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

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. 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. Methods. Six sets of gene expression profiles were obtained from the Gene Expression Omnibus database. Differential expression analysis, weighted gene coexpression network analysis (WGCNA), and multiple machine-learning algorithms were used to screen crucial genes in osteoarthritic cartilage, and genome enrichment and functional annotation analyses were used to decipher the related categories of gene function. Single-sample gene set enrichment analysis was performed to analyze immune cell infiltration. Correlation analysis was used to explore the relationship among the hub genes and immune cells, as well as markers related to articular cartilage degradation and bone mineralization. Results. A total of 46 genes were obtained from the intersection of significantly upregulated genes in osteoarthritic cartilage and the key module genes screened by WGCNA. Functional annotation analysis revealed that these genes were closely related to pathological responses associated with OA, such as inflammation and immunity. Four key dysregulated genes (cartilage acidic protein 1 (CRTAC1), iodothyronine deiodinase 2 (DIO2), angiopoietin-related protein 2 (ANGPTL2), and MAGE family member D1 (MAGED1)) were identified after using machine-learning algorithms. These genes had high diagnostic value in both the training cohort and external validation cohort (receiver operating characteristic > 0.8). The upregulated expression of these hub genes in osteoarthritic cartilage signified higher levels of immune infiltration as well as the expression of metalloproteinases and mineralization markers, suggesting harmful biological alterations and indicating that these hub genes play an important role in the pathogenesis of OA. A competing endogenous RNA network was constructed to reveal the underlying post-transcriptional regulatory mechanisms. Conclusion. The current study explores and validates a dysregulated key gene set in osteoarthritic cartilage that is capable of accurately diagnosing OA and characterizing the biological alterations in osteoarthritic cartilage; this may become a promising indicator in clinical decision-making. This study indicates that dysregulated key genes play an important role in the development and progression of OA, and may be potential therapeutic targets. Cite this article: Bone Joint Res 2024;13(2):66–82

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. Methods. A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results. A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion. The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice. Cite this article: Bone Jt Open 2024;5(1):9–19

Artificial intelligence and machine-learning analytics have gained extensive popularity in recent years due to their clinically relevant applications. A wide range of proof-of-concept studies have demonstrated the ability of these analyses to personalize risk prediction, detect implant specifics from imaging, and monitor and assess patient movement and recovery. Though these applications are exciting and could potentially influence practice, it is imperative to understand when these analyses are indicated and where the data are derived from, prior to investing resources and confidence into the results and conclusions. In this article, we review the current benefits and potential limitations of machine-learning for the orthopaedic surgeon with a specific emphasis on data quality

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. Methods. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration). Results. The developed algorithms distinguished between patients at high and low risk for 90-day and one-year mortality. The penalized logistic regression algorithm had the best performance metrics for both 90-day (c-statistic 0.80, calibration slope 0.95, calibration intercept -0.06, and Brier score 0.039) and one-year (c-statistic 0.76, calibration slope 0.86, calibration intercept -0.20, and Brier score 0.074) mortality prediction in the hold-out set. Conclusion. Using high-quality data, the ML-based prediction models accurately predicted 90-day and one-year mortality in patients aged 50 years or older with a FNF. The final models must be externally validated to assess generalizability to other populations, and prospectively evaluated in the process of shared decision-making. Cite this article: Bone Jt Open 2023;4(3):168–181

Aims. The aim of this study was to develop and evaluate machine-learning-based computerized adaptive tests (CATs) for the Oxford Hip Score (OHS), Oxford Knee Score (OKS), Oxford Shoulder Score (OSS), and the Oxford Elbow Score (OES) and its subscales. Methods. We developed CAT algorithms for the OHS, OKS, OSS, overall OES, and each of the OES subscales, using responses to the full-length questionnaires and a machine-learning technique called regression tree learning. The algorithms were evaluated through a series of simulation studies, in which they aimed to predict respondents’ full-length questionnaire scores from only a selection of their item responses. In each case, the total number of items used by the CAT algorithm was recorded and CAT scores were compared to full-length questionnaire scores by mean, SD, score distribution plots, Pearson’s correlation coefficient, intraclass correlation (ICC), and the Bland-Altman method. Differences between CAT scores and full-length questionnaire scores were contextualized through comparison to the instruments’ minimal clinically important difference (MCID). Results. The CAT algorithms accurately estimated 12-item questionnaire scores from between four and nine items. Scores followed a very similar distribution between CAT and full-length assessments, with the mean score difference ranging from 0.03 to 0.26 out of 48 points. Pearson’s correlation coefficient and ICC were 0.98 for each 12-item scale and 0.95 or higher for the OES subscales. In over 95% of cases, a patient’s CAT score was within five points of the full-length questionnaire score for each 12-item questionnaire. Conclusion. Oxford Hip Score, Oxford Knee Score, Oxford Shoulder Score, and Oxford Elbow Score (including separate subscale scores) CATs all markedly reduce the burden of items to be completed without sacrificing score accuracy. Cite this article: Bone Jt Open 2022;3(10):786–794

