did not. This approach could help early identification of patients at risk of not meeting the MCID threshold one year after treatment

Aims. Clinical decision support systems (CDSS) can support clinicians in selecting appropriate treatments for patients. The objective of this study was to examine if triaging patients with LBP to the most optimal treatment can be improved by using a data-driven approach with the help of machine learning as base of such a CDSS. Methods. A clinical database of the Groningen Spine Center containing patient-reported data from 1546 patients with LBP was used. From this dataset, a training dataset with 354 features was labeled on eight different treatments actually received by these patients. With this dataset, models were trained. A test dataset with 50 cases judged on treatments by 4 experts in LBP triage was used to test these models with data not used to train the models. Prediction accuracy and average area under curve (AUC) were used as performance measures for the models. Results. The AUC values indicated small to medium learning effects showing that machine learning on patient-reported data, to model decision-making processes on treatments for LBP, may be possible. One of the best performing models was the Bayesian Network (BN) model; e.g. predicted surgery with accuracy 0.78 (95% C.I. 0.68– 0.87) and AUC 0.70. Conclusion. Benefits to using BNs compared to other supervised machine learning techniques are that it is easy to exploit expert knowledge in BN models, meaning that advices generated by the model can be explained. The next step is to improve the BN accuracy so that it can actually be used in a CDSS. No conflicts of interest. Sources of funding: This work is partly funded by a grant from the Netherlands Organization for Health Research and Development (ZonMw), grant 10-10400-98-009

Introduction & Aims. Patient recovery after total knee arthroplasty remains highly variable. Despite the growing interest in and implementation of patient reported outcome measures (e.g. Knee Society Score, Oxford Knee Score), the recovery process of the individual patient is poorly monitored. Unfortunately, patient reported outcomes represent a complex interaction of multiple physiological and psychological aspects, they are also limited by the discrete time intervals at which they are administered. The use of wearable sensors presents a potential alternative by continuously monitoring a patient's physical activity. These sensors however present their own challenges. This paper deals with the interpretation of the high frequency time signals acquired when using accelerometer-based wearable sensors. Method. During a preliminary validation, five healthy subjects were equipped with two wireless inertial measurement units (IMUs). Using adhesive tape, these IMU sensors were attached to the thigh and shank respectively. All subjects performed a series of supervised activities of daily living (ADL) in their everyday environment (1: walking, 2: stair ascent, 3: stair descent, 4: sitting, 5: laying, 6: standing). The supervisor timestamped the performed activities, such that the raw IMU signals could be uniquely linked to the performed activities. Subsequently, the acquired signals were reduced in Python. Each five second time window was characterized by the minimum, maximum and mean acceleration per sensor node. In addition, the frequency response was analyzed per sensor node as well as the correlation between both sensor nodes. Various machine learning approaches were subsequently implemented to predict the performed activities. Thereby, 60% of the acquired signals were used to train the mathematical models. These models were than used to predict the activity associated with the remaining 40% of the experimentally obtained data. Results. An overview of the obtained prediction accuracy per model stratified by ADL is provided in Table 1. The Nearest Neighbor and Random Forest algorithms performed worse compared to the Support Vector Machine and Decision Tree approaches. Even for the latter, differentiating between walking and stair ascent/descent remains challenging as well as differentiating between sitting, standing and laying. The prediction accuracies are however exceeding 90% for all activities when using the Support Vector Machine approach. This is further illustrated in Figure 1, indicating the actual versus predicted activity for the validation set. Conclusions. In conclusion, this paper presents an evaluation of different machine learning algorithms for the classification of activities of daily living from accelerometer-based wearable sensors. This facilitates evaluating a patient's ability to walk, climb or descend stairs, stand, lay or sit on a daily basis, understanding how active the patient is overall and which activities are routinely performed following arthroplasty surgery. Currently, effort is undertaken to understand how participation in these activities progresses with recovery following total knee arthroplasty

Single level discectomy (SLD) is one of the most commonly performed spinal surgery procedures. Two key drivers of their cost-of-care are duration of surgery (DOS) and postoperative length of stay (LOS). Therefore, the ability to preoperatively predict SLD DOS and LOS has substantial implications for both hospital and healthcare system finances, scheduling and resource allocation. As such, the goal of this study was to predict DOS and LOS for SLD using machine learning models (MLMs) constructed on preoperative factors using a large North American database. The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for SLD procedures from 2014-2019. The dataset was split in a 60/20/20 ratio of training/validation/testing based on year. Various MLMs (traditional regression models, tree-based models, and multilayer perceptron neural networks) were used and evaluated according to 1) mean squared error (MSE), 2) buffer accuracy (the number of times the predicted target was within a predesignated buffer), and 3) classification accuracy (the number of times the correct class was predicted by the models). To ensure real world applicability, the results of the models were compared to a mean regressor model. A total of 11,525 patients were included in this study. During validation, the neural network model (NNM) had the best MSEs for DOS (0.99) and LOS (0.67). During testing, the NNM had the best MSEs for DOS (0.89) and LOS (0.65). The NNM yielded the best 30-minute buffer accuracy for DOS (70.9%) and ≤120 min, >120 min classification accuracy (86.8%). The NNM had the best 1-day buffer accuracy for LOS (84.5%) and ≤2 days, >2 days classification accuracy (94.6%). All models were more accurate than the mean regressors for both DOS and LOS predictions. We successfully demonstrated that MLMs can be used to accurately predict the DOS and LOS of SLD based on preoperative factors. This big-data application has significant practical implications with respect to surgical scheduling and inpatient bedflow, as well as major implications for both private and publicly funded healthcare systems. Incorporating this artificial intelligence technique in real-time hospital operations would be enhanced by including institution-specific operational factors such as surgical team and operating room workflow

Precision health aims to develop personalised and proactive strategies for predicting, preventing, and treating complex diseases such as osteoarthritis (OA). Due to OA heterogeneity, which makes developing effective treatments challenging, identifying patients at risk for accelerated disease progression is essential for efficient clinical trial design and new treatment target discovery and development. To create a reliable and interpretable precision health tool that predicts rapid knee OA progression over a 2-year period from baseline patient characteristics using an advanced automated machine learning (autoML) framework, “Autoprognosis 2.0”. All available 2-year follow-up periods of 600 patients from the FNIH OA Biomarker Consortium were analysed using “Autoprognosis 2.0” in two separate approaches, with distinct definitions of clinical outcomes: multi-class predictions (categorising disease progression into pain and/or radiographic progression) and binary predictions. Models were developed using a training set of 1352 instances and all available variables (including clinical, X-ray, MRI, and biochemical features), and validated through both stratified 10-fold cross-validation and hold-out validation on a testing set of 339 instances. Model performance was assessed using multiple evaluation metrics. Interpretability analyses were carried out to identify important predictors of progression. Our final models yielded higher accuracy scores for multi-class predictions (AUC-ROC: 0.858, 95% CI: 0.856-0.860) compared to binary predictions (AUC-ROC: 0.717, 95% CI: 0.712-0.722). Important predictors of rapid disease progression included WOMAC scores and MRI features. Additionally, accurate ML models were developed for predicting OA progression in a subgroup of patients aged 65 or younger. This study presents a reliable and interpretable precision health tool for predicting rapid knee OA progression. Our models provide accurate predictions and, importantly, allow specific predictors of rapid disease progression to be identified. Furthermore, the transparency and explainability of our methods may facilitate their acceptance by clinicians and patients, enabling effective translation to clinical practice

Anterior approach total hip arthroplasty (AA-THA) has a steep learning curve, with higher complication rates in initial cases. Proper surgical case selection during the learning curve can reduce early risk. This study aims to identify patient and radiographic factors associated with AA-THA difficulty using Machine Learning (ML). Consecutive primary AA-THA patients from two centres, operated by two expert surgeons, were enrolled (excluding patients with prior hip surgery and first 100 cases per surgeon). K- means prototype clustering – an unsupervised ML algorithm – was used with two variables - operative duration and surgical complications within 6 weeks - to cluster operations into difficult or standard groups. Radiographic measurements (neck shaft angle, offset, LCEA, inter-teardrop distance, Tonnis grade) were measured by two independent observers. These factors, alongside patient factors (BMI, age, sex, laterality) were employed in a multivariate logistic regression analysis and used for k-means clustering. Significant continuous variables were investigated for predictive accuracy using Receiver Operator Characteristics (ROC). Out of 328 THAs analyzed, 130 (40%) were classified as difficult and 198 (60%) as standard. Difficult group had a mean operative time of 106mins (range 99–116) with 2 complications, while standard group had a mean operative time of 77mins (range 69–86) with 0 complications. Decreasing inter-teardrop distance (odds ratio [OR] 0.97, 95% confidence interval [CI] 0.95–0.99, p = 0.03) and right-sided operations (OR 1.73, 95% CI 1.10–2.72, p = 0.02) were associated with operative difficulty. However, ROC analysis showed poor predictive accuracy for these factors alone, with area under the curve of 0.56. Inter-observer reliability was reported as excellent (ICC >0.7). Right-sided hips (for right-hand dominant surgeons) and decreasing inter-teardrop distance were associated with case difficulty in AA-THA. These data could guide case selection during the learning phase. A larger dataset with more complications may reveal further factors

Abstract. Introduction. Precision health aims to develop personalised and proactive strategies for predicting, preventing, and treating complex diseases such as osteoarthritis (OA), a degenerative joint disease affecting over 300 million people worldwide. Due to OA heterogeneity, which makes developing effective treatments challenging, identifying patients at risk for accelerated disease progression is essential for efficient clinical trial design and new treatment target discovery and development. Objectives. This study aims to create a trustworthy and interpretable precision health tool that predicts rapid knee OA progression based on baseline patient characteristics using an advanced automated machine learning (autoML) framework, “Autoprognosis 2.0”. Methods. All available 2-year follow-up periods of 600 patients from the FNIH OA Biomarker Consortium were analysed using “Autoprognosis 2.0” in two separate approaches, with distinct definitions of clinical outcomes: multi-class predictions (categorising patients into non-progressors, pain-only progressors, radiographic-only progressors, and both pain and radiographic progressors) and binary predictions (categorising patients into non-progressors and progressors). Models were developed using a training set of 1352 instances and all available variables (including clinical, X-ray, MRI, and biochemical features), and validated through both stratified 10-fold cross-validation and hold-out validation on a testing set of 339 instances. Model performance was assessed using multiple evaluation metrics, such as AUC-ROC, AUC-PRC, F1-score, precision, and recall. Additionally, interpretability analyses were carried out to identify important predictors of rapid disease progression. Results. Our final models yielded high accuracy scores for both multi-class predictions (AUC-ROC: 0.858, 95% CI: 0.856–0.860; AUC-PRC: 0.675, 95% CI: 0.671–0.679; F1-score: 0.560, 95% CI: 0.554–0.566) and binary predictions (AUC-ROC: 0.717, 95% CI: 0.712–0.722; AUC-PRC: 0.620, 95% CI: 0.616–0.624; F1-score: 0.676, 95% CI: 0.673–0679). Important predictors of rapid disease progression included the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) scores and MRI features. Our models were further successfully validated using a hold-out dataset, which was previously omitted from model development and training (AUC-ROC: 0.877 for multi-class predictions; AUC-ROC: 0.746 for binary predictions). Additionally, accurate ML models were developed for predicting OA progression in a subgroup of patients aged 65 or younger (AUC-ROC: 0.862, 95% CI: 0.861–0.863 for multi-class predictions; AUC-ROC: 0.736, 95% CI: 0.734–0.738 for binary predictions). Conclusions. This study presents a reliable and interpretable precision health tool for predicting rapid knee OA progression using “Autoprognosis 2.0”. Our models provide accurate predictions and offer insights into important predictors of rapid disease progression. Furthermore, the transparency and interpretability of our methods may facilitate their acceptance by clinicians and patients, enabling effective utilisation in clinical practice. Future work should focus on refining these models by increasing the sample size, integrating additional features, and using independent datasets for external validation. Declaration of Interest. (b) declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported:I declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research project

Disorders of human joints manifest during dynamic movement, yet no objective tools are widely available for clinicians to assess or diagnose abnormal joint motion during functional activity. Machine learning tools have supported advances in many applications for image interpretation and understanding and have the potential to enable clinically and economically practical methods for objective assessment of human joint mechanics. We performed a study using convolutional neural networks to autonomously segment radiographic images of knee replacements and to determine the potential for autonomous measurement of knee kinematics. The autonomously segmented images provided superior kinematic measurements for both femur and tibia implant components. We believe this is an encouraging first step towards realization of a completely autonomous capability to accurately quantify dynamic joint motion using a clinically and economically practical methodology

Access to health care, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure low back physiotherapy exercise participation without the direct supervision of a medical professional. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low back physiotherapy exercises using a single mobile phone camera. 24 healthy adult subjects performed seven exercises based on the McKenzie low back physiotherapy program while being filmed with two smartphone cameras. Joint locations were automatically extracted using an open-source pose estimation framework. Engineered features were extracted from the joint location time series and used to train a support vector machine classifier (SVC). A convolutional neural network (CNN) was trained directly on the joint location time series data to classify exercises based on a recording from a single camera. The models were evaluated using a 5-fold cross validation approach, stratified by subject, with the class-balanced accuracy used as the performance metric. Optimal performance was achieved when using a total of 12 pose estimation landmarks from the upper and lower body, with the SVC model achieving a classification accuracy of 96±4% and the CNN model an accuracy of 97±2%. This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively assess at-home low back physiotherapy adherence. This approach could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings

Background. The advent of value-based conscientiousness and rapid-recovery discharge pathways presents surgeons, hospitals, and payers with the challenge of providing the same total hip arthroplasty episode of care in the safest and most economic fashion for the same fee, despite patient differences. Various predictive analytic techniques have been applied to medical risk models, such as sepsis risk scores, but none have been applied or validated to the elective primary total hip arthroplasty (THA) setting for key payment-based metrics. The objective of this study was to develop and validate a predictive machine learning model using preoperative patient demographics for length of stay (LOS) after primary THA as the first step in identifying a patient-specific payment model (PSPM). Methods. Using 229,945 patients undergoing primary THA for osteoarthritis from an administrative database between 2009– 16, we created a naïve Bayesian model to forecast LOS after primary THA using a 3:2 split in which 60% of the available patient data “built” the algorithm and the remaining 40% of patients were used for “testing.” This process was iterated five times for algorithm refinement, and model performance was determined using the area under the receiver operating characteristic curve (AUC), percent accuracy, and positive predictive value. LOS was either grouped as 1–5 days or greater than 5 days. Results. The machine learning model algorithm required age, race, gender, and two comorbidity scores (“risk of illness” and “risk of morbidity”) to demonstrate excellent validity, reliability, and responsiveness with an AUC of 0.87 after five iterations. Hospital stays of greater than 5 days for THA were most associated with increased risk of illness and risk of comorbidity scores during admission compared to 1–5 days of stay. Conclusions. Our machine learning model derived from administrative big data demonstrated excellent validity, reliability, and responsiveness after primary THA while accurately predicting LOS and identifying two comorbidity scores as key value-based metrics. Predictive data has the potential to engender a risk-based PSPM prior to primary THA and other elective orthopaedic procedures

Arthroplasties are widely performed to improve mobility and quality of life for symptomatic knee/hip osteoarthritis patients. With increasing rates of Total Joint Replacements in the United Kingdom, predicting length of stay is vital for hospitals to control costs, manage resources, and prevent postoperative complications. A longer Length of stay has been shown to negatively affect the quality of care, outcomes and patient satisfaction. Thus, predicting LOS enables us to make full use of medical resources. Clinical characteristics were retrospectively collected from 1,303 patients who received TKA and THR. A total of 21 variables were included, to develop predictive models for LOS by multiple machine learning (ML) algorithms, including Random Forest Classifier (RFC), K-Nearest Neighbour (KNN), Extreme Gradient Boost (XgBoost), and Na¯ve Bayes (NB). These models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance. A feature selection approach was used to identify optimal predictive factors. Based on the ROC of Training result, XgBoost algorithm was selected to be applied to the Test set. The areas under the ROC curve (AUCs) of the 4 models ranged from 0.730 to 0.966, where higher AUC values generally indicate better predictive performance. All the ML-based models performed better than conventional statistical methods in ROC curves. The XgBoost algorithm with 21 variables was identified as the best predictive model. The feature selection indicated the top six predictors: Age, Operation Duration, Primary Procedure, BMI, creatinine and Month of Surgery. By analysing clinical characteristics, it is feasible to develop ML-based models for the preoperative prediction of LOS for patients who received TKA and THR, and the XgBoost algorithm performed the best, in terms of accuracy of predictive performance. As this model was originally crafted at Ashford and St. Peters Hospital, we have naturally named it as THE ASHFORD OUTCOME

