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. 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. Methods. This retrospective cohort study included 469 patients, who underwent surgery for BM-E between January 2009 and March 2022 at a tertiary hospital in South Korea. Postoperative survival was calculated using the PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models. Model performance was assessed with area under the curve (AUC), calibration curve, Brier score, and decision curve analysis. Cox regression analyses were performed to evaluate the factors contributing to survival. Results. The SORG model demonstrated the highest discriminatory accuracy with AUC (0.80 (95% confidence interval (CI) 0.76 to 0.85)) at 12 months. In calibration analysis, the PATHfx3.0 and OPTIModel models underestimated survival, while the SPRING13 and IOR models overestimated survival. The SORG model exhibited excellent calibration with intercepts of 0.10 (95% CI -0.13 to 0.33) at 12 months. The SORG model also had lower Brier scores than the null score at three and 12 months, indicating good overall performance. Decision curve analysis showed that all five survival prediction models provided greater net benefit than the default strategy of operating on either all or no patients. Rapid growth cancer and low serum albumin levels were associated with three-, six-, and 12-month survival. Conclusion. State-of-art survival prediction models for BM-E (PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models) are useful clinical tools for orthopaedic surgeons in the decision-making process for the treatment in Asian patients, with SORG models offering the best predictive performance. Rapid growth cancer and serum albumin level are independent, statistically significant factors contributing to survival following surgery of BM-E. Further refinement of survival prediction models will bring about informed and patient-specific treatment of BM-E. Cite this article: Bone Joint J 2024;106-B(2):203–211

Aims. To develop and validate patient-centred algorithms that estimate individual risk of death over the first year after elective joint arthroplasty surgery for osteoarthritis. Methods. A total of 763,213 hip and knee joint arthroplasty episodes recorded in the National Joint Registry for England and Wales (NJR) and 105,407 episodes from the Norwegian Arthroplasty Register were used to model individual mortality risk over the first year after surgery using flexible parametric survival regression. Results. The one-year mortality rates in the NJR were 10.8 and 8.9 per 1,000 patient-years after hip and knee arthroplasty, respectively. The Norwegian mortality rates were 9.1 and 6.0 per 1,000 patient-years, respectively. The strongest predictors of death in the final models were age, sex, body mass index, and American Society of Anesthesiologists grade. Exposure variables related to the intervention, with the exception of knee arthroplasty type, did not add discrimination over patient factors alone. Discrimination was good in both cohorts, with c-indices above 0.76 for the hip and above 0.70 for the knee. Time-dependent Brier scores indicated appropriate estimation of the mortality rate (≤ 0.01, all models). Conclusion. Simple demographic and clinical information may be used to calculate an individualized estimation for one-year mortality risk after hip or knee arthroplasty (. https://jointcalc.shef.ac.uk. ). These models may be used to provide patients with an estimate of the risk of mortality after joint arthroplasty. Cite this article: Bone Joint Res 2020;9(11):808–820

Several different algorithms attempt to estimate life expectancy for patients with metastatic spine disease. The Skeletal Oncology Research Group (SORG) has recently developed a nomogram to estimate survival of patients with metastatic spine disease. Whilst the use of the SORG nomogram has been validated in the international context, there has been no study to date that validates the use of the SORG nomogram in New Zealand. This study aimed to validate the use of the SORG nomogram in Aotearoa New Zealand. We collected data on 100 patients who presented to Waikato Hospital with a diagnosis of spinal metastatic disease. The SORG nomogram gave survival probabilities for each patient at each time point. Receiver Operating Characteristic (ROC) Area Under Curve (AUC) analysis was performed to assess the predictive accuracy of the SORG score. A calibration curve was also performed, and Brier scores calculated. A multivariate Cox regression analysis was performed. The SORG score was correlated with 30 day (AUC = 0.72) and 90-day mortality (AUC = 0.71). The correlation between the SORG score and 90-day mortality was weaker (AUC = 0.69). Using this method, the nomogram was correct for 79 (79%) patients at 30-days, 59 patients (59%) at 90-days, and 42 patients (42%) at 365-days. Calibration curves demonstrated poor forecasting of the SORG nomogram at 30 (Brier score = 0.65) and 365 days (Brier score = 0.33). The calibration curve demonstrated borderline forecasting of the SORG nomogram at 90 days (Brier score = 0.28). Several components of the SORG nomogram were not found to be correlated with mortality. In this New Zealand cohort the SORG nomogram demonstrated only acceptable discrimination at best in predicting life 30-, 90- or 356-day mortality in patients with metastatic spinal disease

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.