The August 2024 Spine Roundup. 360. looks at: Laminectomy adjacent to instrumented fusion increases adjacent segment disease; Influence of the timing of surgery for cervical spinal cord injury without bone injury in the elderly: a retrospective multicentre study; Lumbar vertebral body tethering: single-centre outcomes and reoperations in a consecutive series of 106 patients; Machine-learning algorithms for predicting Cobb angle beyond 25° in female adolescent idiopathic scoliosis patients; Pain in adolescent idiopathic scoliosis; Teriparatide prevents surgery for osteoporotic vertebral compression fracture

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. Methods. A smartwatch was used to collect inertial data from 42 patients performing shoulder physiotherapy exercises for rotator cuff injuries in both in-clinic and at-home settings. A two-stage ML approach was used to detect out-of-distribution (OOD) data (to remove non-exercise data) and subsequently for classification of exercises. We evaluated the performance impact of grouping exercises by motion type, inclusion of non-exercise data for algorithm training, and a patient-specific approach to exercise classification. Algorithm performance was evaluated using both in-clinic and at-home data. Results. The patient-specific approach with engineered features achieved the highest in-clinic performance for differentiating physiotherapy exercise from non-exercise activity (area under the receiver operating characteristic (AUROC) = 0.924). Including non-exercise data in algorithm training further improved classifier performance (random forest, AUROC = 0.985). The highest accuracy achieved for classifying individual in-clinic exercises was 0.903, using a patient-specific method with deep neural network model extracted features. Grouping exercises by motion type improved exercise classification. For at-home data, OOD detection yielded similar performance with the non-exercise data in the algorithm training (fully convolutional network AUROC = 0.919). Conclusion. Including non-exercise data in algorithm training improves detection of exercises. A patient-specific approach leveraging data from earlier patient-supervised sessions should be considered but is highly dependent on per-patient data quality. Cite this article: Bone Joint Res 2023;12(3):165–177

The February 2023 Knee Roundup. 360. 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. 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. Methods. The study included 538 joints that underwent primary THA. The patients were divided into groups using unsupervised time series clustering for five-year BMD loss of Gruen zone 7 postoperatively, and a machine-learning model to predict the BMD loss was developed. Additionally, the predictor for BMD loss was extracted using SHapley Additive exPlanations (SHAP). The patient-specific efficacy of bisphosphonate, which is the most important categorical predictor for BMD loss, was examined by calculating the change in predictive probability when hypothetically switching between the inclusion and exclusion of bisphosphonate. Results. Time series clustering allowed us to divide the patients into two groups, and the predictive factors were identified including patient- and operation-related factors. The area under the receiver operating characteristic (ROC) curve (AUC) for the BMD loss prediction averaged 0.734. Virtual administration of bisphosphonate showed on average 14% efficacy in preventing BMD loss of zone 7. Additionally, stem types and preoperative triglyceride (TG), creatinine (Cr), estimated glomerular filtration rate (eGFR), and creatine kinase (CK) showed significant association with the estimated patient-specific efficacy of bisphosphonate. Conclusion. Periprosthetic BMD loss after THA is predictable based on patient- and operation-related factors, and optimal prescription of bisphosphonate based on the prediction may prevent BMD loss. Cite this article: Bone Joint Res 2024;13(4):184–192

Aims. This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA). Methods. Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay. Results. The predictability of the ANN model, area under the curve (AUC) = 0.801, was similar to the logistic regression model (AUC = 0.796) and identified certain variables as important factors to predict same-day discharge. The ten most important factors favouring same-day discharge in the ANN model include preoperative sodium, preoperative international normalized ratio, BMI, age, anaesthesia type, operating time, dyspnoea status, functional status, race, anaemia status, and chronic obstructive pulmonary disease (COPD). Six of these variables were also found to be significant on logistic regression analysis. Conclusion. Both ANN modelling and logistic regression analysis revealed clinically important factors in predicting patients who can undergo safely undergo same-day discharge from an outpatient TKA. The ANN model provides a beneficial approach to help determine which perioperative factors can predict same-day discharge as of 2018 perioperative recovery protocols. Cite this article: Bone Joint J 2021;103-B(8):1358–1366