Objective. Wearable sensors have enabled objective functional data collection from patients before total knee replacement (TKR) and at clinical follow-ups post-surgery whereas traditional evaluation has solely relied on self-reported subjective measures. The timed-up-and-go (TUG) test has been used to evaluate function but is commonly measured using only total completion time, which does not assess joint function or test completion strategy. The current work employs machine learning techniques to distinguish patient groups based on derived functional metrics from the TUG test and expose clinically important functional parameters that are predictive of patient recovery. Methods. Patients scheduled for TKR (n=70) were recruited and instrumented with a wearable sensor system while performing three TUG test trials. Remaining study patients (n=68) also completed three TUG trials at their 2, 6, and 13-week follow-ups. Many patients (n=36) have also participated up to their 26-week appointment. Custom developed software was used to segment recorded tests into sub-activities and extract 54 functional metrics to evaluate op/non-operative knee function. All preoperative TUG samples and their standardized metrics were clustered into two unlabelled groups using the k-means algorithm. Both groups were tracked forward to see how their early functional parameters translated to functional improvement at their three-month assessment. Test total completion time was used to estimate overall functional improvement and to relate findings to existing literature. Patients that completed their 26-week tests were tracked further to their most recent timepoint. Results. Preoperative clustering separated two groups with different test completion times (n=46 vs. n=22 with mean times of 13s vs. 22s). Of the faster preoperative group, 63% of patients maintained their time, 26% improved, and 11% worsened whereas of the slower preoperative group, 27% maintained, 64% improved, and 9% worsened. The high improvement group improved their times by 4.9s (p<0.01) between preoperative and 13-week visits whereas the other group had no significant change. Test times were different between both groups preoperatively (p<0.001) and at 6 (p=0.01) and 13 (p=0.03) weeks but not at 26 weeks (p=0.67). The high improvement group reached an overall improvement of 9s (p<0.01) at 26 weeks whereas the low improvement group still showed no improvement greater than the TUG minimal detectable change of 2.2s (1.8s, p<0.01)[1]. Test sub-activity times for both groups at each timepoint can be seen in Figure 1. Conclusions. This work has demonstrated that machine learning has the potential to find patterns in preoperative functional parameters that can predict functional improvement after surgery. While useful for assigning labels to the distinguished clusters, test completion time was not among the top distinguishable metrics between groups at three months which highlights the necessity for these more descriptive performance metrics when analyzing patient recovery. It is expected that these early predictions will be used to realistically adjust patient expectations or highlight opportunities for physiotherapeutic intervention to improve future outcomes. For any figures or tables, please contact the authors directly

Total knee and hip arthroplasty (TKA and THA) are the most commonly performed surgical procedures, the costs of which constitute a significant healthcare burden. Improving access to care for THA/TKA requires better efficiency. It is hypothesized that this may be possible through a two-stage approach that utilizes prediction of surgical time to enable optimization of operating room (OR) schedules.

Data from 499,432 elective unilateral arthroplasty procedures, including 302,490 TKAs, and 196,942 THAs, performed from 2014-2019 was extracted from the American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database. A deep multilayer perceptron model was trained to predict duration of surgery (DOS) based on pre-operative clinical and biochemical patient factors. A two-stage approach, utilizing predicted DOS from a held out “test” dataset, was utilized to inform the daily OR schedule. The objective function of the optimization was the total OR utilization, with a penalty for overtime. The scheduling problem and constraints were simulated based on a high-volume elective arthroplasty centre in Canada. This approach was compared to current patient scheduling based on mean procedure DOS. Approaches were compared by performing 1000 simulated OR schedules.

The predict then optimize approach achieved an 18% increase in OR utilization over the mean regressor. The two-stage approach reduced overtime by 25-minutes per OR day, however it created a 7-minute increase in underutilization. Better objective value was seen in 85.1% of the simulations.

With deep learning prediction and mathematical optimization of patient scheduling it is possible to improve overall OR utilization compared to typical scheduling practices. Maximizing utilization of existing healthcare resources can, in limited resource environments, improve patient's access to arthritis care by increasing patient throughput, reducing surgical wait times and in the immediate future, help clear the backlog associated with the COVID-19 pandemic.

The success of a cementless Total Hip Arthroplasty (THA) depends not only on initial micromotion, but also on long-term failure mechanisms, e.g., implant-bone interface stresses and stress shielding. Any preclinical investigation aimed at designing femoral implant needs to account for temporal evolution of interfacial condition, while dealing with these failure mechanisms. The goal of the present multi-criteria optimization study was to search for optimum implant geometry by implementing a novel machine learning framework comprised of a neural network (NN), genetic algorithm (GA) and finite element (FE) analysis. The optimum implant model was subsequently evaluated based on evolutionary interface conditions. The optimization scheme of our earlier study [1] has been used here with an additional inclusion of an NN to predict the initial fixation of an implant model. The entire CAD based parameterization technique for the implant was described previously [1]. Three objective functions, the first two based on proximal resorbed Bone Mass Fraction (BMF) [1] and implant-bone interface failure index [1], respectively, and the other based on initial micromotion, were formulated to model the multi-criteria optimization problem. The first two objective functions, e.g., objectives f1 and f2, were calculated from the FE analysis (Ansys), whereas the third objective (f3) involved an NN developed for the purpose of predicting the post-operative micromotion based on the stem design parameters. Bonded interfacial condition was used to account for the effects of stress shielding and interface stresses, whereas a set of contact models were used to develop the NN for faster prediction of post-operative micromotion. A multi-criteria GA was executed up to a desired number of generations for optimization (Fig. 1). The final trade-off model was further evaluated using a combined remodelling and bone ingrowth simulation based on an evolutionary interface condition [2], and subsequently compared with a generic TriLock implant. The non-dominated solutions obtained from the GA execution were interpolated to determine the 3D nature of the Pareto-optimal surface (Fig. 2). The effects of all failure mechanisms were found to be minimized in these optimized solutions (Fig. 2). However, the most compromised solution, i.e., the trade-off stem geometry (TSG), was chosen for further assessment based on evolutionary interfacial condition. The simulation-based combined remodelling and bone ingrowth study predicted a faster ingrowth for TSG as compared to the generic design. The surface area with post-operative (i.e., iteration 1) ingrowth was found to be ∼50% for the TSG, while that for the TriLock model was ∼38% (Fig. 3). However, both designs predicted similar long-term ingrowth (∼89% surface area). The long-term proximal bone resorption (upto lesser trochanter) was found to be ∼30% for the TSG, as compared to ∼37% for the TriLock model. The TSG was found to be bone-preserving with prominent frontal wedge and rectangular proximal section for better rotational stability; features present in some recent designs. The optimization scheme, therefore, appears to be a quick and robust preclinical assessment tool for cementless femoral implant design. To view tables/figures, please contact authors directly

Physiotherapy is a critical element in successful conservative management of low back pain (LBP). The aim of this study was to develop and evaluate a system with wearable inertial sensors to objectively detect sitting postures and performance of unsupervised exercises containing movement in multiple planes (flexion, extension, rotation).

A set of 8 inertial sensors were placed on 19 healthy adult subjects. Data was acquired as they performed 7 McKenzie low-back exercises and 3 sitting posture positions. This data was used to train two models (Random Forest (RF) and XGBoost (XGB)) using engineered time series features. In addition, a convolutional neural network (CNN) was trained directly on the time series data. A feature importance analysis was performed to identify sensor locations and channels that contributed most to the models. Finally, a subset of sensor locations and channels was included in a hyperparameter grid search to identify the optimal sensor configuration and the best performing algorithm(s) for exercise classification. Models were evaluated using F1-score in a 10-fold cross validation approach.

The optimal hardware configuration was identified as a 3-sensor setup using lower back, left thigh, and right ankle sensors with acceleration, gyroscope, and magnetometer channels. The XBG model achieved the highest exercise (F1=0.94±0.03) and posture (F1=0.90±0.11) classification scores. The CNN achieved similar results with the same sensor locations, using only the accelerometer and gyroscope channels for exercise classification (F1=0.94±0.02) and the accelerometer channel alone for posture classification (F1=0.91±0.03).

This study demonstrates the potential of a 3-sensor lower body wearable solution (e.g. smart pants) that can identify proper sitting postures and exercises in multiple planes, suitable for low back pain. This technology has the potential to improve the effectiveness of LBP rehabilitation by facilitating quantitative feedback, early problem diagnosis, and possible remote monitoring.

To detect early signs of infection infrared thermography has been suggested to provide quantitative information. Our vision is to invent a pin site infection thermographic surveillance tool for patients at home. A preliminary step to this goal is the aim of this study, to automate the process of locating the pin and detecting the pin sites in thermal images efficiently, exactly, and reliably for extracting pin site temperatures.

A total of 1708 pin sites was investigated with Thermography and augmented by 9 different methods in to totally 10.409 images. The dataset was divided into a training set (n=8325), a validation set (n=1040), and a test set (n=1044) of images. The Pin Detection Model (PDM) was developed as follows: A You Only Look Once (YOLOv5) based object detection model with a Complete Detection Intersection over Union (CDIoU), it was pre-trained and finetuned by the through transfer learning. The basic performance of the YOLOv5 with CDIoU model was compared with other conventional models (FCOS and YOLOv4) for deep and transition learning to improve performance and precision. Maximum Temperature Extraction (MTE) Based on Region of Interest (ROI) for all pin sites was generated by the model. Inference of MTE using PDM with infected and un-infected datasets was investigated.

An automatic tool that can identify and annotate pin sites on conventional images using bounding boxes was established. The bounding box was transferred to the infrared image. The PMD algorithm was built on YOLOv5 with CDIoU and has a precision of 0.976. The model offers the pin site detection in 1.8 milliseconds. The thermal data from ROI at the pin site was automatically extracted.

These results enable automatic pin site annotation on thermography. The model tracks the correlation between temperature and infection from the detected pin sites and demonstrates it is a promising tool for automatic pin site detection and maximum temperature extraction for further infection studies. Our work for automatic pin site annotation on thermography paves the way for future research on infection assessment using thermography.

Pedicle screw fixation is a technically demanding procedure with potential difficulties and reoperation rates are currently on the order of 11%. The most common intraoperative practice for position assessment of pedicle screws is biplanar fluoroscopic imaging that is limited to two- dimensions and is associated to low accuracies. We have previously introduced a full-dimensional position assessment framework based on registering intraoperative X-rays to preoperative volumetric images with sufficient accuracies. However, the framework requires a semi-manual process of pedicle screw segmentation and the intraoperative X-rays have to be taken from defined positions in space in order to avoid pedicle screws' head occlusion. This motivated us to develop advancements to the system to achieve higher levels of automation in the hope of higher clinical feasibility.

In this study, we developed an automatic segmentation and X-ray adequacy assessment protocol. An artificial neural network was trained on a dataset that included a number of digitally reconstructed radiographs representing pedicle screw projections from different points of view. This model was able to segment the projection of any pedicle screw given an X-ray as its input with accuracy of 93% of the pixels. Once the pedicle screw was segmented, a number of descriptive geometric features were extracted from the isolated blob. These segmented images were manually labels as ‘adequate’ or ‘not adequate’ depending on the visibility of the screw axis. The extracted features along with their corresponding labels were used to train a decision tree model that could classify each X-ray based on its adequacy with accuracies on the order of 95%.

In conclusion, we presented here a robust, fast and automated pedicle screw segmentation process, combined with an accurate and automatic algorithm for classifying views of pedicle screws as adequate or not. These tools represent a useful step towards full automation of our pedicle screw positioning assessment system.

Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’). Cite this article: Bone Joint J 2022;104-B(8):911–914

Aims. A substantial fraction of patients undergoing knee arthroplasty (KA) or hip arthroplasty (HA) do not achieve an improvement as high as the minimal clinically important difference (MCID), i.e. do not achieve a meaningful improvement. Using three patient-reported outcome measures (PROMs), our aim was: 1) to assess machine learning (ML), the simple pre-surgery PROM score, and logistic-regression (LR)-derived performance in their prediction of whether patients undergoing HA or KA achieve an improvement as high or higher than a calculated MCID; and 2) to test whether ML is able to outperform LR or pre-surgery PROM scores in predictive performance. Methods. MCIDs were derived using the change difference method in a sample of 1,843 HA and 1,546 KA patients. An artificial neural network, a gradient boosting machine, least absolute shrinkage and selection operator (LASSO) regression, ridge regression, elastic net, random forest, LR, and pre-surgery PROM scores were applied to predict MCID for the following PROMs: EuroQol five-dimension, five-level questionnaire (EQ-5D-5L), EQ visual analogue scale (EQ-VAS), Hip disability and Osteoarthritis Outcome Score-Physical Function Short-form (HOOS-PS), and Knee injury and Osteoarthritis Outcome Score-Physical Function Short-form (KOOS-PS). Results. Predictive performance of the best models per outcome ranged from 0.71 for HOOS-PS to 0.84 for EQ-VAS (HA sample). ML statistically significantly outperformed LR and pre-surgery PROM scores in two out of six cases. Conclusion. MCIDs can be predicted with reasonable performance. ML was able to outperform traditional methods, although only in a minority of cases. Cite this article: Bone Joint Res 2023;12(9):512–521

Aims. The lack of disease-modifying treatments for osteoarthritis (OA) is linked to a shortage of suitable biomarkers. This study combines multi-molecule synovial fluid analysis with machine learning to produce an accurate diagnostic biomarker model for end-stage knee OA (esOA). Methods. Synovial fluid (SF) from patients with esOA, non-OA knee injury, and inflammatory knee arthritis were analyzed for 35 potential markers using immunoassays. Partial least square discriminant analysis (PLS-DA) was used to derive a biomarker model for cohort classification. The ability of the biomarker model to diagnose esOA was validated by identical wide-spectrum SF analysis of a test cohort of ten patients with esOA. Results. PLS-DA produced a streamlined biomarker model with excellent sensitivity (95%), specificity (98.4%), and reliability (97.4%). The eight-biomarker model produced a fingerprint for esOA comprising type IIA procollagen N-terminal propeptide (PIIANP), tissue inhibitor of metalloproteinase (TIMP)-1, a disintegrin and metalloproteinase with thrombospondin motifs 4 (ADAMTS-4), monocyte chemoattractant protein (MCP)-1, interferon-γ-inducible protein-10 (IP-10), and transforming growth factor (TGF)-β3. Receiver operating characteristic (ROC) analysis demonstrated excellent discriminatory accuracy: area under the curve (AUC) being 0.970 for esOA, 0.957 for knee injury, and 1 for inflammatory arthritis. All ten validation test patients were classified correctly as esOA (accuracy 100%; reliability 100%) by the biomarker model. Conclusion. SF analysis coupled with machine learning produced a partially validated biomarker model with cohort-specific fingerprints that accurately and reliably discriminated esOA from knee injury and inflammatory arthritis with almost 100% efficacy. The presented findings and approach represent a new biomarker concept and potential diagnostic tool to stage disease in therapy trials and monitor the efficacy of such interventions. Cite this article: Bone Joint Res 2020;9(9):623–632

In recent years, machine learning (ML) and artificial neural networks (ANNs), a particular subset of ML, have been adopted by various areas of healthcare. A number of diagnostic and prognostic algorithms have been designed and implemented across a range of orthopaedic sub-specialties to date, with many positive results. However, the methodology of many of these studies is flawed, and few compare the use of ML with the current approach in clinical practice. Spinal surgery has advanced rapidly over the past three decades, particularly in the areas of implant technology, advanced surgical techniques, biologics, and enhanced recovery protocols. It is therefore regarded an innovative field. Inevitably, spinal surgeons will wish to incorporate ML into their practice should models prove effective in diagnostic or prognostic terms. The purpose of this article is to review published studies that describe the application of neural networks to spinal surgery and which actively compare ANN models to contemporary clinical standards allowing evaluation of their efficacy, accuracy, and relatability. It also explores some of the limitations of the technology, which act to constrain the widespread adoption of neural networks for diagnostic and prognostic use in spinal care. Finally, it describes the necessary considerations should institutions wish to incorporate ANNs into their practices. In doing so, the aim of this review is to provide a practical approach for spinal surgeons to understand the relevant aspects of neural networks. Cite this article: Bone Joint J 2021;103-B(9):1442–1448

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Aims

This study was designed to develop a model for predicting bone mineral density (BMD) loss of the femur after total hip arthroplasty (THA) using artificial intelligence (AI), and to identify factors that influence the prediction. Additionally, we virtually examined the efficacy of administration of bisphosphonate for cases with severe BMD loss based on the predictive model.

Aims

To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials.

There is increasing popularity in the use of artificial intelligence and machine-learning techniques to provide diagnostic and prognostic models for various aspects of Trauma & Orthopaedic surgery. However, correct interpretation of these models is difficult for those without specific knowledge of computing or health data science methodology. Lack of current reporting standards leads to the potential for significant heterogeneity in the design and quality of published studies. We provide an overview of machine-learning techniques for the lay individual, including key terminology and best practice reporting guidelines.

Cite this article: Bone Joint J 2021;103-B(12):1754–1758.

Aims

Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool.

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as ‘big data’, AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI’s limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Cite this article: Bone Joint Res 2023;12(7):447–454.

Aims

Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are.

