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

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 aims of this study were to assess mapping models to predict the three-level version of EuroQoL five-dimension utility index (EQ-5D-3L) from the Oxford Knee Score (OKS) and validate these before and after total knee arthroplasty (TKA). Methods. A retrospective cohort of 5,857 patients was used to create the prediction models, and a second cohort of 721 patients from a different centre was used to validate the models, all of whom underwent TKA. Patient characteristics, BMI, OKS, and EQ-5D-3L were collected preoperatively and one year postoperatively. Generalized linear regression was used to formulate the prediction models. Results. There were significant correlations between the OKS and EQ-5D-3L preoperatively (r = 0.68; p < 0.001) and postoperatively (r = 0.77; p < 0.001) and for the change in the scores (r = 0.61; p < 0.001). Three different models (preoperative, postoperative, and change) were created. There were no significant differences between the actual and predicted mean EQ-5D-3L utilities at any timepoint or for change in the scores (p > 0.090) in the validation cohort. There was a significant correlation between the actual and predicted EQ-5D-3L utilities preoperatively (r = 0.63; p < 0.001) and postoperatively (r = 0.77; p < 0.001) and for the change in the scores (r = 0.56; p < 0.001). Bland-Altman plots demonstrated that a lower utility was overestimated, and higher utility was underestimated. The individual predicted EQ-5D-3L that was within ± 0.05 and ± 0.010 (minimal clinically important difference (MCID)) of the actual EQ-5D-3L varied between 13% to 35% and 26% to 64%, respectively, according to timepoint assessed and change in the scores, but was not significantly different between the modelling and validation cohorts (p ≥ 0.148). Conclusion. The OKS can be used to estimate EQ-5D-3L. Predicted individual patient utility error beyond the MCID varied from one-third to two-thirds depending on timepoint assessed, but the mean for a cohort did not differ and could be employed for this purpose. Cite this article: Bone Jt Open 2022;3(7):573–581

Aims. No predictive model has been published to forecast operating time for total knee arthroplasty (TKA). The aims of this study were to design and validate a predictive model to estimate operating time for robotic-assisted TKA based on demographic data, and evaluate the added predictive power of CT scan-based predictors and their impact on the accuracy of the predictive model. Methods. A retrospective study was conducted on 1,061 TKAs performed from January 2016 to December 2019 with an image-based robotic-assisted system. Demographic data included age, sex, height, and weight. The femoral and tibial mechanical axis and the osteophyte volume were calculated from CT scans. These inputs were used to develop a predictive model aimed to predict operating time based on demographic data only, and demographic and 3D patient anatomy data. Results. The key factors for predicting operating time were the surgeon and patient weight, followed by 12 anatomical parameters derived from CT scans. The predictive model based only on demographic data showed that 90% of predictions were within 15 minutes of actual operating time, with 73% within ten minutes. The predictive model including demographic data and CT scans showed that 94% of predictions were within 15 minutes of actual operating time and 88% within ten minutes. Conclusion. The primary factors for predicting robotic-assisted TKA operating time were surgeon, patient weight, and osteophyte volume. This study demonstrates that incorporating 3D patient-specific data can improve operating time predictions models, which may lead to improved operating room planning and efficiency. Cite this article: Bone Jt Open 2022;3(5):383–389

Aims. The aim of this study was to develop and internally validate a prognostic nomogram to predict the probability of gaining a functional range of motion (ROM ≥ 120°) after open arthrolysis of the elbow in patients with post-traumatic stiffness of the elbow. Methods. We developed the Shanghai Prediction Model for Elbow Stiffness Surgical Outcome (SPESSO) based on a dataset of 551 patients who underwent open arthrolysis of the elbow in four institutions. Demographic and clinical characteristics were collected from medical records. The least absolute shrinkage and selection operator regression model was used to optimize the selection of relevant features. Multivariable logistic regression analysis was used to build the SPESSO. Its prediction performance was evaluated using the concordance index (C-index) and a calibration graph. Internal validation was conducted using bootstrapping validation. Results. BMI, the duration of stiffness, the preoperative ROM, the preoperative intensity of pain, and grade of post-traumatic osteoarthritis of the elbow were identified as predictors of outcome and incorporated to construct the nomogram. SPESSO displayed good discrimination with a C-index of 0.73 (95% confidence interval 0.64 to 0.81). A high C-index value of 0.70 could still be reached in the interval validation. The calibration graph showed good agreement between the nomogram prediction and the outcome. Conclusion. The newly developed SPESSO is a valid and convenient model which can be used to predict the outcome of open arthrolysis of the elbow. It could assist clinicians in counselling patients regarding the choice and expectations of treatment. Cite this article: Bone Joint J 2022;104-B(4):486–494