Aims. Precise implant positioning, tailored to individual spinopelvic biomechanics and phenotype, is paramount for stability in total hip arthroplasty (THA). Despite a few studies on instability prediction, there is a notable gap in research utilizing artificial intelligence (AI). The objective of our pilot study was to evaluate the feasibility of developing an AI algorithm tailored to individual spinopelvic mechanics and patient phenotype for predicting impingement. Methods. This international, multicentre prospective cohort study across two centres encompassed 157 adults undergoing primary robotic arm-assisted THA. Impingement during specific flexion and extension stances was identified using the virtual range of motion (ROM) tool of the robotic software. The primary AI model, the Light Gradient-Boosting Machine (LGBM), used tabular data to predict impingement presence, direction (flexion or extension), and type. A secondary model integrating tabular data with plain anteroposterior pelvis radiographs was evaluated to assess for any potential enhancement in prediction accuracy. Results. We identified nine predictors from an analysis of baseline spinopelvic characteristics and surgical planning parameters. Using fivefold cross-validation, the LGBM achieved 70.2% impingement prediction accuracy. With impingement data, the LGBM estimated direction with 85% accuracy, while the support vector machine (SVM) determined impingement type with 72.9% accuracy. After integrating imaging data with a multilayer perceptron (tabular) and a convolutional neural network (radiograph), the LGBM’s prediction was 68.1%. Both combined and LGBM-only had similar impingement direction prediction rates (around 84.5%). Conclusion. This study is a pioneering effort in leveraging AI for impingement prediction in THA, utilizing a comprehensive, real-world clinical dataset. Our machine-learning algorithm demonstrated promising accuracy in predicting impingement, its type, and direction. While the addition of imaging data to our deep-learning algorithm did not boost accuracy, the potential for refined annotations, such as landmark markings, offers avenues for future enhancement. Prior to clinical integration, external validation and larger-scale testing of this algorithm are essential. Cite this article: Bone Jt Open 2024;5(8):671–680

Aims. To compare the gait of unicompartmental knee arthroplasty (UKA) and total knee arthroplasty (TKA) patients with healthy controls, using a machine-learning approach. Patients and Methods. 145 participants (121 healthy controls, 12 patients with cruciate-retaining TKA, and 12 with mobile-bearing medial UKA) were recruited. The TKA and UKA patients were a minimum of 12 months post-operative, and matched for pattern and severity of arthrosis, age, and body mass index. . Participants walked on an instrumented treadmill until their maximum walking speed was reached. Temporospatial gait parameters, and vertical ground reaction force data, were captured at each speed. Oxford knee scores (OKS) were also collected. An ensemble of trees algorithm was used to analyse the data: 27 gait variables were used to train classification trees for each speed, with a binary output prediction of whether these variables were derived from a UKA or TKA patient. Healthy control gait data was then tested by the decision trees at each speed and a final classification (UKA or TKA) reached for each subject in a majority voting manner over all gait cycles and speeds. Top walking speed was also recorded. Results. 92% of the healthy controls were classified by the decision tree as a UKA, 5% as a TKA, and 3% were unclassified. There was no significant difference in OKS between the UKA and TKA patients (p = 0.077). Top walking speed in TKA patients (1.6 m/s; 1.3 to 2.1) was significantly lower than that of both the UKA group (2.2 m/s; 1.8 to 2.7) and healthy controls (2.2 m/s; 1.5 to 2.7; p < 0.001). . Conclusion. UKA results in a more physiological gait compared with TKA, and a higher top walking speed. This difference in function was not detected by the OKS. Cite this article: Bone Joint J 2016;98-B(10 Suppl B):16–21

The August 2023 Knee Roundup³⁶⁰ 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?

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.

The October 2023 Spine Roundup³⁶⁰ looks at: Cutting through surgical smoke: the science of cleaner air in spinal operations; Unlocking success: key factors in thoracic spine decompression and fusion for ossification of the posterior longitudinal ligament; Deep learning algorithm for identifying cervical cord compression due to degenerative canal stenosis on radiography; Surgeon experience influences robotics learning curve for minimally invasive lumbar fusion; Decision-making algorithm for the surgical treatment of degenerative lumbar spondylolisthesis of L4/L5; Response to preoperative steroid injections predicts surgical outcomes in patients undergoing fusion for isthmic spondylolisthesis.

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.

Aims

To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports.

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.