Aims

This study aimed to explore the biological and clinical importance of dysregulated key genes in osteoarthritis (OA) patients at the cartilage level to find potential biomarkers and targets for diagnosing and treating OA.

Aims. To determine the major risk factors for unplanned reoperations (UROs) following corrective surgery for adult spinal deformity (ASD) and their interactions, using machine learning-based prediction algorithms and game theory. Methods. Patients who underwent surgery for ASD, with a minimum of two-year follow-up, were retrospectively reviewed. In total, 210 patients were included and randomly allocated into training (70% of the sample size) and test (the remaining 30%) sets to develop the machine learning algorithm. Risk factors were included in the analysis, along with clinical characteristics and parameters acquired through diagnostic radiology. Results. Overall, 152 patients without and 58 with a history of surgical revision following surgery for ASD were observed; the mean age was 68.9 years (SD 8.7) and 66.9 years (SD 6.6), respectively. On implementing a random forest model, the classification of URO events resulted in a balanced accuracy of 86.8%. Among machine learning-extracted risk factors, URO, proximal junction failure (PJF), and postoperative distance from the posterosuperior corner of C7 and the vertical axis from the centroid of C2 (SVA) were significant upon Kaplan-Meier survival analysis. Conclusion. The major risk factors for URO following surgery for ASD, i.e. postoperative SVA and PJF, and their interactions were identified using a machine learning algorithm and game theory. Clinical benefits will depend on patient risk profiles. Cite this article: Bone Joint Res 2023;12(4):245–255

Aims. The aim of this study was to identify factors associated with five-year cancer-related mortality in patients with limb and trunk soft-tissue sarcoma (STS) and develop and validate machine learning algorithms in order to predict five-year cancer-related mortality in these patients. Methods. Demographic, clinicopathological, and treatment variables of limb and trunk STS patients in the Surveillance, Epidemiology, and End Results Program (SEER) database from 2004 to 2017 were analyzed. Multivariable logistic regression was used to determine factors significantly associated with five-year cancer-related mortality. Various machine learning models were developed and compared using area under the curve (AUC), calibration, and decision curve analysis. The model that performed best on the SEER testing data was further assessed to determine the variables most important in its predictive capacity. This model was externally validated using our institutional dataset. Results. A total of 13,646 patients with STS from the SEER database were included, of whom 35.9% experienced five-year cancer-related mortality. The random forest model performed the best overall and identified tumour size as the most important variable when predicting mortality in patients with STS, followed by M stage, histological subtype, age, and surgical excision. Each variable was significant in logistic regression. External validation yielded an AUC of 0.752. Conclusion. This study identified clinically important variables associated with five-year cancer-related mortality in patients with limb and trunk STS, and developed a predictive model that demonstrated good accuracy and predictability. Orthopaedic oncologists may use these findings to further risk-stratify their patients and recommend an optimal course of treatment. Cite this article: Bone Joint J 2023;105-B(6):702–710

Aims

The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?

Aims

Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction.

Aims

Accurate identification of the ankle joint centre is critical for estimating tibial coronal alignment in total knee arthroplasty (TKA). The purpose of the current study was to leverage artificial intelligence (AI) to determine the accuracy and effect of using different radiological anatomical landmarks to quantify mechanical alignment in relation to a traditionally defined radiological ankle centre.

Aims

An objective technological solution for tracking adherence to at-home shoulder physiotherapy is important for improving patient engagement and rehabilitation outcomes, but remains a significant challenge. The aim of this research was to evaluate performance of machine-learning (ML) methodologies for detecting and classifying inertial data collected during in-clinic and at-home shoulder physiotherapy exercise.

Aims

This study aimed to compare the performance of survival prediction models for bone metastases of the extremities (BM-E) with pathological fractures in an Asian cohort, and investigate patient characteristics associated with survival.

Identification of patients at risk of not achieving minimally clinically important differences (MCID) in patient reported outcome measures (PROMs) is important to ensure principled and informed pre-operative decision making. Machine learning techniques may enable the generation of a predictive model for attainment of MCID in hip arthroscopy. Aims: 1) to determine whether machine learning techniques could predict which patients will achieve MCID in the iHOT-12 PROM 6 months after arthroscopic management of femoroacetabular impingement (FAI), 2) to determine which factors contribute to their predictive power. Data from the UK Non-Arthroplasty Hip Registry database was utilised. We identified 1917 patients who had undergone hip arthroscopy for FAI with both baseline and 6 month follow up iHOT-12 and baseline EQ-5D scores. We trained three established machine learning algorithms on our dataset to predict an outcome of iHOT-12 MCID improvement at 6 months given baseline characteristics including demographic factors, disease characteristics and PROMs. Performance was assessed using area under the receiver operating characteristic (AUROC) statistics with 5-fold cross validation. The three machine learning algorithms showed quite different performance. The linear logistic regression model achieved AUROC = 0.59, the deep neural network achieved AUROC = 0.82, while a random forest model had the best predictive performance with AUROC 0.87. Of demographic factors, we found that BMI and age were key predictors for this model. We also found that removing all features except baseline responses to the iHOT-12 questionnaire had little effect on performance for the random forest model (AUROC = 0.85). Disease characteristics had little effect on model performance. Machine learning models are able to predict with good accuracy 6-month post-operative MCID attainment in patients undergoing arthroscopic management for FAI. Baseline scores from the iHOT-12 questionnaire are sufficient to predict with good accuracy whether a patient is likely to reach MCID in post-operative PROMs

Aims. Failure of irrigation and debridement (I&D) for prosthetic joint infection (PJI) is influenced by numerous host, surgical, and pathogen-related factors. We aimed to develop and validate a practical, easy-to-use tool based on machine learning that may accurately predict outcome following I&D surgery taking into account the influence of numerous factors. Methods. This was an international, multicentre retrospective study of 1,174 revision total hip (THA) and knee arthroplasties (TKA) undergoing I&D for PJI between January 2005 and December 2017. PJI was defined using the Musculoskeletal Infection Society (MSIS) criteria. A total of 52 variables including demographics, comorbidities, and clinical and laboratory findings were evaluated using random forest machine learning analysis. The algorithm was then verified through cross-validation. Results. Of the 1,174 patients that were included in the study, 405 patients (34.5%) failed treatment. Using random forest analysis, an algorithm that provides the probability for failure for each specific patient was created. By order of importance, the ten most important variables associated with failure of I&D were serum CRP levels, positive blood cultures, indication for index arthroplasty other than osteoarthritis, not exchanging the modular components, use of immunosuppressive medication, late acute (haematogenous) infections, methicillin-resistant Staphylococcus aureus infection, overlying skin infection, polymicrobial infection, and older age. The algorithm had good discriminatory capability (area under the curve = 0.74). Cross-validation showed similar probabilities comparing predicted and observed failures indicating high accuracy of the model. Conclusion. This is the first study in the orthopaedic literature to use machine learning as a tool for predicting outcomes following I&D surgery. The developed algorithm provides the medical profession with a tool that can be employed in clinical decision-making and improve patient care. Future studies should aid in further validating this tool on additional cohorts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):11–19

External validation of machine learning predictive models is achieved through evaluation of model performance on different groups of patients than were used for algorithm development. This important step is uncommonly performed, inhibiting clinical translation of newly developed models. Recently, machine learning was used to develop a tool that can quantify revision risk for a patient undergoing primary anterior cruciate ligament (ACL) reconstruction (https://swastvedt.shinyapps.io/calculator_rev/). The source of data included nearly 25,000 patients with primary ACL reconstruction recorded in the Norwegian Knee Ligament Register (NKLR). The result was a well-calibrated tool capable of predicting revision risk one, two, and five years after primary ACL reconstruction with moderate accuracy. The purpose of this study was to determine the external validity of the NKLR model by assessing algorithm performance when applied to patients from the Danish Knee Ligament Registry (DKLR). The primary outcome measure of the NKLR model was probability of revision ACL reconstruction within 1, 2, and/or 5 years. For the index study, 24 total predictor variables in the NKLR were included and the models eliminated variables which did not significantly improve prediction ability - without sacrificing accuracy. The result was a well calibrated algorithm developed using the Cox Lasso model that only required five variables (out of the original 24) for outcome prediction. For this external validation study, all DKLR patients with complete data for the five variables required for NKLR prediction were included. The five variables were: graft choice, femur fixation device, Knee Injury and Osteoarthritis Outcome Score (KOOS) Quality of Life subscale score at surgery, years from injury to surgery, and age at surgery. Predicted revision probabilities were calculated for all DKLR patients. The model performance was assessed using the same metrics as the NKLR study: concordance and calibration. In total, 10,922 DKLR patients were included for analysis. Average follow-up time or time-to-revision was 8.4 (±4.3) years and overall revision rate was 6.9%. Surgical technique trends (i.e., graft choice and fixation devices) and injury characteristics (i.e., concomitant meniscus and cartilage pathology) were dissimilar between registries. The model produced similar concordance when applied to the DKLR population compared to the original NKLR test data (DKLR: 0.68; NKLR: 0.68-0.69). Calibration was poorer for the DKLR population at one and five years post primary surgery but similar to the NKLR at two years. The NKLR machine learning algorithm demonstrated similar performance when applied to patients from the DKLR, suggesting that it is valid for application outside of the initial patient population. This represents the first machine learning model for predicting revision ACL reconstruction that has been externally validated. Clinicians can use this in-clinic calculator to estimate revision risk at a patient specific level when discussing outcome expectations pre-operatively. While encouraging, it should be noted that the performance of the model on patients undergoing ACL reconstruction outside of Scandinavia remains unknown

Approximately 20% of patients feel unsatisfied 12 months after primary total knee arthroplasty (TKA). Current predictive tools for TKA focus on the clinician as the intended user rather than the patient. The aim of this study is to develop a tool that can be used by patients without clinician assistance, to predict health-related quality of life (HRQoL) outcomes 12 months after total knee arthroplasty (TKA). All patients with primary TKAs for osteoarthritis between 2012 and 2019 at a tertiary institutional registry were analysed. The predictive outcome was improvement in Veterans-RAND 12 utility score at 12 months after surgery. Potential predictors included patient demographics, co-morbidities, and patient reported outcome scores at baseline. Logistic regression and three machine learning algorithms were used. Models were evaluated using both discrimination and calibration metrics. Predictive outcomes were categorised into deciles from 1 being the least likely to improve to 10 being the most likely to improve. 3703 eligible patients were included in the analysis. The logistic regression model performed the best in out-of-sample evaluation for both discrimination (AUC = 0.712) and calibration (gradient = 1.176, intercept = -0.116, Brier score = 0.201) metrics. Machine learning algorithms were not superior to logistic regression in any performance metric. Patients in the lowest decile (1) had a 29% probability for improvement and patients in the highest decile (10) had an 86% probability for improvement. Logistic regression outperformed machine learning algorithms in this study. The final model performed well enough with calibration metrics to accurately predict improvement after TKA using deciles. An ongoing randomised controlled trial (ACTRN12622000072718) is evaluating the effect of this tool on patient willingness for surgery. Full results of this trial are expected to be available by April 2023. A free-to-use online version of the tool is available at . smartchoice.org.au.

Background. Magnetic resonance imaging (MRI) algorithm identifies end stage severely degenerated disc as ‘black’, and a moderately degenerate to non-degenerated disc as ‘white’. MRI is based on signal intensity changes that identifies loss of proteoglycans, water, and general radial bulging but lacks association with microscopic features such as fissure, endplate damage, persistent inflammatory catabolism that facilitates proteoglycan loss leading to ultimate collapse of annulus with neo-innervation and vascularization, as an indicator of pain. Thus, we propose a novel machine learning based imaging tool that combines quantifiable microscopic histopathological features with macroscopic signal intensities changes for hybrid assessment of disc degeneration. Methods. 100-disc tissue were collected from patients undergoing surgeries and cadaveric controls, age range of 35–75 years. MRI Pfirrmann grades were collected in each case, and each disc specimen were processed to identify the 1) region of interest 2) analytical imaging vector 3) data assimilation, grading and scoring pattern 4) identification of machine learning algorithm 5) predictive learning parameters to form an interface between hardware and software operating system. Results. Kernel algorithm defines non-linear data in xy histogram. X,Y values are scored histological spatial variables that signifies loss of proteoglycans, blood vessels ingrowth, and occurrence of tears or fissures in the inner and outer annulus regions mapped with the dampening and graded series of signal intensity changes. Conclusion. To our knowledge this study is the first to propose a machine learning method between microscopic spatial tissue changes and macroscopic signal intensity grades in the intervertebral disc. No conflict of interest declared.  . Sources of Funding. ICMR/5/4-5/3/42/Neuro/2022-NCD-1, Dr TMA PAI SMU/ 131/ REG/ TMA PURK/ 164/2020. A part of the above study was presented as an oral paper at the International Society for the Study of Lumbar Spine (ISSLS) meeting held on 1–5. th. May 2023, Melbourne, Australia

The December 2023 Research Roundup. 360. looks at: Tissue integration and chondroprotective potential of acetabular labral augmentation with autograft tendon: study of a porcine model; The Irish National Orthopaedic Register under cyberattack: what happened, and what were the consequences?; An overview of machine learning in orthopaedic surgery: an educational paper; Beware of the fungus…; New evidence for COVID-19 in patients undergoing joint replacement surgery

The June 2023 Hip & Pelvis Roundup. 360. looks at: Machine learning to identify surgical candidates for hip and knee arthroplasty: a viable option?; Poor outcome after debridement and implant retention; Can you cement polyethylene liners into well-fixed acetabular shells in hip revision?; Revision stem in primary arthroplasties: the Exeter 44/0 125 mm stem; Depression and anxiety: could they be linked to infection?; Does where you live affect your outcomes after hip and knee arthroplasties?; Racial disparities in outcomes after total hip arthroplasty and total knee arthroplasty are substantially mediated by socioeconomic disadvantage both in black and white patients

Introduction. Machine learning is a relatively novel method to orthopaedics which can be used to evaluate complex associations and patterns in outcomes and healthcare data. The purpose of this study is to utilize 3 different supervised machine learning algorithms to evaluate outcomes from a multi-center international database of a single shoulder prosthesis to evaluate the accuracy of each model to predict post-operative outcomes of both aTSA and rTSA. Methods. Data from a multi-center international database consisting of 6485 patients who received primary total shoulder arthroplasty using a single shoulder prosthesis (Equinoxe, Exactech, Inc) were analyzed from 19,796 patient visits in this study. Specifically, demographic, comorbidity, implant type and implant size, surgical technique, pre-operative PROMs and ROM measures, post-operative PROMs and ROM measures, pre-operative and post-operative radiographic data, and also adverse event and complication data were obtained for 2367 primary aTSA patients from 8042 visits at an average follow-up of 22 months and 4118 primary rTSA from 11,754 visits at an average follow-up of 16 months were analyzed to create a predictive model using 3 different supervised machine learning techniques: 1) linear regression, 2) random forest, and 3) XGBoost. Each of these 3 different machine learning techniques evaluated the pre-operative parameters and created a predictive model which targeted the post-operative composite score, which was a 100 point score consisting of 50% post-operative composite outcome score (calculated from 33.3% ASES + 33.3% UCLA + 33.3% Constant) and 50% post-operative composite ROM score (calculated from S curves weighted by 70% active forward flexion + 15% internal rotation score + 15% active external rotation). 3 additional predictive models were created to control for the time required for patient improvement after surgery, to do this, each primary aTSA and primary rTSA cohort was subdivided to only include patient data follow-up visits >20 months after surgery, this yielded 1317 primary aTSA patients from 2962 visits at an average follow-up of 50 months and 1593 primary rTSA from 3144 visits at an average follow-up of 42 months. Each of these 6 predictive models were trained using a random selection of 80% of each cohort, then each model predicted the outcomes of the remaining 20% of the data based upon the demographic, comorbidity, implant type and implant size, surgical technique, pre-operative PROMs and ROM measures inputs of each 20% cohort. The error of all 6 predictive models was calculated from the root mean square error (RMSE) between the actual and predicted post-op composite score. The accuracy of each model was determined by subtracting the percent difference of each RMSE value from the average composite score associated with each cohort. Results. For all patient visits, the XGBoost decision tree algorithm was the most accurate model for both aTSA & rTSA patients, with an accuracy of ∼89.5% for both aTSA and rTSA. However for patients with 20+ month visits only, the random forest decision tree algorithm was the most accurate model for both aTSA & rTSA patients, with an accuracy of ∼89.5% for both aTSA and rTSA. The linear regression model was the least accurate predictive model for each of the cohorts analyzed. However, it should be noted that all 3 machine learning models provided accuracy of ∼85% or better and a RMSE <12. (Table 1) Figures 1 and 2 depict the typical spread and RMSE of the actual vs. predicted total composite score associated with the 3 models for aTSA (Figure 1) and rTSA (Figure 2). Discussion. The results of this study demonstrate that multiple different machine learning algorithms can be utilized to create models that predict outcomes with higher accuracy for both aTSA and rTSA, for numerous timepoints after surgery. Future research should test this model on different datasets and using different machine learning methods in order to reduce over- and under-fitting model errors. For any figures or tables, please contact the authors directly

The August 2023 Hip & Pelvis Roundup. 360. looks at: Using machine learning to predict venous thromboembolism and major bleeding events following total joint arthroplasty; Antibiotic length in revision total hip arthroplasty; Preoperative colonization and worse outcomes; Short stem cemented total hip arthroplasty; What are the outcomes of one- versus two-stage revisions in the UK?; To cement or not to cement? The best approach in hemiarthroplasty; Similar re-revisions in cemented and cementless femoral revisions for periprosthetic femoral fractures in total hip arthroplasty; Are hip precautions still needed?

