Background
Estimating the risk of revision after arthroplasty could inform patient and surgeon decision-making. However, there is a lack of well-performing prediction models assisting in this task, which may be due to current conventional modeling approaches such as traditional survivorship estimators (such as Kaplan-Meier) or competing risk estimators. Recent advances in machine learning survival analysis might improve decision support tools in this setting. Therefore, this study aimed to assess the performance of machine learning compared with that of conventional modeling to predict revision after arthroplasty.

Question/purpose
Does machine learning perform better than traditional regression models for estimating the risk of revision for patients undergoing hip or knee arthroplasty?

Methods
Eleven datasets from published studies from the Dutch Arthroplasty Register reporting on factors associated with revision or survival after partial or total knee and hip arthroplasty between 2018 and 2022 were included in our study. The 11 datasets were observational registry studies, with a sample size ranging from 3038 to 218,214 procedures. We developed a set of time-to-event models for each dataset, leading to 11 comparisons. A set of predictors (factors associated with revision surgery) was identified based on the variables that were selected in the included studies. We assessed the predictive performance of two state-of-the-art statistical time-to-event models for 1-, 2-, and 3-year follow-up: a Fine and Gray model (which models the cumulative incidence of revision) and a cause-specific Cox model (which models the hazard of revision). These were compared with a machine-learning approach (a random survival forest model, which is a decision tree–based machine-learning algorithm for time-to-event analysis). Performance was assessed according to discriminative ability (time-dependent area under the receiver operating curve), calibration (slope and intercept), and overall prediction error (scaled Brier score). Discrimination, known as the area under the receiver operating characteristic curve, measures the model’s ability to distinguish patients who achieved the outcomes from those who did not and ranges from 0.5 to 1.0, with 1.0 indicating the highest discrimination score and 0.50 the lowest. Calibration plots the predicted versus the observed probabilities; a perfect plot has an intercept of 0 and a slope of 1. The Brier score calculates a composite of discrimination and calibration, with 0 indicating perfect prediction and 1 the poorest. A scaled version of the Brier score, 1 – (model Brier score/null model Brier score), can be interpreted as the amount of overall prediction error.

Results
Using machine learning survivorship analysis, we found no differences between the competing risks estimator and traditional regression models for patients undergoing arthroplasty in terms of discriminative ability (patients who received a revision compared with those who did not). We found no consistent differences between the validated performance (time-dependent area under the receiver operating characteristic curve) of different modeling approaches because these values ranged between -0.04 and 0.03 across the 11 datasets (the time-dependent area under the receiver operating characteristic curve of the models across 11 datasets ranged between 0.52 to 0.68). In addition, the calibration metrics and scaled Brier scores produced comparable estimates, showing no advantage of machine learning over traditional regression models.

Conclusion
Machine learning did not outperform traditional regression models.

Clinical Relevance
Neither machine learning modeling nor traditional regression methods were sufficiently accurate in order to offer prognostic information when predicting revision arthroplasty. The benefit of these modeling approaches may be limited in this context.

Introduction: It is unclear if the collar and cuff treatment improve alignment in displaced surgical neck fractures of the proximal humerus. Therefore, this study evaluated if the neckshaft angle and extent of displacement would improve between trauma and onset of radiographically visible callus in non-operatively treated surgical neck fractures (Boileau type A, B, C). Materials and Methods: A consecutive series of patients (≥ 18 years old) were retrospectively evaluated from a level 1 trauma center in Australia (inclusion period: 2016–2020) and a level 2 trauma center in the Netherlands (inclusion period: 2004 to 2018). Patients were included if they sustained a Boileau-type fracture and underwent initial non-operative treatment. The first radiograph had to be obtained within 24 h after the initial injury and the follow-up radiograph(s) 1 week after trauma and before the start of radiographically visible callus. On each radiograph, the maximal medial gap (MMG), maximal lateral gap (MLG), and neck-shaft angle (NSA) were measured. Linear mixed modelling was performed to evaluate if these measurements would improve over time. Results: Sixty-seven patients were included: 25 type A, 11 type B, and 31 type C fractures. The mean age (range) was 68 years (24–93), and the mean number (range) of follow-up radiographs per patient was 1 (1–4). Linear mixed modelling on both MMG and MLG revealed no improvement during follow-up among the three groups. Mean NSA of type A fractures improved significantly from 161° at trauma to 152° at last follow-up (p-value = 0.004). Conclusions: Apart from humeral head angulation improvement in type A, there is no increase nor reduction in displacement among the three fracture patterns. Therefore, it is advised that surgical decision-making should be performed immediately after trauma. Level of clinical evidence: Level IV, retrospective case series.