Oh Juhan, Park Minah, Cha Yonghan, Kim Jae-Hyun, Kim Seung Hoon
Eulji University School of Medicine, Daejeon, Republic of Korea.
Department of Ophthalmology, Soonchunhyang University Hospital Cheonan, Soonchunhyang University College of Medicine, 31 Soonchunhyang 6-Gil Dongnam-Gu, Cheonan, 31151, Republic of Korea.
BMC Musculoskelet Disord. 2025 May 8;26(1):451. doi: 10.1186/s12891-025-08710-z.
To evaluate machine learning-based survival model roles in predicting rehospitalization after hip fractures to improve reduce the burden on the healthcare system.
This retrospective cohort study examined 718 patients with hip fractures hospitalized at the Daejeon Eulji Medical Center between January 2020 and June 2022. Demographic and clinical variables, and rehospitalization data were collected at 6 weeks and 3, 6, 12, and 24 months. Cox proportional hazards (CoxPH), random survival forest (RSF), gradient boosting (GB), and fast survival support vector machine (SVM) models were developed. Model performance was assessed using the concordance index (c-index), area under the curve (AUC), and Kaplan-Meier survival curves. Feature importance was analyzed using permutation importance, with the best model selected based on overall performance.
Hyperparameter tuning optimized the models. The GB model had the highest mean AUC of 0.868, followed by the RSF (0.785), SVM (0.763), and CoxPH (0.736) models. Feature importance analysis highlighted femoral neck T-score, age, body mass index, operation time, compression fracture, and total calcium as significant predictors. Feature selection improved the c-index for the RSF model from 0.742 to 0.874 and CoxPH model from 0.717 to 0.915; the GB and SVM models exhibited a c-index decline post-feature selection. The GB and RSF models predicted lower rehospitalization probabilities than Kaplan-Meier estimates; the CoxPH model's predictions were closely aligned with the observed data.
The effect of feature selection on model performance highlights the need for comprehensive variable selection and model evaluation strategies to improve predictive accuracy.
评估基于机器学习的生存模型在预测髋部骨折后再入院情况中的作用，以减轻医疗系统负担。
这项回顾性队列研究对2020年1月至2022年6月期间在大田乙支医疗中心住院的718例髋部骨折患者进行了检查。收集了人口统计学和临床变量以及在6周、3个月、6个月、12个月和24个月时的再入院数据。开发了Cox比例风险（CoxPH）模型、随机生存森林（RSF）模型、梯度提升（GB）模型和快速生存支持向量机（SVM）模型。使用一致性指数（c指数）、曲线下面积（AUC）和Kaplan-Meier生存曲线评估模型性能。使用排列重要性分析特征重要性，根据整体性能选择最佳模型。
超参数调整优化了模型。GB模型的平均AUC最高，为0.868，其次是RSF模型（0.785）、SVM模型（0.763）和CoxPH模型（0.736）。特征重要性分析突出显示股骨颈T评分、年龄、体重指数、手术时间、压缩性骨折和总钙是重要预测因素。特征选择使RSF模型的c指数从0.742提高到0.874，使CoxPH模型的c指数从0.717提高到0.915；GB模型和SVM模型在特征选择后c指数下降。GB模型和RSF模型预测的再入院概率低于Kaplan-Meier估计值；CoxPH模型的预测与观察数据密切一致。
特征选择对模型性能的影响凸显了需要综合的变量选择和模型评估策略来提高预测准确性。