The development of an algorithm that provides accurate individualised estimates of revision risk could help patients make informed surgical treatment choices. This requires building a survival model based on fixed and modifiable risk factors that predict outcome at the individual level. Here we compare different survival models for predicting prosthesis survivorship after hip replacement for osteoarthritis using data from the National Joint Registry for England, Wales, Northern Ireland and the Isle of Man. In this comparative study we implemented parametric and flexible parametric (FP) methods and random survival forests (RSF). The overall performance of the parametric models was compared using Akaike information criterion (AIC). The preferred parametric model and the RSF algorithm were further compared in terms of the Brier score, concordance index (C index) and calibration. The dataset contains 327 238 hip replacements for osteoarthritis carried out in England and Wales between 2003 and 2015. The AIC value for the FP model was the lowest. The averages of survival probability estimates were in good agreement with the observed values for the FP model and the RSF algorithm. The integrated Brier score of the FP model and the RSF approach over 10 years were similar: 0.011 (95% confidence interval: 0.011–0.011). The C index of the FP model at 10 years was 59.4% (95% confidence interval: 59.4%–59.4%). This was 56.2% (56.1%–56.3%) for the RSF method. The FP model outperformed other commonly used survival models across chosen validation criteria. However, it does not provide high discriminatory power at the individual level. Models with more comprehensive risk adjustment may provide additional insights for individual risk

Introduction. The development of an algorithm that provides accurate individualised estimates of revision risk could help patients make informed surgical treatment choices. This requires building a survival model based on fixed and modifiable risk factors that predict outcome at the individual level. Here we compare different survival models for predicting prosthesis survivorship after hip replacement for osteoarthritis using data from the National Joint Registry for England, Wales, Northern Ireland and the Isle of Man (NJR). Methods. In this comparative study we implemented parametric and flexible parametric (FP) methods and random survival forests (RSF). The overall performance of the parametric models was compared using Akaike information criterion (AIC). The preferred parametric model and the RSF algorithm were further compared in terms of the Brier score, concordance index and calibration via repeated five-fold cross-validation. Results. The dataset contains 327 238 hip replacements for osteoarthritis carried out in England and Wales between 2003 and 2015. The AIC value for the FP model was the lowest. The averages of survival probability estimates are shown in Figure 1. The integrated Brier score of the FP model and the RSF approach over 10 years were similar: 0.011 (95% confidence interval: 0.011–0.011). The concordance index of the FP model at 10 years was 59.4% (95% confidence interval: 59.4%–59.4%). The concordance index was 56.2% (56.1%–56.3%) for the RSF method. Calibration plots for the FP model and the RSF algorithm are presented in Figure 2. Conclusion. The flexible parametric model outperformed other commonly used survival models across chosen validation criteria. However, it does not provide high discriminatory power at the individual level. This might be due to variable outcomes generated by different fixation or bearing types that cannot be captured using a single model. More complex multi-state models may provide better discrimination. For any figures and tables, please contact the authors directly

Aim. Recurrence of bone and joint infection, despite appropriate therapy, is well recognised and stimulates ongoing interest in identifying host factors that predict infection recurrence. Clinical prediction models exist for those treated with DAIR, but to date no models with a low risk of bias predict orthopaedic infection recurrence for people with surgically excised infection and removed metalwork. The aims of this study were to construct and internally validate a risk prediction model for infection recurrence at 12 months, and to identify factors that predict recurrence. Predictive factors must be easy to check in pre-operative assessment and relevant across patient groups. Methods. Four prospectively collected datasets including 1173 participants treated in European centres between 2003 and 2021, followed up to 12 months after surgery for orthopaedic infections, were included in logistic regression modelling [1–3]. The definition of infection recurrence was identical and ascertained separately from baseline factors in three contributing cohorts. Eight predictive factors were investigated following a priori sample size calculation: age, gender, BMI, ASA score, the number of prior operations, immunosuppressive medication, glycosylated haemoglobin (HbA1c), and smoking. Missing data, including systematically missing predictors, were imputed using Multiple Imputation by Chained Equations. Weekly alcohol intake was not included in modelling due to low inter-observer reliability (mean reported intake 12 units per week, 95% CI for mean inter-rater error −16.0 to +15.4 units per week). Results. Participants were 64% male, with a median age of 60 years (range 18–95). 86% of participants had lower limb orthopaedic infections. 732 participants were treated for osteomyelitis, including FRI, and 432 for PJI. 16% of participants experienced treatment failure by 12 months. The full prediction model had moderate apparent discrimination: AUROC (C statistic) 0.67, Brier score 0.13, and reasonable apparent calibration. Of the predictors of interest, associations with failure were seen with prior operations at the same anatomical site (odds ratio for failure 1.51 for each additional prior surgery; 95% CI 1.02 to 2.22, p=0.06), and the current use of immunosuppressive medications (odds ratio for failure 2.94; 95% CI 0.89 to 9.77, p=0.08). Conclusions. This association between number of prior surgeries and treatment failure supports the urgent need to streamline referral pathways for people with orthopaedic infection to specialist multidisciplinary units

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

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 June 2024 Hip & Pelvis Roundup³⁶⁰ 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.

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.

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

Our aim was to develop and validate nomograms that would predict the cumulative incidence of sarcoma-specific death (CISSD) and disease progression (CIDP) in patients with localized high-grade primary central and dedifferentiated chondrosarcoma.