Aims. Advances in treatment have extended the life expectancy of patients with metastatic bone disease (MBD). Patients could experience more skeletal-related events (SREs) as a result of this progress. Those who have already experienced a SRE could encounter another local management for a subsequent SRE, which is not part of the treatment for the initial SRE. However, there is a noted gap in research on the rate and characteristics of subsequent SREs requiring further localized treatment, obligating clinicians to extrapolate from experiences with initial SREs when confronting subsequent ones. This study aimed to investigate the proportion of MBD patients developing subsequent SREs requiring local treatment, examine if there are prognostic differences at the initial treatment between those with single versus subsequent SREs, and determine if clinical, oncological, and prognostic features differ between initial and subsequent SRE treatments. Methods. This retrospective study included 3,814 adult patients who received local treatment – surgery and/or radiotherapy – for bone metastasis between 1 January 2010 and 31 December 2019. All included patients had at least one SRE requiring local treatment. A subsequent SRE was defined as a second SRE requiring local treatment. Clinical, oncological, and prognostic features were compared between single SREs and subsequent SREs using Mann-Whitney U test, Fisher’s exact test, and Kaplan–Meier curve. Results. Of the 3,814 patients with SREs, 3,159 (83%) patients had a single SRE and 655 (17%) patients developed a subsequent SRE. Patients who developed subsequent SREs generally had characteristics that favoured longer survival, such as higher BMI, higher albumin levels, fewer comorbidities, or lower neutrophil count. Once the patient got to the point of subsequent SRE, their clinical and oncological characteristics and one-year survival (28%) were not as good as those with only a single SRE (35%; p < 0.001), indicating that clinicians’ experiences when treating the initial SRE are not similar when treating a subsequent SRE. Conclusion. This study found that 17% of patients required treatments for a second, subsequent SRE, and the current clinical guideline did not provide a specific approach to this clinical condition. We observed that referencing the initial treatment, patients in the subsequent SRE group had longer six-week, 90-day, and one-year median survival than patients in the single SRE group. Once patients develop a subsequent SRE, they have a worse one-year survival rate than those who receive treatment for a single SRE. Future research should identify prognostic factors and assess the applicability of existing survival prediction models for better management of subsequent SREs. Cite this article: Bone Joint Res 2024;13(9):497–506

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?. Methods. The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS). Results. Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN’s performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV). Conclusion. The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis–Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice. Cite this article: Bone Jt Open 2021;2(10):879–885

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.

Aims

To map literature on prognostic factors related to outcomes of revision total knee arthroplasty (rTKA), to identify extensively studied factors and to guide future research into what domains need further exploration.

Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles (https://www.ideal-collaboration.net/). Adherence to the framework would provide a robust evidence-based mechanism for developing trust in AI applications, where the underlying algorithms are unlikely to be fully understood by clinical teams.

Cite this article: Bone Joint Res 2024;13(9):507–512.

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

This study aimed to assess the risk of acute kidney injury (AKI) associated with combined intravenous (IV) and topical antibiotic therapy in patients undergoing treatment for periprosthetic joint infections (PJIs) following total knee arthroplasty (TKA), utilizing the Kidney Disease: Improving Global Outcomes (KDIGO) criteria for classification.

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

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

Frailty greatly increases the risk of adverse outcome of trauma in older people. Frailty detection tools appear to be unsuitable for use in traumatically injured older patients. We therefore aimed to develop a method for detecting frailty in older people sustaining trauma using routinely collected clinical data.

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

Lumbar spinal stenosis (LSS) is a common skeletal system disease that has been partly attributed to genetic variation. However, the correlation between genetic variation and pathological changes in LSS is insufficient, and it is difficult to provide a reference for the early diagnosis and treatment of the disease.

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.

Aims

To perform an incremental cost-utility analysis and assess the impact of differential costs and case volume on the cost-effectiveness of robotic arm-assisted unicompartmental knee arthroplasty (rUKA) compared to manual (mUKA).

Aims

To explore key stakeholder views around feasibility and acceptability of trials seeking to prevent post-traumatic osteoarthritis (PTOA) following knee injury, and provide guidance for next steps in PTOA trial design.