Preoperative factors predict prolonged length of stay, serious adverse complications, and readmission following operative intervention of proximal humerus fractures: a machine learning analysis of a national database

Abstract

Proximal humerus fractures are a common injury, predominantly affecting older adults. This study aimed to develop risk-prediction models for prolonged length of hospital stay (LOS), serious adverse complications, and readmission within 30 days of surgically treated proximal humerus fractures using machine learning (ML) techniques. Adult patients (age >18) who underwent open reduction internal fixation (ORIF), hemiarthroplasty, or total shoulder arthroplasty for proximal humerus fracture between 2016 and 2021 were included. Preoperative demographic and clinical variables were collected for all patients and used to establish ML-based algorithms. The model with optimal performance was selected according to area under the curve (AUC) on the receiver operating curve (ROC) curve and overall accuracy, and the specific predictive features most important to model derivation were identified. A total of 7473 patients were included (72.1% male, mean age 66.2±13.7 years). Models produced via gradient boosting performed best for predicting prolonged LOS and complications. The model predicting prolonged LOS demonstrated good discrimination and performance, as indicated by (Mean: 0.700, SE: 0.017), recall (Mean: 0.551, SE: 0.017), accuracy (Mean: 0.717, SE: 0.010), F1-score (Mean: 0.616, SE: 0.014), AUC (Mean: 0.779, SE: 0.010), and Brier score (Mean: 0.283, SE: 0.010) Preoperative hematocrit, preoperative platelet count, and patient age were considered the strongest predictive features. The model predicting serious adverse complications exhibited comparable discrimination [precision (Mean:0.226, SE: 0.024), recall (Mean: 0.697, SE: 0.048), accuracy (Mean: 0.811, SE: 0.010), F1-score (Mean: 0.341, SE: 0.031)] and superior performance relative to the LOS model [AUC (Mean: 0.806, SE:0.024), Brier score (Mean: 0.189, SE: 0.010), noting preoperative hematocrit, operative time, and patient age to be most influential. However, the 30-day readmission model achieved the weakest relative performance, displaying low measures of precision (Mean: 0.070, SE: 0.012) and recall (Mean: 0.389, SE: 0.053), despite good accuracy (Mean: 0.791, SE: 0.009). Predictive models constructed using ML techniques demonstrated favorable discrimination and satisfactory-to-excellent performance in forecasting prolonged LOS and serious adverse complications occurring within 30 days of surgical intervention for proximal humerus fracture. Modifiable preoperative factors such as hematocrit and platelet count were identified as significant predictive features, suggesting that clinicians could address these factors during preoperative patient optimization to enhance outcomes. Overall, these findings highlight the potential for ML techniques to enhance preoperative management, facilitate shared decision-making, and enable more effective and personalized orthopedic care by exploring alternative approaches to risk stratification.