The June 2024 Hip & Pelvis Roundup. 360. looks at: Machine learning did not outperform conventional competing risk modelling to predict revision arthroplasty; Unravelling the risks: incidence and reoperation rates for femoral fractures post-total hip arthroplasty; Spinal versus general anaesthesia for hip arthroscopy: a COVID-19 pandemic- and opioid epidemic-driven study; Development and validation of a deep-learning model to predict total hip arthroplasty on radiographs; Ambulatory centres lead in same-day hip and knee arthroplasty success; Exploring the impact of smokeless tobacco on total hip arthroplasty outcomes: a deeper dive into postoperative complications

Abstract. Objectives. Spinal disorders such as back pain incur a substantial societal and economic burden. Unfortunately, there is lack of understanding and treatment of these disorders are further impeded by the inability to assess spinal forces in vivo. The aim of this project is to address this challenge by developing and testing a novel image-driven approach that will assess the forces in an individual's spine in vivo by incorporating information acquired from multimodal imaging (magnetic resonance imaging (MRI) and biplane X-rays) in a subject-specific model. Methods. Magnetic resonance and biplane X-ray imaging are used to capture information about the anatomy, tissues, and motion of an individual's spine as they perform a range of everyday activities. This information is then utilised in a subject-specific computational model based on the finite element method to predict the forces in their spine. The project is also utilising novel machine learning algorithms and in vitro, six-axis mechanical testing on human, porcine and bovine samples to develop and test the modelling methods rigorously. Results & Discussion. MRI sequences have been identified that provide high-quality image data and information on different tissue types which will be used to predict subject-specific disc properties. In-vivo protocols to capture motion analysis, EMG muscle activity, and video X-rays of the spine have been designed with planned data collection of 15 healthy volunteers. Preliminary modelling work has evaluated potential machine learning approaches and quantified the sensitivity of the models developed to material properties. Conclusion. The development and testing of these image-driven subject-specific spine models will provide a new tool for determining forces in the spine. It will also provide new tools for measuring and modelling spine movement and quantifying the properties of the spinal tissues. Acknowledgments. Funding from the EPSRC: EP/V036602/1 (Meakin, Holsgrove & Javadi) and EP/V032275/1 (Holt & Williams). Declaration of Interest. (b) declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported:I declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research project

The August 2023 Knee Roundup. 360. looks at: Curettage and cementation of giant cell tumour of bone: is arthritis a given?; Anterior knee pain following total knee arthroplasty: does the patellar cement-bone interface affect postoperative anterior knee pain?; Nickel allergy and total knee arthroplasty; The use of artificial intelligence for the prediction of periprosthetic joint infection following aseptic revision total knee arthroplasty; Ambulatory unicompartmental knee arthroplasty: development of a patient selection tool using machine learning; Femoral asymmetry: a missing piece in knee alignment; Needle arthroscopy – a benefit to patients in the outpatient setting; Can lateral unicompartmental knees be done in a day-case setting?

Introduction. Instability remains a common complication following total hip arthroplasty (THA) and continues to account for the highest percentage of revisions in numerous registries. Many risk factors have been described, yet a patient-specific risk assessment tool remains elusive. The purpose of this study was to apply a machine learning algorithm to develop a patient-specific risk score capable of dynamic adjustment based on operative decisions. Methods. 22,086 THA performed between 1998–2018 were evaluated. 632 THA sustained a postoperative dislocation (2.9%). Patients were robustly characterized based on non-modifiable factors: demographics, THA indication, spinal disease, spine surgery, neurologic disease, connective tissue disease; and modifiable operative decisions: surgical approach, femoral head size, acetabular liner (standard/elevated/constrained/dual-mobility). Models were built with a binary outcome (event/no event) at 1-year and 5-year postoperatively. Inverse Probability Censoring Weighting accounted for censoring bias. An ensemble algorithm was created that included Generalized Linear Model, Generalized Additive Model, Lasso Penalized Regression, Kernel-Based Support Vector Machines, Random Forest and Optimized Gradient Boosting Machine. Convex combination of weights minimized the negative binomial log-likelihood loss function. Ten-fold cross-validation accounted for the rarity of dislocation events. Results. The 1-year model achieved an area under the curve (AUC)=0.63, sensitivity=70%, specificity=50%, positive predictive value (PPV)=3% and negative predictive value (NPV)=99%. The 5-year model achieved an AUC=0.62, sensitivity=69%, specificity=51%, PPV=7% and NPV=97%. All cohort-level accuracy metrics performed better than chance. The two most influential predictors in the model were surgical approach and acetabular liner. Conclusions. This machine learning algorithm demonstrates high sensitivity and NPV, suggesting screening tool utility. The model is strengthened by a multivariable dataset portending differential dislocation risk. Two modifiable variables (approach and acetabular liner) were the most influential in dislocation risk. Calculator utilization in “app” form could enable individualized risk prognostication. Furthermore, algorithm development through machine learning facilitates perpetual model performance enhancement with future data input

Background. Implant loosening is a common cause of a poor outcome and pain after total knee arthroplasty (TKA). Despite the increase in use of expensive techniques like arthrography, the detection of prosthetic loosening is often unclear pre-operatively, leading to diagnostic uncertainty and extensive workup. The objective of this study was to evaluate the ability of a machine learning (ML) algorithm to diagnose prosthetic loosening from pre-operative radiographs, and to observe what model inputs improve the performance of the model. Methods. 754 patients underwent a first-time revision of a total joint at our institution from 2012–2018. Pre-operative X-Rays (XR) were collected for each patient. AP and lateral X-Rays, in addition to demographic and comorbidity information, were collected for each patient. Each patient was determined to have either loose or fixed prosthetics based on a manual abstraction of the written findings in their operative report, which is considered the gold standard of diagnosing prosthetic loosening. We trained a series of deep convolution neural network (CNN) models to predict if a prosthesis was found to be loose in the operating room from the pre-operative XR. Each XR was pre-processed to segment the bone, implant, and bone-implant interface. A series of CNN models were built using existing, proven CNN architectures and weights optimized to our dataset. We then integrated our best performing model with historical patient data to create a final model and determine the incremental accuracy provided by additional layers of clinical information fed into the model. The models were evaluated by its accuracy, sensitivity and specificity. Results. The CNN we built demonstrated high performance at detecting prosthetic loosening from radiographs alone. Our first model built from scratch on just the image as an input had an accuracy of 70%. Our final model which was built by fine-tuning and optimizing a publicly available model named DenseNet, combining the AP and lateral radiographs, incorporating information from the patient history, had an accuracy, sensitivity, and specificity of 98.5%, 93.9%, and 99.5% on the patients that it was trained on, and an accuracy, sensitivity, and specificity of 88.3%, 70.2%, and 95.6% on the patients it was tested on. Conclusions. The use of machine learning (ML) can accurately detect the presence of prosthetic loosening based on plain radiographs. Its accuracy is progressively enhanced when additional clinical data is added to the loosening analysis algorithm. While this type of machine learning may not be sufficient in its present state of development as a standalone metric of loosening, it is clearly a useful augment for clinical decision making in its present state. Further study and development will be needed to determine the feasibility of applying machine learning as a more definitive test in the clinical setting. For figures, tables, or references, please contact authors directly

Aims. The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. Methods. A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset. Results. The convolutional neural network we built performed well when detecting loosening from radiographs alone. The first model built de novo with only the radiological image as input had an accuracy of 70%. The final model, which was built by fine-tuning a publicly available model named DenseNet, combining the AP and lateral radiographs, and incorporating information from the patient’s history, had an accuracy, sensitivity, and specificity of 88.3%, 70.2%, and 95.6% on the independent test dataset. It performed better for cases of revision THA with an accuracy of 90.1%, than for cases of revision TKA with an accuracy of 85.8%. Conclusion. This study showed that machine learning can detect prosthetic loosening from radiographs. Its accuracy is enhanced when using highly trained public algorithms, and when adding clinical data to the algorithm. While this algorithm may not be sufficient in its present state of development as a standalone metric of loosening, it is currently a useful augment for clinical decision making. Cite this article: Bone Joint J 2020;102-B(6 Supple A):101–106

Technological advancements in orthopaedic surgery have mainly focused on increasing precision during the operation however, there have been few developments in post-operative physiotherapy. We have developed a computer vision program using machine learning that can virtually measure the range of movement of a joint to track progress after surgery. This data can be used by physiotherapists to change patients’ exercise regimes with more objectively and help patients visualise the progress that they have made. In this study, we tested our program's reliability and validity to find a benchmark for future use on patients. We compared 150 shoulder joint angles, measured using a goniometer, and those calculated by our program called ArmTracking in a group of 10 participants (5 males and 5 females). Reliability was tested using adjusted R squared and validity was tested using 95% limits of agreement. Our clinically acceptable limit of agreement was ± 10° for ArmTracking to be used interchangeably with goniometry. ArmTracking showed excellent overall reliability of 97.1% when all shoulder movements were combined but there were lower scores for some movements like shoulder extension at 75.8%. There was moderate validity shown when all shoulder movements were combined at 9.6° overestimation and 18.3° underestimation. Computer vision programs have a great potential to be used in telerehabilitation to collect useful information as patients carry out prescribed exercises at home. However, they need to be trained well for precise joint detections to reduce the range of errors in readings

Artificial Intelligence (AI) is becoming more powerful but is barely used to counter the growth in health care burden. AI applications to increase efficiency in orthopedics are rare. We questioned if (1) we could train machine learning (ML) algorithms, based on answers from digitalized history taking questionnaires, to predict treatment of hip osteoartritis (either conservative or surgical); (2) such an algorithm could streamline clinical consultation. Multiple ML models were trained on 600 annotated (80% training, 20% test) digital history taking questionnaires, acquired before consultation. Best performing models, based on balanced accuracy and optimized automated hyperparameter tuning, were build into our daily clinical orthopedic practice. Fifty patients with hip complaints (>45 years) were prospectively predicted and planned (partly blinded, partly unblinded) for consultation with the physician assistant (conservative) or orthopedic surgeon (operative). Tailored patient information based on the prediction was automatically sent to a smartphone app. Level of evidence: IV. Random Forest and BernoulliNB were the most accurate ML models (0.75 balanced accuracy). Treatment prediction was correct in 45 out of 50 consultations (90%), p<0.0001 (sign and binomial test). Specialized consultations where conservatively predicted patients were seen by the physician assistant and surgical patients by the orthopedic surgeon were highly appreciated and effective. Treatment strategy of hip osteoartritis based on answers from digital history taking questionnaires was accurately predicted before patients entered the hospital. This can make outpatient consultation scheduling more efficient and tailor pre-consultation patient education

Currently implemented accuracy metrics in open-source libraries for segmentation by supervised machine learning are typically one-dimensional scores [1]. While extremely relevant to evaluate applicability in clinics, anatomical location of segmentation errors is often neglected. This study aims to include the three-dimensional (3D) spatial information in the development of a novel framework for segmentation accuracy evaluation and comparison between different methods. Predicted and ground truth (manually segmented) segmentation masks are meshed into 3D surfaces. A template mesh of the same anatomical structure is then registered to all ground truth 3D surfaces. This ensures all surface points on the ground truth meshes to be in the same anatomically homologous order. Next, point-wise surface deviations between the registered ground truth mesh and the meshed segmentation prediction are calculated and allow for color plotting of point-wise descriptive statistics. Statistical parametric mapping includes point-wise false discovery rate (FDR) adjusted p-values (also referred to as q-values). The framework reads volumetric image data containing the segmentation masks of both ground truth and segmentation prediction. 3D color plots containing descriptive statistics (mean absolute value, maximal value,…) on point-wise segmentation errors are rendered. As an example, we compared segmentation results of nnUNet [2], UNet++ [3] and UNETR [4] by visualizing the mean absolute error (surface deviation from ground truth) as a color plot on the 3D model of bone and cartilage of the mean distal femur. A novel framework to evaluate segmentation accuracy is presented. Output includes anatomical information on the segmentation errors, as well as point-wise comparative statistics on different segmentation algorithms. Clearly, this allows for a better informed decision-making process when selecting the best algorithm for a specific clinical application

Background. Postoperative recovery after routine total hip arthroplasty (THA) can lead to the development of prolonged opioid use but there are few tools for predicting this adverse outcome. The purpose of this study was to develop machine learning algorithms for preoperative prediction of prolonged post-operative opioid use after THA. Methods. A retrospective review of electronic health records was conducted at two academic medical centers and three community hospitals to identify adult patients who underwent THA for osteoarthritis between January 1. st. , 2000 and August 1. st. , 2018. Prolonged postoperative opioid prescriptions were defined as continuous opioid prescriptions after surgery to at least 90 days after surgery. Five machine learning algorithms were developed to predict this outcome and were assessed by discrimination, calibration, and decision curve analysis. Results. Overall, 5507 patients underwent THA, of which 345 (6.3%) had prolonged postoperative opioid prescriptions. The factors determined for prediction of prolonged postoperative opioid prescriptions were: age, duration of pre-operative opioid exposure, preoperative hemoglobin, and certain preoperative medications (anti-depressants, benzodiazepines, non-steroidal anti-inflammatory drugs, and beta-2-agonists). The elastic-net penalized logistic regression model achieved the best performance across discrimination (c-statistic = 0.77), calibration, and decision curve analysis. This model was incorporated into a digital application able to provide both predictions and explanations; available here: . https://sorg-apps.shinyapps.io/thaopioid/. Conclusion. If externally validated in independent populations, the algorithms developed in this study could improve preoperative screening and support for THA patients at high-risk for prolonged postoperative opioid use. Early identification and intervention in high-risk cases may mitigate the long-term adverse consequence of opioid dependence. For any tables or figures, please contact the authors directly

Serial section electron microscopy (SSEM) was initially developed to map the neural connections in the brain. SSEM eventually led to the term ‘Connectomics’ to be coined to describe process of following a cell or structure through a volume of tissue. This permits the true three-dimensionality to be appreciated and relationships between cells and structures. The purpose of this study was to utilize this methodology to interrogate S. aureus infected bone. Bone samples were harvested from mice tibia infected with S. aureus and were fixed, decalcified, and osmicated. The samples were paraffin embedded and 5-micron sections were cut to identify regions of bacterial invasion into the osteocyte-lacuna-canalicular-network (OLCN). This area was cut from the paraffin block, deparaffinized, post-fixed and reprocessed into epoxy resin. Serial sections were cut at 60nm and collected onto Kapton tape utilizing the Automated Tape-collecting Ultramicrotome (ATUMtome) system. Samples were mounted onto 4” silicon wafers and post-stained with 2% uranyl acetate followed by 0.3% lead citrate and carbon coated. A ZEISS GeminiSEM 450 scanning electron microscope fitted with an electron backscatter diffusion detector was used to image the sections. The image stack was aligned and segmented using the open-source software, VASTlite. 264 serial sections were imaged, representing approximately 40 × 45 × 15-micron (x, y, z) volume of tissue. 70% of the canaliculi demonstrated infiltration by S. aureus. This study demonstrates that SSEM can be applied to the skeletal system and provide a new solution to investigate the OLCN system. It is feasible that this methodology could be implemented to investigate why some canaliculi are resistant to colonization and potentially opens up a new direction for the prevention of chronic osteomyelitis. In order to make this a realistic target, automated segmentation methodologies utilizing machine learning must be developed and applied to the bone tissue datasets

Gait analysis is an indispensable tool for scientific assessment and treatment of individuals whose ability to walk is impaired. The high cost of installation and operation are a major limitation for wide-spread use in clinical routine. Advances in Artificial Intelligence (AI) could significantly reduce the required instrumentation. A mobile phone could be all equipment necessary for 3D gait analysis. MediaPipe Pose provided by Google Research is such a Machine Learning approach for human body tracking from monocular RGB video frames that is detecting 3D-landmarks of the human body. Aim of this study was to analyze the accuracy of gait phase detection based on the joint landmarks identified by the AI system. Motion data from 10 healthy volunteers walking on a treadmill with a fixed speed of 4.5km/h (Callis, Sprintex, Germany) was sampled with a mobile phone (iPhone SE 2nd Generation, Apple). The video was processed with Mediapipe Pose (Version 0.9.1.0) using custom python software. Gait phases (Initial Contact - IC and Toe Off - TO) were detected from the angular velocities of the lower legs. For the determination of ground truth, the movement was simultaneously recorded with the AS-200 System (LaiTronic GmbH, Innsbruck, Austria). The number of detected strides, the error in IC detection and stance phase duration was calculated. In total, 1692 strides were detected from the reference system during the trials from which the AI-system identified 679 strides. The absolute mean error (AME) in IC detection was 39.3 ± 36.6 ms while the AME for stance duration was 187.6 ± 140 ms. Landmark detection is a challenging task for the AI-system as can clearly be seen be the rate of only 40% detected strides. As mentioned by Fadillioglu et al., error in TO-detection is higher than in IC-detection

