Chu Jingjing, Li Ying, Wang Xinyi, Xu Qun, Xu Zherong
The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qingchun Road, Hangzhou, 310003, China, 86 057187236171.
Zhejiang University School of Medicine, Hangzhou, China.
JMIR Aging. 2025 Apr 17;8:e66723. doi: 10.2196/66723.
Disability profoundly affects older adults' quality of life and imposes considerable burdens on health care systems in China's aging society. Timely predictive models are essential for early intervention.
We aimed to build effective predictive models of disability for early intervention and management in older adults in China, integrating physical, cognitive, physiological, and psychological factors.
Data from the China Health and Retirement Longitudinal Study (CHARLS), spanning from 2015 to 2020 and involving 2450 older individuals initially in good health, were analyzed. The dataset was randomly divided into a training set with 70% data and a testing set with 30% data. LASSO regression with 10-fold cross-validation identified key predictors, which were then used to develop an Extreme Gradient Boosting (XGBoost) model. Model performance was evaluated using receiever operating characteristic curves, calibration curves, and clinical decision and impact curves. Variable contributions were interpreted using SHapley Additive exPlanations (SHAP) values.
LASSO regression was used to evaluate 36 potential predictors, resulting in a model incorporating 9 key variables: age, hand grip strength, standing balance, the 5-repetition chair stand test (CS-5), pain, depression, cognition, respiratory function, and comorbidities. The XGBoost model demonstrated an area under the curve of 0.846 (95% CI 0.825-0.866) for the training set and 0.698 (95% CI 0.654-0.743) for the testing set. Calibration curves demonstrated reliable predictive accuracy, with mean absolute errors of 0.001 and 0.011 for the training and testing sets, respectively. Clinical decision and impact curves demonstrated significant utility across risk thresholds. SHAP analysis identified pain, respiratory function, and age as top predictors, highlighting their substantial roles in disability risk. Hand grip and the CS-5 also significantly influenced the model. A web-based application was developed for personalized risk assessment and decision-making.
A reliable predictive model for 5-year disability risk in Chinese older adults was developed and validated. This model enables the identification of high-risk individuals, supports early interventions, and optimizes resource allocation. Future efforts will focus on updating the model with new CHARLS data and validating it with external datasets.
在中国老龄化社会中，残疾严重影响老年人的生活质量，并给医疗保健系统带来相当大的负担。及时的预测模型对于早期干预至关重要。
我们旨在构建有效的老年人残疾预测模型，以便在中国老年人中进行早期干预和管理，综合考虑身体、认知、生理和心理因素。
分析了中国健康与养老追踪调查（CHARLS）2015年至2020年的数据，涉及2450名最初健康状况良好的老年人。数据集被随机分为包含70%数据的训练集和包含30%数据的测试集。采用10折交叉验证的LASSO回归确定关键预测因素，然后用于开发极端梯度提升（XGBoost）模型。使用受试者工作特征曲线、校准曲线以及临床决策和影响曲线评估模型性能。使用SHapley加性解释（SHAP）值解释变量贡献。
LASSO回归用于评估36个潜在预测因素，得到一个包含9个关键变量的模型：年龄、握力、站立平衡、5次重复坐立试验（CS-5）、疼痛、抑郁、认知、呼吸功能和合并症。XGBoost模型在训练集的曲线下面积为0.846（95%CI 0.825-0.866），在测试集为0.698（95%CI 0.654-0.743）。校准曲线显示预测准确性可靠，训练集和测试集的平均绝对误差分别为0.001和0.011。临床决策和影响曲线显示在不同风险阈值下具有显著效用。SHAP分析确定疼痛、呼吸功能和年龄是主要预测因素，突出了它们在残疾风险中的重要作用。握力和CS-5也对模型有显著影响。开发了一个基于网络的应用程序用于个性化风险评估和决策。
开发并验证了一个可靠的中国老年人5年残疾风险预测模型。该模型能够识别高危个体，支持早期干预，并优化资源分配。未来的工作将集中于用新的CHARLS数据更新模型并用外部数据集进行验证。
