基于机器学习算法构建日常生活活动能力障碍老年人抑郁风险预测模型

打开文本图片集

【中图分类号】R749.4 【文献标识码】A

【Abstract】 Objective Explore the influencing factors depression in elderly people with activities daily living （ADL） disorders，and constructa depression risk prediction model for elderly people with ADL disorders in based on machine learning （ML） algorithms. Methods Based on the fifth round data from the Health and Retirement Longitudinal Study （CHARLS） project， the Boruta algorithm and Lasso regression algorithm were used to screen depression risk factors in elderly people with ADL disorders.The9 ML methods random forest， light gradient boosting machine，extreme gradient boosting，Logistic regression，K-nearest neighbor， support vector machine， artificial neural network，decision tree，and Elastic Net regression algorithm were used to constructa depresion risk prediction model，and SHAP algorithm was used to explain the final model. Results A total 3，167 elderly individuals with ADL disorders were included， with a depression detection rate 60.69% . The random forest model has the best predictive performance， with AUCs 0.804 [95%C] （0.788， 0.820）] and 0.779 [95%C] （0.752， 0.806）] on the training and testing sets，respectively.The SHAP algorithm results showed that the impact life satisfaction，painand discomfort，self-rated healthstatus，satisfaction withchildrelationships，gender，whetherany falls have occurred since 2018，the numberoutpatient visits to medical institutions in a month，age，education level，and whether the internet has been used in the past month on thedepression risk prediction model for elderly people with ADL disorders decreased in order.The calibration curve indicates that the predicted performance the model is basically consistent with the actual results，and the decision curve shows that the model has good clinical applicability. Conclusion Early age，female，low educational level，declining self-evaluation health status，lowlifesatisfaction，lowchild relationshipsatisfaction，increased numberoutpatient clinics inmedical institutions，fals，physical pain，and inability to use the internet significantly increased the risk depression among the elderly with ADL disorders. Among the depression risk prediction models constructed based on ML algorithm， the random forest model achieved the optimal prediction performance.

【KeyWords】Activity daily living ability; Depression; Risk prediction model; Machine learning SHAP algorithm

国家统计局最新数据显示，我国已进人中度老龄化社会，随着老龄化的进一步加深，日常生活活动（activitydailyliving，ADL）能力在老年人身心健康中扮演着重要角色。（剩余15113字）