Periacetabular Osteotomy (PAO) has become the most important surgical procedure for patients with hip dysplasia, offering significant pain relief and improved joint function. This study focuses on recovery after PAO, specifically the return to sports (RTS) timeline, with the objective of identifying preoperative predictors to optimize patient outcomes. Our prospective, monocentric study from 2019 to 2023 included 698 hips from 606 patients undergoing PAO. Comprehensive preoperative data were collected, including demographic information, clinical assessments (Modified Harris Hip Score (mHHS), International Hip Outcome Tool-12 (iHot-12), Hip Disability and Osteoarthritis Outcome Score (HOOS), UCLA Activity Score) and psychological evaluations (Brief Symptom Inventory (BSI) and SF-36 Health Survey). Advanced logistic regression and machine learning techniques (R Core Team. (2016)) were employed to develop a predictive model. Multivariate regression analysis revealed that several preoperative factors significantly influenced the RTS timeline. These included gender, invasiveness of the surgical approach, preoperative UCLA Score, preoperative sports activity level, mHHS, and various HOOS subscales (Sport/Recreation, Symptoms, Pain) as well as psychological factors (BSI and SF-36). The subsequent model, using a decision tree approach, showed that the combination of a UCLA score greater than 3 (p<0.001), non-female gender (p=0.003), preoperative sports frequency not less than twice per week (p<0.001), participation in high-impact sports preoperatively (p=0.008), and a BSI anxiety score less than 2 (p<0.001) had the highest likelihood of early RTS with a probability of 71.4% at three months. Using a decision tree approach, this model provides a nuanced prediction of RTS after PAO, highlighting the synergy of physical, psychological, and lifestyle influences. By quantifying the impact of these variables, it provides clinicians with a valuable tool for predicting individual patient recovery trajectories, aiding in tailored rehabilitation planning and predicting postoperative satisfaction

Advances in cancer therapy have prolonged patient survival even in the presence of disseminated disease and an increasing number of cancer patients are living with metastatic bone disease (MBD). The proximal femur is the most common long bone involved in MBD and pathologic fractures of the femur are associated with significant morbidity, mortality and loss of quality of life (QoL). Successful prophylactic surgery for an impending fracture of the proximal femur has been shown in multiple cohort studies to result in longer survival, preserved mobility, lower transfusion rates and shorter post-operative hospital stays. However, there is currently no optimal method to predict a pathologic fracture. The most well-known tool is Mirel's criteria, established in 1989 and is limited from guiding clinical practice due to poor specificity and sensitivity. The ideal clinical decision support tool will be of the highest sensitivity and specificity, non-invasive, generalizable to all patients, and not a burden on hospital resources or the patient's time. Our research uses novel machine learning techniques to develop a model to fill this considerable gap in the treatment pathway of MBD of the femur. The goal of our study is to train a convolutional neural network (CNN) to predict fracture risk when metastatic bone disease is present in the proximal femur. Our fracture risk prediction tool was developed by analysis of prospectively collected data of consecutive MBD patients presenting from 2009–2016. Patients with primary bone tumors, pathologic fractures at initial presentation, and hematologic malignancies were excluded. A total of 546 patients comprising 114 pathologic fractures were included. Every patient had at least one Anterior-Posterior X-ray and clinical data including patient demographics, Mirel's criteria, tumor biology, all previous radiation and chemotherapy received, multiple pain and function scores, medications and time to fracture or time to death. We have trained a convolutional neural network (CNN) with AP X-ray images of 546 patients with metastatic bone disease of the proximal femur. The digital X-ray data is converted into a matrix representing the color information at each pixel. Our CNN contains five convolutional layers, a fully connected layers of 512 units and a final output layer. As the information passes through successive levels of the network, higher level features are abstracted from the data. The model converges on two fully connected deep neural network layers that output the risk of fracture. This prediction is compared to the true outcome, and any errors are back-propagated through the network to accordingly adjust the weights between connections, until overall prediction accuracy is optimized. Methods to improve learning included using stochastic gradient descent with a learning rate of 0.01 and a momentum rate of 0.9. We used average classification accuracy and the average F1 score across five test sets to measure model performance. We compute F1 = 2 x (precision x recall)/(precision + recall). F1 is a measure of a model's accuracy in binary classification, in our case, whether a lesion would result in pathologic fracture or not. Our model achieved 88.2% accuracy in predicting fracture risk across five-fold cross validation testing. The F1 statistic is 0.87. This is the first reported application of convolutional neural networks, a machine learning algorithm, to this important Orthopaedic problem. Our neural network model was able to achieve reasonable accuracy in classifying fracture risk of metastatic proximal femur lesions from analysis of X-rays and clinical information. Our future work will aim to externally validate this algorithm on an international cohort

Over 8000 total hip arthroplasties (THA) in the UK were revised in 2019, half for aseptic loosening. It is believed that Artificial Intelligence (AI) could identify or predict failing THA and result in early recognition of poorly performing implants and reduce patient suffering. The aim of this study is to investigate whether Artificial Intelligence based machine learning (ML) / Deep Learning (DL) techniques can train an algorithm to identify and/or predict failing uncemented THA. Consent was sought from patients followed up in a single design, uncemented THA implant surveillance study (2010–2021). Oxford hip scores and radiographs were collected at yearly intervals. Radiographs were analysed by 3 observers for presence of markers of implant loosening/failure: periprosthetic lucency, cortical hypertrophy, and pedestal formation. DL using the RGB ResNet 18 model, with images entered chronologically, was trained according to revision status and radiographic features. Data augmentation and cross validation were used to increase the available training data, reduce bias, and improve verification of results. 184 patients consented to inclusion. 6 (3.2%) patients were revised for aseptic loosening. 2097 radiographs were analysed: 21 (11.4%) patients had three radiographic features of failure. 166 patients were used for ML algorithm testing of 3 scenarios to detect those who were revised. 1) The use of revision as an end point was associated with increased variability in accuracy. The area under the curve (AUC) was 23–97%. 2) Using 2/3 radiographic features associated with failure was associated with improved results, AUC: 75–100%. 3) Using 3/3 radiographic features, had less variability, reduced AUC of 73%, but 5/6 patients who had been revised were identified (total 66 identified). The best algorithm identified the greatest number of revised hips (5/6), predicting failure 2–8 years before revision, before all radiographic features were visible and before a significant fall in the Oxford Hip score. True-Positive: 0.77, False Positive: 0.29. ML algorithms can identify failing THA before visible features on radiographs or before PROM scores deteriorate. This is an important finding that could identify failing THA early

Excessive resident duty hours (RDH) are a recognized issue with implications for physician well-being and patient safety. A major component of the RDH concern is on-call duty. While considerable work has been done to reduce resident call workload, there is a paucity of research in optimizing resident call scheduling. Call coverage is scheduled manually rather than demand-based, which generally leads to over-scheduling to prevent a service gap. Machine learning (ML) has been widely applied in other industries to prevent such issues of a supply-demand mismatch. However, the healthcare field has been slow to adopt these innovations. As such, the aim of this study was to use ML models to 1) predict demand on orthopaedic surgery residents at a level I trauma centre and 2) identify variables key to demand prediction. Daily surgical handover emails over an eight year (2012-2019) period at a level I trauma centre were collected. The following data was used to calculate demand: spine call coverage, date, and number of operating rooms (ORs), traumas, admissions and consults completed. Various ML models (linear, tree-based and neural networks) were trained to predict the workload, with their results compared to the current scheduling approach. Quality of models was determined by using the area under the receiver operator curve (AUC) and accuracy of the predictions. The top ten most important variables were extracted from the most successful model. During training, the model with the highest AUC and accuracy was the multivariate adaptive regression splines (MARS) model, with an AUC of 0.78±0.03 and accuracy of 71.7%±3.1%. During testing, the model with the highest AUC and accuracy was the neural network model, with an AUC of 0.81 and accuracy of 73.7%. All models were better than the current approach, which had an AUC of 0.50 and accuracy of 50.1%. Key variables used by the neural network model were (descending order): spine call duty, year, weekday/weekend, month, and day of the week. This was the first study attempting to use ML to predict the service demand on orthopaedic surgery residents at a major level I trauma centre. Multiple ML models were shown to be more appropriate and accurate at predicting the demand on surgical residents as compared to the current scheduling approach. Future work should look to incorporate predictive models with optimization strategies to match scheduling with demand in order to improve resident well being and patient care

Most cost containment efforts in public health systems have focused on regulating the use of hospital resources, especially operative time. As such, attempting to maximize the efficiency of limited operative time is important. Typically, hospital operating room (OR) scheduling of time is performed in two tiers: 1) master surgical scheduling (annual allocation of time between surgical services and surgeons) and 2) daily scheduling (a surgeon's selection of cases per operative day). Master surgical scheduling is based on a hospital's annual case mix and depends on the annual throughput rate per case type. This throughput rate depends on the efficiency of surgeons’ daily scheduling. However, daily scheduling is predominantly performed manually, which requires that the human planner simultaneously reasons about unknowns such as case-specific length-of-surgery and variability while attempting to maximize throughput. This often leads to OR overtime and likely sub-optimal throughput rate. In contrast, scheduling using mathematical and optimization methods can produce maximum systems efficiency, and is extensively used in the business world. As such, the purpose of our study was to compare the efficiency of 1) manual and 2) optimized OR scheduling at an academic-affiliated community hospital representative of most North American centres. Historic OR data was collected over a four year period for seven surgeons. The actual scheduling, surgical duration, overtime and number of OR days were extracted. This data was first configured to represent the historic manual scheduling process. Following this, the data was then used as the input to an integer linear programming model with the goal of determining the minimum number of OR days to complete the same number of cases while not exceeding the historic overtime values. Parameters included the use of a different quantile for each case type's surgical duration in order to ensure a schedule within five percent of the historic overtime value per OR day. All surgeons saw a median 10% (range: 9.2% to 18.3%) reduction in the number of OR days needed to complete their annual case-load compared to their historical scheduling practices. Meanwhile, the OR overtime varied by a maximum of 5%. The daily OR configurations differed from historic configurations in 87% of cases. In addition, the number of configurations per surgeon was reduced from an average of six to four. Our study demonstrates a significant increase in OR throughput rate (10%) with no change in operative time required. This has considerable implications in terms of cost reduction, surgical wait lists and surgeon satisfaction. A limitation of this study was that the potential gains are based on the efficiency of the pre-existing manual scheduling at our hospital. However, given the range of scenarios tested, number of surgeons included and the similarity of our hospital size and configuration to the majority of North American hospitals with an orthopedic service, these results are generalizable. Further optimization may be achieved by taking into account factors that could predict case duration such as surgeon experience, patients characteristics, and institutional attributes via machine learning

Abstract. Objectives. Biomechanics is an essential form of measurement in the understanding of the development and progression of osteoarthritis (OA). However, the number of participants in biomechanical studies are often small and there is limited ways to share or combine data from across institutions or studies. This is essential for applying modern machine learning methods, where large, complex datasets can be used to identify patterns in the data. Using these data-driven approaches, it could be possible to better predict the optimal interventions for patients at an early stage, potentially avoiding pain and inappropriate surgery or rehabilitation. In this project we developed a prototype database platform for combining and sharing biomechanics datasets. The database includes methods for importing and standardising data and associated variables, to create a seamless, searchable combined dataset of both healthy and knee OA biomechanics. Methods. Data was curated through calls to members of the OATech Network+ (. https://www.oatechnetwork.org/. ). The requirements were 3D motion capture data from previous studies that related to analysing the biomechanics of knee OA, including participants with OA at any stage of progression plus healthy controls. As a minimum we required kinematic data of the lower limbs, plus associated kinetic data (i.e. ground reaction forces). Any additional, complementary data such as EMG could also be provided. Relevant ethical approvals had to be in place that allowed re-use of the data for other research purposes. The datasets were uploaded to a University hosted cloud platform. The database platform was developed using Javascript and hosted on a Windows server, located and managed within the department. Results. Three independent datasets were curated following the call to OATech Network+ members. These originated from separate studies collected from biomechanics labs at Cardiff University, Keele University, and Imperial College London. Participants with knee OA were at various stages of progression and all datasets included healthy controls. The total sample size of the three datasets is n=244, split approximately equally between healthy and knee OA participants. Naming conventions and formatting of the exported data varied greatly across datasets. Datasets were therefore formatted into a common format prior to upload, with guidelines developed for future contributions. Uploading data at the marker set level was too complicated for combination at the prototype stage. Therefore, processed variables relating to joint angles and joint moments were used. The resulting prototype database included an import function to align and standardise variables. A a simple query tool was further developed to extract outputs from the database, along with a suitable user interface for basic data exploration. Conclusion. Combining biomechanics dataset presents a wide range of challenges from both a technical and data governance context. Here we have taken the first steps to demonstrate a proof-of-concept that can combine heterogenous data from independent OA-related biomechanics studies into a combined, searchable resource. Expanding this in the future to a fully open access database will create an essential resource that will facilitate the application of data-driven models and analyses for better understanding, stratification and prediction of OA progression. Declaration of Interest. (b) declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported:I declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research project

Total knee and hip arthroplasty (TKA and THA) are two of the highest volume and resource intensive surgical procedures. Key drivers of the cost of surgical care are duration of surgery (DOS) and postoperative inpatient length of stay (LOS). The ability to predict TKA and THA DOS and LOS has substantial implications for hospital finances, scheduling and resource allocation. The goal of this study was to predict DOS and LOS for elective unilateral TKAs and THAs using machine learning models (MLMs) constructed on preoperative patient factors using a large North American database. The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for elective unilateral TKA and THA procedures from 2014-2019. The dataset was split into training, validation and testing based on year. Multiple conventional and deep MLMs such as linear, tree-based and multilayer perceptrons (MLPs) were constructed. The models with best performance on the validation set were evaluated on the testing set. Models were evaluated according to 1) mean squared error (MSE), 2) buffer accuracy (the number of times the predicted target was within a predesignated buffer of the actual target), and 3) classification accuracy (the number of times the correct class was predicted by the models). To ensure useful predictions, the results of the models were compared to a mean regressor. A total of 499,432 patients (TKA 302,490; THA 196,942) were included. The MLP models had the best MSEs and accuracy across both TKA and THA patients. During testing, the TKA MSEs for DOS and LOS were 0.893 and 0.688 while the THA MSEs for DOS and LOS were 0.895 and 0.691. The TKA DOS 30-minute buffer accuracy and ≤120 min, >120 min classification accuracy were 78.8% and 88.3%, while the TKA LOS 1-day buffer accuracy and ≤2 days, >2 days classification accuracy were 75.2% and 76.1%. The THA DOS 30-minute buffer accuracy and ≤120 min, >120 min classification accuracy were 81.6% and 91.4%, while the THA LOS 1-day buffer accuracy and ≤2 days, >2 days classification accuracy were 78.3% and 80.4%. All models across both TKA and THA patients were more accurate than the mean regressors for both DOS and LOS predictions across both buffer and classification accuracies. Conventional and deep MLMs have been effectively implemented to predict the DOS and LOS of elective unilateral TKA and THA patients based on preoperative patient factors using a large North American database with a high level of accuracy. Future work should include using operational factors to further refine these models and improve predictive accuracy. Results of this work will allow institutions to optimize their resource allocation, reduce costs and improve surgical scheduling. Acknowledgements:. The American College of Surgeons National Surgical Quality Improvement Program and the hospitals participating in the ACS NSQIP are the source of the data used herein; they have not verified and are not responsible for the statistical validity of the data analysis or the conclusions derived by the authors

Cobalt chrome alloy is commonly used in joint replacement surgery. However, it is recognised that some patients develop lymphocyte mediated delayed type hypersensitivity (DTH) responses to this material, which may result in extensive bone and soft tissue destruction. Phase 1. United Kingdom: From an existing database, we identified extreme phenotype patient groups following metal on metal (MoM) hip resurfacing or THR: ALVAL with low wearing prostheses; ALVAL with high wear; no ALVAL with high wear; and asymptomatic patients with implants in situ for longer than ten years. Class I and II HLA genotype frequency distributions were compared between these patients’ groups, and in silico peptide binding studies were carried out using validated methodology. Phase 2. United Kingdom: We expanded the study to include more patients, including those with intermediary phenotypes to test whether an algorithm could be developed incorporating “risk genotypes”, patient age, sex and metal exposure. This model was trained in phase 3. Phase 3. United Kingdom, Australia, United States. Patients from other centres were invited to give DNA samples. The data set was split in two. 70% was used to develop machine learning models to predict failure secondary to DTH. The predictions were tested using the remaining blinded 30% of data, using time-dependent AUROCs, and integrated calibration index performance statistics. A total of 606 DNA samples, from 397 males and 209 female patients, were typed. This included 176 from patients with failed prostheses, and 430 from asymptomatic patients at a mean of >10 years follow up. C-index and ROC(t) scores suggested a high degree of discrimination, whilst the IBS indicated good calibration and further backed up the indication of high discriminatory ability. At ten years, the weighted mean survival probability error was < 4%. At present, there are no tests in widespread clinical use which use a patient's genetic profile to guide implant selection or inform post-operative management. The algorithm described herein may address this issue and we suggest that the application may not be restricted to the field of MoM hip arthroplasty

