Prediction of the fall risk at home in maintenance-hemodialysis patients.

This study aimed to identify key factors associated with home falls and to develop a prediction model for maintenance hemodialysis (MHD) patients using the Person-Environment-Occupation (PEO) framework. In a single-center retrospective cohort of 365 MHD patients, multidimensional data were collected and variables were selected using LASSO regression. A Random Forest (RF) prediction model was developed, with the Synthetic Minority Over-sampling Technique (SMOTE) applied to address class imbalance. The RF model showed good discriminative performance in the internal test set, with an area under the curve (AUC) of 0.938 (95% CI: 0.89-0.98), accuracy of 0.909, sensitivity of 0.922, and specificity of 0.850. SHAP analysis revealed the top six predictors as history of falls, serum potassium level, use of walking aids, absence of anti-slip devices in bathrooms, intradialytic hypotension, and history of diabetes mellitus. The RF model developed within the PEO framework showed promising performance for identifying home fall risk in MHD patients in this single-center cohort. This model may assist in preliminary risk stratification and highlight potentially modifiable factors, although external validation is required before broader clinical application.