JMIR Publications

ABSTRACT

Background:

With the global aging population, chronic diseases, economic woes, and labor shortages emerge. Elderly activities of daily living (ADL) dysfunction impacts lives and burdens society.

Objective:

Aging populations have led to increased chronic diseases, economic challenges, and labor shortages, posing a significant threat to public health. To address this, a predictive model for activities of daily living (ADL) dysfunction in the elderly was developed and validated.

Methods:

Data from 5081 participants aged 60 to 80 in the China Health and Retirement Longitudinal Survey (CHARLS) wave 3 was analyzed. Participants were divided into training and testing groups. Predictive factors were identified using Least Absolute Shrinkage and Selection Operator (LASSO) and multivariable logistic regression, resulting in a nomogram model. The model's performance was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Decision Curve Analysis (DCA). SHapley Additive exPlanations (SHAP) values were used to interpret the characteristics of the model's predictor variables.

Results:

Six variables were identified as feature variable for ADL dysfunction in the elderly, which were integrated into the final model. The nomogram's predictive performance was deemed acceptable, with ROC curve values of 0.77 (95% CI: 0.76-0.79) for the training set and 0.77 (95% CI: 0.75-0.79) for the testing set. The calibration curve confirmed the model's accuracy, and the DCA showed it had good clinical utility.

Conclusions:

Six key factors were chosen to create a nomogram predicting ADL dysfunction in the elderly. This nomogram demonstrates high evaluation performance and serves as a dependable tool for forecasting ADL dysfunction in the elderly.