Aim. While metagenomic (microbial DNA) sequencing technologies can detect the presence of microbes in a clinical sample, it is unknown whether this signal represents dead or live organisms. Metatranscriptomics (sequencing of RNA) offers the potential to detect transcriptionally “active” organisms within a microbial community, and map expressed genes to functional pathways of interest (e.g. antibiotic resistance). We used this approach to evaluate the utility of metatrancriptomics to diagnose PJI and predict antibiotic resistance. Method. In this prospective study, samples were collected from 20 patients undergoing revision TJA (10 aseptic and 10 infected) and 10 primary TJA. Synovial fluid and peripheral blood samples were obtained at the time of surgery, as well as negative field controls (skin swabs, air swabs, sterile water). All samples were shipped to the laboratory for metatranscriptomic analysis. Following microbial RNA extraction and host analyte subtraction, metatranscriptomic sequencing was performed. Bioinformatic analyses were implemented prior to mapping against curated microbial sequence databases– to generate taxonomic expression profiles. Principle Coordinates Analysis (PCoA) and Partial Least Squares-Discriminant Analysis were utilized to ordinate metatranscriptomic profiles, using the 2018 definition of PJI as the gold-standard. Results. After RNA metatranscriptomic analysis, blinded PCoA modeling revealed accurate and distinct clustering of samples into 3 separate cohorts (infected, aseptic, and primary joints) – based on their active transcriptomic profile, both in synovial fluid and blood (synovial anosim p=0.001; blood anosim p=0.034). Differential metatranscriptomic signatures for infected versus noninfected cohorts enabled us to train machine learning algorithms to 84.9% predictive accuracy for infection. Multiple antibiotic resistance genes were expressed, with high concordance to conventional antibiotic sensitivity data. Conclusions. Our findings highlight the potential of metatranscriptomics for infection diagnosis. To our knowledge, this is the first report of RNA sequencing in the orthopaedic literature. Further work in larger patient cohorts will better inform deep learning approaches to improve accuracy, predictive power, and clinical utility of this technology

During OA the homeostasis of healthy articular chondrocytes is dysregulated, which leads to a phenotypical transition of the cells, further influenced by external stimuli. Chondrocytes sense those stimuli, integrate them at the intracellular level and respond by modifying their secretory and molecular state. This process is controlled by a complex interplay of intracellular factors. Each factor is influenced by a myriad of feedback mechanisms, making the prediction of what will happen in case of external perturbation challenging. Hampering the hypertrophic phenotype has emerged as a potential therapeutic strategy to help OA patients (Ripmeester et al. 2018). Therefore, we developed a computational model of the chondrocyte's underlying regulatory network (RN) to identify key regulators as potential drug targets. A mechanistic mathematical model of articular chondrocyte differentiation was implemented with a semi-quantitative formalism. It is composed of a protein RN and a gene RN(GRN) and developed by combining two strategies. First, we established a mechanistic network based on accumulation of decades of biological knowledge. Second, we combined that mechanistic network with data-driven modelling by inferring an OA-GRN using an ensemble of machine learning methods. This required a large gene expression dataset, provided by distinct public microarrays merged through an in-house pipeline for cross-platform integration. We successfully merged various micro-array experiments into one single dataset where the biological variance was predominant over the batch effect from the different technical platforms. The gain of information provided by this merge enabled us to reconstruct an OA-GRN which subsequently served to complete our mechanistic model. With this model, we studied the system's multi-stability, equating the model's stable states to chondrocyte phenotypes. The network structure explained the occurrence of two biologically relevant phenotypes: a hypertrophic-like and a healthy-like phenotype, recognized based on known cell state markers. Second, we tested several hypotheses that could trigger the onset of OA to validate the model with relevant biological phenomena. For instance, forced inflammation pushed the chondrocyte towards hypertrophy but this was partly rescued by higher levels of TGF-β. However, we could annihilate this rescue by concomitantly mimicking an increase in the ALK1/ALK5 balance. Finally, we performed a screening of in-silico (combinatorial) perturbations (inhibitions and/or over-activations) to identify key molecular factors involved in the stability of the chondrocyte state. More precisely, we looked for the most potent conditions for decreasing hypertrophy. Preliminary validation experiments have confirmed that PKA activation could decrease the hypertrophic phenotype in primary chondrocytes. Importantly the in-silico results highlighted that targeting two factors at the same time would greatly help reducing hypertrophic changes. A priori testing of conditions with in-silico models may cut time and cost of experiments via target prioritization and opens new routes for OA combinatorial therapies

Background. Advanced technologies, like robotics, provide enhanced precision for implanting total knee arthroplasty (TKA) components; however, optimal component position and limb alignment remain unknown. This study purpose was to identify the ideal target sagittal component position and coronal limb alignment that produce optimal clinical outcomes. Methods. A retrospective review of 1,091 consecutive TKAs was performed. All TKAs were PCL retaining or sacrificing with anterior lipped (49.4%) or conforming bearings (50.6%) performed with modern perioperative protocols. Posterior tibial slope, femoral flexion, and tibiofemoral limb alignment were measured with a standardized protocols. Patients were grouped by the ‘how often does your knee feel normal?’ outcome score at latest follow-up. Machine learning algorithms were used to identify optimal alignment zones which predicted improved outcomes scores. Results. Mean age and BMI were 66 years and 34 kg/m. 2. with 67% female. Demographics and relevant covariates did not affect outcomes (p≥0.145) except for BMI (p=0.077) but the difference was not clinically significant. For sagittal alignment, approximating native tibial slope within 0 to +2° with some amount of femoral flexion within 0 to +3° (possibly up to +9°) was predictive of knees always feeling normal. For knees in preoperative varus or neutral, knees were more likely to always feel normal when postoperative tibiofemoral alignment was in varus (>−1°). Knees aligned in valgus preoperatively were more likely to always feel normal in valgus (<−7°) or varus (>−4°) postoperatively. Conclusion. Superior patient-reported outcomes correlated with approximating native tibial slope and incorporating some femoral flexion while maintaining similar preoperative coronal limb alignment. Excessive deviation from native tibial slope, excessive femoral flexion or any femoral component extension, or coronal alignment overcorrection beyond the preoperative limb alignment correlated with worse outcomes

Introduction. Clinical decision support tools are software that match the input characteristics of an individual patient to an established knowledge base to create patient-specific assessments that support and better inform individualized healthcare decisions. Clinical decision support tools can facilitate better evidence-based care and offer the potential for improved treatment quality and selection, shared decision making, while also standardizing patient expectations. Methods. Predict+ is a novel, clinical decision support tool that leverages clinical data from the Exactech Equinoxe shoulder clinical outcomes database, which is composed of >11,000 shoulder arthroplasty patients using one specific implant type from more than 30 different clinical sites using standardized forms. Predict+ utilizes multiple coordinated and locked supervised machine learning algorithms to make patient-specific predictions of 7 outcome measures at multiple postoperative timepoints (from 3 months to 7 years after surgery) using as few as 19 preoperative inputs. Predict+ algorithms predictive accuracy for the 7 clinical outcome measures for each of aTSA and rTSA were quantified using the mean absolute error and the area under the receiver operating curve (AUROC). Results. Predict+ was released in November 2020 and is currently in limited launch in the US and select international markets. Predict+ utilizes an interactive graphical user interface to facilitate efficient entry of the preoperative inputs to generate personalized predictions of 7 clinical outcome measures achieved with aTSA and rTSA. Predict+ outputs a simple, patient-friendly graphical overview of preoperative status and a personalized 2-year outcome summary of aTSA and rTSA predictions for all 7 outcome measures to aid in the preoperative patient consultation process. Additionally, Predict+ outputs a detailed line-graph view of a patient's preoperative status and their personalized aTSA, rTSA, and aTSA vs. rTSA predicted outcomes for the 7 outcome measures at 6 postoperative timepoints. For each line-graph, the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) patient-satisfaction improvement thresholds are displayed to aid the surgeon in assessing improvement potential for aTSA and rTSA and also relative to an average age and gender matched patient. The initial clinical experience of Predict+ has been positive. Input of the preoperative patient data is efficient and generally completed in <5 minutes. However, continued workflow improvements are necessary to limit the occurrence of responder fatigue. The graphical user interface is intuitive and facilitated a rapid assessment of expected patient outcomes. We have not found the use of this tool to be disruptive of our clinic's workflow. Ultimately, this tool has positively shifted the preoperative consultation towards discussion of clinical outcomes data, and that has been helpful to guide a patient's understanding of what can be realistically achieved with shoulder arthroplasty. Discussion and Conclusions. Predict+ aims to improve a surgeon's ability to preoperatively counsel patients electing to undergo shoulder arthroplasty. We are hopeful this innovative tool will help align surgeon and patient expectations and ultimately improve patient satisfaction with this elective procedure. Future research is required, but our initial experience demonstrates the positive potential of this predictive tool

To explore a novel machine learning model to evaluate the vertebral fracture risk using Decision Tree model and train the model by Bone Mineral Density (BMD) of different compartments of vertebral body. We collected a Computed Tomography image dataset, including 10 patients with osteoporotic fracture and 10 patients without osteoporotic fracture. 40 non-fracture Vertebral bodies from T11 to L5 were segmented from 10 patients with osteoporotic fracture in the CT database and 53 non-fracture Vertebral bodies from T11 to L5 were segmented from 10 patients without osteoporotic fracture in the CT database. Based on the biomechanical properties, 93 vertebral bodies were further segmented into 11 compartments: eight trabecular bone, cortical shell, top and bottom endplate. BMD of these 11 compartments was calculated based on the HU value in CT images. Decision tree model was used to build fracture prediction model, and Support Vector Machine was built as a compared model. All BMD data was shuffled to a random order. 70% of data was used as training data, and 30% left was used as test data. Then, training prediction accuracy and testing prediction accuracy were calculated separately in the two models. The training accuracy of Decision Tree model is 100% and testing accuracy is 92.14% after trained by BMD data of 11 compartments of the vertebral body. The type I error is 7.14% and type II error is 0%. The training accuracy of Support Vector Machine model is 100% and the testing accuracy is 78.57%. The type I error is 17.86% and type II error is 3.57%. The performance of vertebral body fracture prediction using Decision Tree is significantly higher than using Support Vector Machine. The Decision Tree model is a potential risk assessment method for clinical application. The pilot evidence showed that Decision Tree prediction model overcomes the overfitting drawback of Support Vector Machine Model. However, larger dataset and cohort study should be conducted for further evidence

Participation in a physical therapy program is considered one of the greatest predictors for successful conservative management of common shoulder disorders, however, adherence to standard exercise protocols is often poor (around 50%) and typically worse for unsupervised home exercise programs. Currently, there are limited tools available for objective measurement of adherence and performance of shoulder rehabilitation in the home setting. The goal of this study was to develop and evaluate the potential for performing home shoulder physiotherapy monitoring using a commercial smartwatch. We hypothesize that shoulder physiotherapy exercises can be classified by analyzing the temporal sequence of inertial sensor outputs from a smartwatch worn on the extremity performing the exercise. Twenty healthy adult subjects with no prior shoulder disorders performed seven exercises from a standard evidence-based rotator cuff physiotherapy protocol: pendulum, abduction, forward elevation, internal/external rotation and trapezius extension with a resistance band, and a weighted bent-over row. Each participant performed 20 repetitions of each exercise bilaterally under the supervision of an orthopaedic surgeon, while 6-axis inertial sensor data was collected at 50 Hz from an Apple Watch. Using the scikit-learn and keras platforms, four supervised learning algorithms were trained to classify the exercises: k-nearest neighbour (k-NN), random forest (RF), support vector machine classifier (SVC), and a deep convolutional recurrent neural network (CRNN). Algorithm performance was evaluated using 5-fold cross-validation stratified first temporally and then by subject. Categorical classification accuracy was above 94% for all algorithms on the temporally stratified cross validation, with the best performance achieved by the CRNN algorithm (99.4± 0.2%). The subject stratified cross validation, which evaluated classifier performance on unseen subjects, yielded lower accuracies scores again with CRNN performing best (88.9 ± 1.6%). This proof-of concept study demonstrates the feasibility of a smartwatch device and machine learning approach to more easily monitor and assess the at-home adherence of shoulder physiotherapy exercise protocols. Future work will focus on translation of this technology to the clinical setting and evaluating exercise classification in shoulder disorder populations

Quantitative assessment of metastatic involvement of the bony spine is important for assessing disease progression and treatment response. Quantification of metastatic involvement is challenging as tumours may appear as osteolytic (bone resorbing), osteoblastic (bone forming) or mixed. This investigation aimed to develop an automated method to accurately segment osteoblastic lesions in a animal model of metastatically involved vertebrae, imaged with micro computed tomography (μCT). Radiomics seeks to apply standardized features extracted from medical images for the purpose of decision-support as well as diagnosis and treatment planning. Here we investigate the application of radiomic-based features for the delineation of osteoblastic vertebral metastases. Osteoblastic lesions affect bone deposition and bone quality, resulting in a change in the texture of bony material physically seen through μCT imaging. We hypothesize that radiomics based features will be sensitive to changes in osteoblastic lesion bone texture and that these changes will be useful for automating segmentation. Osteoblastic metastases were generated via intracardiac injection of human ZR-75-1 breast cancer cells into a preclinical athymic rat model (n=3). Four months post inoculation, ex-vivo μCT images (µCT100, Scanco) were acquired of each rodent spine focused on the metastatically involved third lumbar vertebra (L3) at 7µm/voxel and resampled to 34µm/voxel. The trabecular bone within each vertebra was isolated using an atlas and level-set based segmentation approach previously developed by our group. Pyradiomics, an open source Radiomics library written in python, was used to calculate 3D image features at each voxel location within the vertebral bone. Thresholding of each radiomic feature map was used to isolate the osteoblastic lesions. The utility of radiomic feature-based segmentation of osteoblastic bone tissue was evaluated on randomly selected 2D sagittal and axial slices of the μCT volume. Feature segmentations were compared to ground truth osteoblastic lesion segmentations by calculating the Dice Similarity Coefficient (DSC). Manually defined ground truth osteoblastic tumor segmentations on the μCT slices were informed by histological confirmation of the lesions. The radiomic based features that best segmented osteoblastic tissue while optimizing computational time were derived from the Neighbouring Gray Tone Difference Matrix (NGTDM). Measures of coarseness yielded the best agreement with the manual segmentations (DSC=707%) followed by contrast, strength and complexity (DSC=6513%, 5428%, and 4826%, respectively). This pilot study using a radiomic based approach demonstrates the utility of the NGTDM features for segmentation of vertebral osteoblastic lesions. This investigation looked at the utility of isolated features to segment osteoblastic lesions and found modest performance in isolation. In future work we will explore combining these features using machine learning based classifiers (i.e. decision forests, support vector machines, etc.) to improve segmentation performance

This research sought a mathematical model to relate the postero-anterior (PA) and lateral (LAT) views of the spinal curve in scoliosis in an attempt to justify the acquisition of only One X-ray, thereby reducing patient exposure to harmful X-radiation while preserving complete 3D characterization of the spine. Using powerful developments in functional statistics and machine learning, no such relation could be found. Thus, this research sustained the clinical decision to acquire two biplanar X-rays and supported current research in 3D spinal curvature analysis. Scoliosis is monitored through full spinal X-rays, and this serial protocol causes an increased incidence of cancer development. This research sustains the clinical decision at Hôpital Sainte-Justine in Montréal and elsewhere to acquire postero-anterior (PA) and lateral (LAT) X-rays, despite the increased exposure to X-radiation. Indeed, geometrically, these two views are required to reconstruct the spine in 3D. However, under the assumption of strong physiological patterns between the PA and LAT views of the spinal curve, one of these X-rays may be redundant for some or all patients. The purpose of this study was to seek this a priori assumption. To this end, a database consisting of three hundred and sixty-nine spinal reconstructions from distinct patients was used. Two powerful geometric modeling approaches were exploited: functional data analysis and minimum noise fractions. These resulted in five comprehensive, uncorrelated and noise-insensitive features in each plane. Simple linear regression yielded no relation that was statistically significant (p< 0.05) and genereralizable to a set of previously unseen samples. Therefore, nonlinear relational modeling was attempted using support vector regression, a recent advance in machine learning theory. This tool was incapable of identifying a robust regression, suggesting that the PA and LAT views are mathematically independent. Thus, this study highlights the necessity of two biplanar X-rays to evaluate scoliotic deformities and fully characterize spinal shape. Further, this study supports the practical insufficiency observed by clinical staff with respect to current 2D scoliosis classifications that has resulted in current efforts to propose 3D classification schemes

Purposes and Background. Musculoskeletal disorders including as back and neck pain are leading causes of work disability. Effective interventions exist (i.e. functional restoration, multidisciplinary biopsychosocial rehabilitation, workplace-based interventions, etc.), but it is difficult to select the optimal intervention for specific patients. The Work Assessment Triage Tool (WATT) is a clinical decision support tool developed using machine learning to help select interventions. The WATT algorithm categorizes patients based on individual, occupational, and clinical characteristics according to likelihood of successful return-to-work following rehabilitation. Internal validation showed acceptable classification accuracy, but WATT has not been tested beyond the original development sample. Our purpose was to externally validate the WATT. Methods and Results. A population-based cohort design was used, with administrative and clinical data extracted from a Canadian provincial compensation database. Data were available on workers being considered for rehabilitation between January 2013 and December 2016. Data was obtained on patient characteristics (ie. age, sex, education level), clinical factors (ie. diagnosis, part of body affected, pain and disability ratings), occupational factors (ie. occupation, employment status, modified work availability), type of rehabilitation program undertaken, and return-to-work outcomes (receipt of wage replacement benefits 30 days after assessment). Analysis included classification accuracy statistics of WATT recommendations for selecting interventions that lead to successful RTW outcomes. The sample included 5296 workers of which 33% had spinal conditions. Sensitivity of the WATT was 0.35 while specificity was 0.83. Overall accuracy was 73%. Conclusion. Accuracy of the WATT for selecting successful rehabilitation programs was modest. Algorithm revision and further validation is needed. No conflicts of interest. Sources of funding: Funding was provided by the Workers' Compensation Board of Alberta

INTRODUCTION. Statistical shape models (SSM) have become a common tool to create reference models for design input and verification of total joint implants. In a recent discussion paper around Artificial Intelligence and Machine Learning, the FDA emphasizes the importance of independent test data [1]. A leave-one-out test is a standard way to evaluate the generalization ability of an SSM [2]; however, this test does not fulfill the independence requirement of the FDA. In this study, we constructed an SSM of the knee (femur and tibia). Next to the standard leave-one-out validation, we used an independent test set of patients from a different geographical region than the patients used to build the SSM. We assessed the ability of the SSM to predict the shapes of knees in this independent test set. METHODS. A dataset of 82 computed tomography (CT) scans of Caucasian patients (42 male, 40 female) from 11 different geographic locations in France, Germany, Austria, Italy and Australia were used as training set to make an SSM of the femur and tibia. A leave-one-out test was performed to assess the ability of the SSM to predict shapes within the training set. A test dataset of 4 CT scans of Caucasian patients from Russia were used for the validation. The SSM was fitted onto each of the femur and tibia shapes and the root mean square error (RMSE) was measured. RESULTS. The leave-one-out tests showed that the femur and tibia SSMs were able to predict patients in the input population with an RMSE of 0.59 ± 0.1 mm (average ± standard deviation) for the femur and 0.70 ± 0.1 mm for the tibia. The validation test showed that the femur and tibia SSMs were able to predict the shapes of the Russian patients with an RMSE 0.62 ± 0.1 mm for the femur and 0.71 ± 0.1 mm for the tibia. DISCUSSION. There were no significant differences in the ability of the SSM to predict femur and tibia shapes of patients in a new geographic region compared to the ability of the SSM to predict shapes within the training set. CONCLUSIONS. Based on this study, 11 different geographic locations in France, Germany, Austria, Italy and Australia provide a complete sample of the Caucasian population. Using an independent set of CT scans is a valuable tool to further validate the generalization ability of an SSM. For any figures or tables, please contact authors directly

Our lab uses computer-aided design to build in silico libraries of surface topographies, which we reproduce on polymeric chips and analyse for cellular responses using high content imaging and machine learning. In addition, we use transcriptomics and mass spectrometry to obtain a holistic view of biomaterial-mediated cellular responses and build gene regulatory networks thereof. This approach enables us to parameterize both the biomaterial properties as well as the cell response and to correlate them using computational tools. We think that this approach can be translated to other biomaterial platforms, such as polymer arrays, and foresee large scale crosstalk between them if we can standardize our methodology to describe the materials and to analyse the cells. To this end, we have started cBIT, the compendium for biomaterial-induced transcriptomics, an open-source database in which scientists can deposit and search material-induced transcriptomics data. The meta-analyses that cBIT enables, could lead to the identification of genes, pathways or expression profiles that can inform the design and development of new biomaterials. As such, by generating new information and simultaneously accumulating it in cBIT, we expect it is possible to one day predict cell responses to biomaterials

Advances in cancer therapy have prolonged cancer patient survival even in the presence of disseminated disease and an increasing number of cancer patients are living with metastatic bone disease (MBD). The proximal femur is the most common long bone involved in MBD and pathologic fractures of the femur are associated with significant morbidity, mortality and loss of quality of life (QoL). Successful prophylactic surgery for an impending fracture of the proximal femur has been shown in multiple cohort studies to result in patients more likely to walk after surgery, longer survival, lower transfusion rates and shorter post-operative hospital stays. However, there is currently no optimal method to predict a pathologic fracture. The most well-known tool is Mirel's criteria, established in 1989 and is limited from guiding clinical practice due to poor specificity and sensitivity. The goal of our study is to train a convolutional neural network (CNN) to predict fracture risk when metastatic bone disease is present in the proximal femur. Our fracture risk prediction tool was developed by analysis of prospectively collected data for MBD patients (2009–2016) in order to determine which features are most commonly associated with fracture. Patients with primary bone tumors, pathologic fractures at initial presentation, and hematologic malignancies were excluded. A total of 1146 patients comprising 224 pathologic fractures were included. Every patient had at least one Anterior-Posterior X-ray. The clinical data includes patient demographics, tumor biology, all previous radiation and chemotherapy received, multiple pain and function scores, medications and time to fracture or time to death. Each of Mirel's criteria has been further subdivided and recorded for each lesion. We have trained a convolutional neural network (CNN) with X-ray images of 1146 patients with metastatic bone disease of the proximal femur. The digital X-ray data is converted into a matrix representing the color information at each pixel. Our CNN contains five convolutional layers, a fully connected layers of 512 units and a final output layer. As the information passes through successive levels of the network, higher level features are abstracted from the data. This model converges on two fully connected deep neural network layers that output the fracture risk. This prediction is compared to the true outcome, and any errors are back-propagated through the network to accordingly adjust the weights between connections. Methods to improve learning included using stochastic gradient descent with a learning rate of 0.01 and a momentum rate of 0.9. We used average classification accuracy and the average F1 score across test sets to measure model performance. We compute F1 = 2 x (precision x recall)/(precision + recall). F1 is a measure of a test's accuracy in binary classification, in our case, whether a lesion would result in pathologic fracture or not. Five-fold cross validation testing of our fully trained model revealed accurate classification for 88.2% of patients with metastatic bone disease of the proximal femur. The F1 statistic is 0.87. This represents a 24% error reduction from using Mirel's criteria alone to classify the risk of fracture in this cohort. This is the first reported application of convolutional neural networks, a machine learning algorithm, to an important Orthopaedic problem. Our neural network model was able to achieve impressive accuracy in classifying fracture risk of metastatic proximal femur lesions from analysis of X-rays and clinical information. Our future work will aim to validate this algorithm on an external cohort

Introduction. Identifying knee osteoarthritis patient phenotypes is relevant to assessing treatment efficacy. Biomechanical variability has not been applied to phenotyping, yet features may be related to outcomes of total knee arthroplasty (TKA), an inherently mechanical surgery. This study aimed to i) identify biomechanical phenotypes among TKA candidates based on demographic and gait mechanic similarities, and ii) compare objective gait improvements between phenotypes post-TKA. Methods. TKA patients underwent 3D gait analysis one-week pre (n=134) and one-year post-TKA (n=105). Principal component analysis was applied to frontal and sagittal knee angle and moment gait waveforms, extracting major patterns of variability. Demographics (age, sex, BMI), gait speed, and frontal and sagittal pre-TKA angle and moment principal component (PC) scores previously found to differentiate sex, osteoarthritis (OA) severity, and symptoms of TKA recipients were standardized (mean=0, SD=1, [134×15]) to perform multidimensional scaling and machine learning based hierarchical clustering. Final clusters were validated by examining inter-cluster differences at baseline and gait changes (Post. PCscore. –Pre. PCscore. ) by k-way Chi-Squared, and ANOVA tests. Results. Four (k=4) TKA candidate groups yielded optimum clustering metrics, interpreted as 1) high-functioning males, 2) older stiff-kneed males, 3) slower stiff-kneed females, and 4) high-functioning females. Pre-TKA, higher-functioning clusters (1 & 4) had more dynamic loading/un-loading kinetic patterns during stance (flexion moment PC2, 3<2<4<1, P<0.001; adduction moent PC2; 3,2<4<1; P<0.001). Post-TKA, higher-functioning clusters demonstrated less gait improvement (flexion angle ΔPC2, 1,2,4<3, P<0.001; flexion moment ΔPC2, 4<2,3, P<0.001; adduction moment ΔPC2, 1<3, P=0.01). Conclusions. TKA candidates can be characterized by four clusters, interpreted as 1) high-functioning males, 2) older stiff-kneed males, 3) slower stiff-kneed females, and 4) high-functioning females, differing by demographics and biomechanical severity features. Functional gains after TKA were cluster-specific; stiff-gait clusters experienced more improvement, while higher-functioning clusters demonstrated some functional decline. Results suggest the presence of cohorts who may not benefit functionally from TKA. Cluster profiling may aid in triaging and developing osteoarthritis management and surgical strategies that meet individual or group-level function needs. For figures, tables, or references, please contact authors directly

INTRODUCTION. The advent of CT based 3D preoperative planning software for reverse total shoulder arthroplasty (RTSA) provides surgeons with more data than ever before to prepare for a case. Interestingly, as the usage of such software has increased, further questions have appeared over the optimal way to plan and place a glenoid implant for RTSA. In this study, a survey of shoulder specialists from the American Shoulder and Elbow Society (ASES) was conducted to examine thought patterns in current RTSA implant selection and placement. METHODS. 172 ASES members completed an 18-question survey on their thought process for how they select and place a RTSA glenoid implant. Data was collected using a custom online Survey Monkey survey. Surgeon answers were split into two cohorts based on number of arthroplasties performed per year: between 0–75 was considered low volume (LV), and between 75–200+ was considered high volume (HV). Data was analyzed for each cohort to examine differences in thought patterns, implant selection, and implant placement. RESULTS. 70 surgeons were grouped into the LV cohort, and 102 surgeons were grouped into the HV cohort. 46.1% of surgeons in the HV cohort reported using a preoperative planning software for the majority of cases, 48% reported seldom use, and 5.9% reported no use. In the LV cohort, 41.4% reported use for the majority of cases, 24.3% reported seldom use, and 34.3% reported no use (Figure 1). When questioned on what percentage of RTSA cases do surgeons use augmented glenoid implants, 26.7% in the HV cohort responded never using augments vs. 32.4% in the LV cohort, 32.7% responded using augments <15% of the time in the HV cohort vs. 30.9% in the LV cohort, 26.7% responded using augments between 15–45% of the time in the HV cohort vs. 27.9% in the LV cohort, and 13.8% responded using augments >45% of the time in the HV cohort vs. 8.8% in the LV cohort (Figure 2). When asked what the maximum allowable superior inclination for a RTSA glenoid implant is, surgeons answered 10° 20.6% of the time in the HV cohort vs. 30% in the LV cohort, 5° 18.6% of the time in the HV cohort vs. 25.7% in the LV cohort, 0° 38.2% of the time in the HV cohort vs. 25.7% in the LV cohort, and no fixed degree 22.5% of the time in the HV cohort vs. 18.6% in the LV cohort (Figure 3). CONCLUSION. The results of this study show that even within a group of highly trained surgeons, there are widely varying opinions on how to plan the optimal RTSA case. Variation between high and low volume surgeons reveals even greater differences, suggesting that experience affects thought pattern. Despite these differences, there is no way to prove the optimal implant selection and placement without consistent data collection and long-term clinical outcomes. Machine learning on large preoperative planning databases combined with clinical outcomes data may provide further clarity on optimal implant placement and selection. For any figures or tables, please contact the authors directly

The COVID-19 pandemic has led to unprecedented times worldwide. From lockdowns to masks now being part of our everyday routine, to the halting of elective surgeries, the virus has touched everyone and every part of our personal and professional lives. Perhaps, now more than ever, our ability to adapt, change and persevere is critical to our survival. This year's closed meeting of The Knee Society demonstrated exactly those characteristics. When it became evident that an in-person meeting would not be feasible, The Knee Society leadership, under the direction of President John Callaghan, MD and Program Chair Craig Della Valle, MD created a unique and engaging meeting held on September 10–12, 2020. Special recognition should be given to Olga Foley and Cynthia Garcia at The Knee Society for their flexibility and creativeness in putting together a world-class flawless virtual program. The Bone & Joint Journal is very pleased to partner with The Knee Society to once again publish the proceedings of the closed meeting of the Knee Society. The Knee Society is a United States based society of highly selected members who have shown leadership in education and research in knee surgery. It invites up to 15% international members; this includes some of the key opinion leaders in knee surgery from outside the USA. Each year, the top research papers from The Knee Society meeting will be published and made available to the wider orthopaedic community in The Bone & Joint Journal. The first such proceedings were published in BJJ in 2019. International dissemination should help to fulfil the mission and vision of the Knee Society of advancing the care of patients with knee disorders through leadership, education and research. The quality of dissemination that The Bone & Joint Journal provides should enhance the profile of this work and allow a larger body of surgeons, associated healthcare professionals and patients to benefit from the expertise of the members of The Knee Society. The meeting is one of the highlights of the annual academic calendar for knee surgeons. With nearly every member in attendance virtually throughout the 3 days, the top research papers from the membership were presented and discussed in a virtual format that allowed for lively interaction and discussion. There are 75 abstracts presented. More selective proceedings with full papers will be available after a robust peer review process in 2021, both online and in The Bone & Joint Journal. The meeting commenced with the first group of scientific papers focused on Periprosthetic Joint Infection. Dr Berry and colleagues from the Mayo Clinic further help to clarify the issue of serology and aspirate results to diagnose TKA PJI in the acute postoperative setting. 177 TKA's had an aspiration within 12 weeks and 22 were proven to have PJI. Their results demonstrated that acute PJI after TKA should be suspected within 6 weeks if CRP is ≥81 mg/L, synovial WBCs are ≥8500 cells/μL, and/or synovial neutrophils≥86%. Between 6– 12 weeks, concerning thresholds include a CRP ≥ 32 mg/L, synovial WBC ≥7450, and synovial neutrophils ≥ 84%. While historically the results of a DAIR procedure for PJI have been variable, Tom Fehring's study showed promise with the local delivery of vancomycin through the Intraosseous route improved early results. New member Simon Young contrasted the efficacy of the DAIR procedure when comparing early infections to late acute hematogenous PJI. DAIR failed in 63% of late hematogenous PJIs (implant age>1 year) compared to 36% of early (<1year) PJIs. Dr Masri demonstrated in a small group of patients that those with well-functioning articulating spacers can retain their spacers for over 12 months with no difference in infection from those that had a formal two stage exchange. The mental toll of PJI was demonstrated in a longitudinal study by Doug Dennis, where patient being treated with 2 stage exchange had 4x higher rates of depression compared to patient undergoing aseptic revision. The second session focused on both postoperative issues with regards to anticoagulation and manipulation. Steven Haas demonstrated high complication rates with utilization of anticoagulation for treatment of postoperative pulmonary embolism with modern therapeutic anticoagulation (warfarin, enoxaparin, Xa inhibitors) with the Xa inhibitors demonstrating lower complication rates. Two papers focused on the topic of manipulation. Mark Pagnano presented data on timing of manipulation under anesthesia up to even past 12 months. While gains were modest, a subset of patients did achieve substantial gains in ROM > 20degrees even after 3 months post op. Dr Westrich's study demonstrated no difference in MUA outcomes with either IV sedation or neuraxial anesthesia although the length of stay was shorter in the IV sedation group. Several studies in Session II focused on kinematics and femoral component position. Dr Li's in vivo kinematic study during weightbearing flexion and gait demonstrated that several knees rotated with a lateral pivot motion and not all knees can be described with a single motion character. Dr Mayman and his group utilized a computational knee model to demonstrate that additional distal femoral resection results in increasing levels of mid -flexion instability and cautioned against the use of additional bony resection as the first line for flexion contractures. Using computer navigation, Dr Huddleston's study nicely outlined the variability in femoral component rotation to achieve a rectangular flexion gap utilizing a gap balanced method. The third session opened the meeting on Friday morning. The focus was on unicompartmental knee arthroplasty and the increasing utilization of robotic assisted total knee arthroplasty. David Murray showed using registry data that for patient with higher comorbidities (ASA >3), UKA was safer and more cost effective than TKA while Dr Della Valle's group demonstrated overall lower average healthcare costs in UKA patients compared to TKA in the first 10 years after surgery. Dr Geller assessed UKA survivorship among 3 international registries. While survivorship varied by nation and designs, certain designs consistently had better overall performance. Dr Nunley and his group showed robotic navigation UKA significantly reduced outliers in alignment and overhang compared to manual UKA. Dr Catani's data demonstrated that full thickness cartilage loss should still be considered a requirement for UKA success even with robotic assistance. Despite a high dislocation rate of 4%, Mr Dodd demonstrated high survivorship for lateral UKA despite historical contraindications. The growing evidence for robotics TKA was demonstrated in two studies. Professor Haddad showed less soft tissue injury, reduced bone trauma and improved accuracy or rTKA compared to manual TKA while Dr Gustke single surgeon study showed his rTKA had improved forgotten joint scores and less ligament releasing required for balancing. Despite these finding, Dr Lee's study demonstrated that a robotic TKA could not guarantee excellent pain relief and other factors such a patient expectations and psychological factors play a role. Our fourth session was devoted to machine learning and smart tools and modeling. Dr Meneghini used machine learning algorithms to identify optimal alignment outcomes that correlated with patient outcomes. Several parameters such as native tibial slope, femoral sagittal position and coronal limb alignment correlated with outcomes. Along the same lines, Bozic and coauthors demonstrated that using AI algorithms incorporated with PROM's improved levels of shared decision making and patient satisfaction. Dr Lombardi demonstrated that a mobile patient engagement platform that provided smart phone-based exercise and education was comparable to traditional methods. Dr Mahfouz demonstrated the accuracy of using ultrasound to produce 3D models of the bone compared to conventional CT based strategies and Dr Mahoney showed the valued of a preop 3D model in reproducing more normal knee kinematics. The last two talks of the session focused on some of the positives of the COVID-19 pandemic, namely the embracing of telemedicine by patients and surgeons as demonstrated by Dr Slover and the increasing and far reaching educational opportunities made available to residents and fellows during the pandemic. Session five focused on risk stratification and optimization prior to TKA. Dr O'Connor demonstrated that that the implementation of an optimization program preoperatively reduced length of stay and ED visits, and Charles Nelson's study showed that risk stratification tool can lower complication rates in obese patients undergoing TKA comparable to those that are nonobese. Dr Markel's study demonstrated that those who have preoperative depression and anxiety are at higher risk of complications and readmissions after surgery and these issues should be addressed preoperatively. Interestingly, a study by Dr Callaghan demonstrated that care improvement pathways have not lowered the gap in complications for morbidly obese patients undergoing TKA, Dr Barsoum argued that the overall complication rates were low and this patient cohort had significant gains in PROMS after TKA that would not be experienced if arbitrary cutoff for limited surgery were established. The final session on Friday, Session six, had several well done and interesting studies. There continues to be mounting evidence that liposomal bupivacaine has little effect on managing post-operative pain to warrant its increased use. Bill Macaulay and colleagues showed no change in pain scores, opioid consumption and functional scores when liposomal bupivacaine was discontinued at a large academic medical center. Dr Bugbee importantly demonstrated that a supervised ambulation program reduced falls in the early postoperative period. Several paper on healthcare economics were presented. Rich Iorio showed that stratifying complexity of total joint cases between hospitals with a system can be efficient and cost savings while Dr Jiranek demonstrated in his study that complex TKAs can be identified preoperatively and are associated with prolonged operative time and cost of care and consideration should be given in future reimbursement models to a complexity modifier. Dr Springer, in their evaluation of Medicare bundled payment models, demonstrated that providers and hospitals in historical bundled models that became efficient were penalized in the new model, forcing many groups to drop out and return to a fee for service model. Ron Delanois important work showed that social determinants can have a major negative impact on outcomes following TKA. Our final day on Saturday opened with Session seven, and several interesting paper on metal ions/debris in TKA. Dr Whitesides simulator study showed the absence of scratches and material loss in a ceramic TKA compared with Co-Cr TKA and suggested an advantage to this material in patients with metal sensitivity. Conversely, in a histological study of failed TKA, perivascular lymphocytic infiltration was not associated with worse clinical outcomes or differences in revision in a series of 617 aseptic revisions, 19% of which had PVLI found on histology. The Mayo group and Dr Trousdale however, noted that serum metal ion levels can be helpful in identifying implant failure in a group of revision TKAs, especially those with metallic junctions. Dr Dalury demonstrated nicely that use of maximally conforming inserts did not have a negative effect on implant loosening in a series of 76 revision TKA's at an average follow up of 7 years, while Kevin Garvin and his group showed no difference in end of stem pain between cemented and cementless stems in revision TKA. The final two studies in the session by Bolognesi and Peters respectively showed that metaphyseal cones continue to demonstrate excelled survivorship in rTKA setting despite extensive bone loss. Session eight was highlighted by a large series of revision reported by new member Dr Schwarzkopf, who showed that revision TKA done by high volume surgeons demonstrated better outcomes and lower revision rates compared to surgeon who did less than 18 rTKA's per year. Dr Maniar importantly showed that preoperatively, patients with high activity level and low pain and indicated by a high preop forgotten joint score did poorly following TKA while David Ayers nicely demonstrated that KOOS scores that assess specific postoperative outcomes can predict patient dissatisfaction after TKA. The final paper in this session by Max Courtney showed that the majority of surgical cancellations are due to medical issues, yet a minority of these undergo any intervention specifically for that condition, but they resulted in a delay of 5 months. The first two studies of Session nine focused on polyethylene thickness. Dr Backstein demonstrated no difference in KSS scores, change in ROM and aseptic revision rates based on polyethylene thickness in a series of 195 TKA's. An interesting lab study by Dr Tim Wright showed a surprising consistency in liner thickness choice among varying levels of surgeon experience that did not correlate with applied forces or gap stability estimates. Two studies looked specifically at the issue of tibial loosening and implant design. Nam and colleagues were not able to demonstrate concerning findings for increasing tibial loosening in a tibial baseplate with a shortened tibial keel at short term follow up, while Lachiewicz demonstrated a 19% revision or revision pending rate in 223 cemented fixed bearing ATTUNE TKA at a mean of 30 months. Our final session of the meeting, began with encouraging news, that despite only currently capturing about 40% of TJA's done in the US, the American Joint Replacement Registry data is representative of data in other representative US databases. An interesting study presented by Robert Barrack looked at bone remodeling in the proximal tibia after cemented and cementless TKA of two different designs. No significant difference was noted among the groups with the exception of the cemented thicker cobalt chrome tray which demonstrated significantly more bone mineral density loss. Along the same lines, a study out of Dr Bostrom's lab demonstrated treatment of a murine tibial model with iPTH prevents fibrous tissue formation and enhances bone formation in cementless implants. New Member Jamie Howard showed no difference in implant migration and kinematics of a single radius cementless design using either a measured resection or gap balancing technique and Dr Cushner show no difference in blood loss with cemented or cementless TKA with the use of TKA. The final two studies looked at staging and bilateral TKA's. Peter Sharkey showed that simultaneous TKA's were associated with higher complication compared to staged TKA and that staged TKA with less than a 90-day interval was not associated with higher risk. However, Mark Figgie showed that patients undergoing simultaneous TKA compared to staged TKA, missed 17 fewer days of work. In spite of the virtual nature of the meeting, there were some outstanding scientific interactions and the material presented will continue to generate debate and to guide the direction of knee arthroplasty as we move forwards

A total hip replacement (THR) patient's spinopelvic mobility might predispose them to an increased risk of impingement, instability and edge-loading. This risk can be minimised by considering their preoperative movement during planning of component alignment. However, the question of whether the preoperative, arthritic motion is representative of the postoperative mobility has been raised. We aimed to determine the change in functional pelvic tilt in a series of THR patients at one-year. Four-hundred and eleven patients had their pelvic tilt and lumbar lordotic angle (LLA) measured in the standing and flexed-seated (position when patients initiate rising from a seat) positions as part of routine planning for THR. All measurements were performed on lateral radiographs. At 12-months postoperatively, the same two lateral images were taken and pelvic tilt measured. Pearson correlation was used to investigate the linear relationship between pre-and post-op pelvic tilt. Furthermore, a predictive model of post-op pelvic tilt was developed using machine learning algorithms. The model incorporating four preoperative inputs – standing pelvic tilt, seated pelvic tilt, standing LLA and seated LLA. In the standing position, there was a mean 2° posterior rotation after THR, with a maximum posterior change of 13°. The Pearson correlation coefficient between pre-and post-op standing pelvic tilt was 0.84. This prediction of post-op standing tilt improved to 0.91 when the three further inputs were incorporated to the predictive model. In the flexed-seated position, there was a mean 7° anterior rotation after THR, with a maximum anterior change of 45°. The Pearson correlation coefficient between pre-and post-op seated pelvic tilt was 0.54. This prediction of post-op seated tilt improved to 0.71 when the three further inputs were incorporated to the predictive model. The best predictor of post-operative spinopelvic mobility, is the patients pre-operative spinopelvic mobility, and this should routinely be measured when planning THR. The predictive model will continue to improve in accuracy as more data and more variables (contralateral hip pathology, pelvic incidence, age and gender) are incorporated into the model

Introduction. Custom flanged acetabular components (CFAC) have been shown to be effective in treating complex acetabular reconstructions in revision total hip arthroplasty (THA). However, the specific patient factors and CFAC design characteristics that affect the overall survivorship remain unclear. Once the surgeon opts to follow this treatment pathway, numerous decisions need to be made during the pre-operative design phase and during implantation, which may influence the ultimate success of CFAC. The goal of this study was to retrospectively review the entire cohort of CFAC cases performed at a large volume institution and to identify any patient, surgeon, or design factors that may be related to the long-term survival of these prostheses. Methods. We reviewed 96 CFAC cases performed in 91 patients between 2004 and 2017, from which 36 variables were collected spanning patient demographics, pre-operative clinical and radiographic features, intraoperative information, and implant design characteristics. Patient demographics and relevant clinical features were collected from individual medical records. Radiographic review included analysis of pre-operative radiographs, computer tomographic (CT) scans, and serial post-operative radiographs. Radiographic failure was defined as loosening or gross migration as determined by a board-certified orthopedic surgeon. CFAC implant design characteristics and intra-operative features were collected from the design record, surgical record and post-operative radiograph for each case respectively. Two sets of statistical analyses were performed with this dataset. First, univariate analyses were performed for each variable, comprising of a Pearson chi-square test for categorical variables and an independent t-test for continuous variables. Second, a random forest supervised machine learning method was applied to identify the most influential variables within the dataset, which were then used to perform a bivariable logistic regression to generate odds ratios. Statistical significance for this study was set at p < 0.05. Results. Radiographic failures occurred in 22/96 (23%) of cases with 12/96 (13%) undergoing re-revision (time to revision: Mean 25.1 months; Range: 3 – 84, SD 26.5). No relationship between radiographic failure and the preoperative Paprosky grade or the presence of a discontinuity was observed. The rate of radiographic failure (loosening and/or migration) was inversely associated with age, with increased failure seen in patients who were younger at the time of surgery; (mean age: 54.4±13.0 v. 64.8±11.4 years; p=0.007). Patients whose initial diagnosis was not osteoarthritis were more likely to fail than those with primary OA (OR: 3.79, p=0.0173) and were younger at the time of surgery (p=0.013). The presence of ischial screws from previous surgery (28%) was also an independent risk factor for failure (OR: 3.11, p=0.021). Random forest analysis identified the age at index procedure and the location of the inferior-most ischial screw as the most sensitive predictors of radiographic failure. As patient age at the time of surgery increased, there was subsequent a decreased rate of failure (OR: 0.93 odds ratio per year, p =0.005). When the bottom-most ischial screw was within the top half of the obturator foramen, it was 4 times more likely to fail than when this screw was located at the bottom half of the obturator foramen (OR = 3.98, p=0.046) (p < 0.05). Discussion and Conclusion. This study was able to identify the patient and design variables predictive of survival of CFAC prostheses used in complex revision THA. Younger patients (<55years) are at increased risk for failure either due to a more active lifestyle or because they have a non-OA primary diagnosis that predisposes them to earlier THA. Compromised ischial bone stock or inadequate ischial fixation both had a significant impact on CFAC implant survivorship as both the presence of pre-CFAC ischial screw fixation and lack of inferior ischial fixation correlated with increased rate of failure. These findings highlight the importance of rigid ischial fixation sufficient to resist the high pull-out forces generated during activities of daily living

Cite this article: Bone Joint Res 2023;12(8):494–496.

In professional football a key factor regarding injury is the time to return to play. Accurate prediction of this would aid planning by the club in the event of injury. It would also aid the club medical staff. Gaussian processes may be used for machine learning tasks such as regression and classification. This study determines whether machine-learning methods may be used for predicting how many days a player is unavailable to play. A database of injuries at one English Premier League Professional Football Club was reviewed for a number of factors for each injury. Twenty-five variables were recorded for each injury, including time to return to play. This was determined to be the response variable. We used a Gaussian process model with a Laplacian kernel to determine whether the return to play could be predicted from the other variables. The root mean square error was 13.186 days (S.D.: 8.073), the mean absolute error was 8.192 days (S.D.:13.106) and the mean relative error 171.97% (S.D.:75.56%). A linear trend was observed and the model demonstrated high accuracy with greater errors being observed for cases where the value of the response variable was higher, i.e. in those cases where the time to return to play was lengthy. This is the first step in attempting to design a computer-based model that will accurately predict the time for a professional footballer to return to play. The model is extremely accurate for most cases, with errors increasing as the severity of the case increases too

The February 2023 Knee Roundup³⁶⁰ looks at: Machine-learning models: are all complications predictable?; Positive cultures can be safely ignored in revision arthroplasty patients that do not meet the 2018 International Consensus Meeting Criteria; Spinal versus general anaesthesia in contemporary primary total knee arthroplasty; Preoperative pain and early arthritis are associated with poor outcomes in total knee arthroplasty; Risk factors for infection and revision surgery following patellar tendon and quadriceps tendon repairs; Supervised versus unsupervised rehabilitation following total knee arthroplasty; Kinematic alignment has similar outcomes to mechanical alignment: a systematic review and meta-analysis; Lifetime risk of revision after knee arthroplasty influenced by age, sex, and indication; Risk factors for knee osteoarthritis after traumatic knee injury.

Aims

The preoperative grading of chondrosarcomas of bone that accurately predicts surgical management is difficult for surgeons, radiologists, and pathologists. There are often discrepancies in grade between the initial biopsy and the final histology. Recent advances in the use of imaging methods have shown promise in the ability to predict the final grade. The most important clinical distinction is between grade 1 chondrosarcomas, which are amenable to curettage, and resection-grade chondrosarcomas (grade 2 and 3) which require en bloc resection. The aim of this study was to evaluate the use of a Radiological Aggressiveness Score (RAS) to predict the grade of primary chondrosarcomas in long bones and thus to guide management.

Aims

This systematic review aims to identify 3D predictors derived from biplanar reconstruction, and to describe current methods for improving curve prediction in patients with mild adolescent idiopathic scoliosis.

The June 2023 Spine Roundup³⁶⁰ looks at: Characteristics and comparative study of thoracolumbar spine injury and dislocation fracture due to tertiary trauma; Sublingual sufentanil for postoperative pain management after lumbar spinal fusion surgery; Minimally invasive bipolar technique for adult neuromuscular scoliosis; Predictive factors for degenerative lumbar spinal stenosis; Lumbosacral transitional vertebrae and lumbar fusion surgery at level L4/5; Does recall of preoperative scores contaminate trial outcomes? A randomized controlled trial; Vancomycin in fibrin glue for prevention of SSI; Perioperative nutritional supplementation decreases wound healing complications following elective lumbar spine surgery: a randomized controlled trial.

Aims

Cemented hemiarthroplasty is an effective form of treatment for most patients with an intracapsular fracture of the hip. However, it remains unclear whether there are subgroups of patients who may benefit from the alternative operation of a modern uncemented hemiarthroplasty – the aim of this study was to investigate this issue. Knowledge about the heterogeneity of treatment effects is important for surgeons in order to target operations towards specific subgroups who would benefit the most.

We aim to explore the potential technologies for monitoring and assessment of patients undergoing arthroplasty by examining selected literature focusing on the technology currently available and reflecting on possible future development and application. The reviewed literature indicates a large variety of different hardware and software, widely available and used in a limited manner, to assess patients’ performance. There are extensive opportunities to enhance and integrate the systems which are already in existence to develop patient-specific pathways for rehabilitation.

Cite this article: Bone Joint J 2022;104-B(10):1104–1109.

Aims

The aim of this study was to estimate the 90-day periprosthetic joint infection (PJI) rates following total knee arthroplasty (TKA) and total hip arthroplasty (THA) for osteoarthritis (OA).