Developing a Nomogram Prediction Model for Dietary Behavior Adherence in Hemodialysis Patients.

Objective: To develop a nomogram prediction model for dietary behavior adherence in hemodialysis (HD) patients, providing a simple and accurate tool for individualized risk prediction and supporting effective intervention strategies. Methods: A total of 236 HD patients admitted from January 2022 to January 2024 were retrospectively included as the modeling group, and another 121 HD patients admitted from January 2024 to May 2025 served as the validation group. Patients in both groups were classified into compliance and non-compliance groups according to their dietary adherence. Lasso regression and multivariate logistic analysis were used to identify independent predictors and construct the nomogram. Internal and external validation were performed using ROC curves, the Hosmer-Lemeshow (H-L) test, calibration curves, and decision curve analysis (DCA). Results: Among the 236 patients in the modeling group, 73 (30.93%) showed dietary non-compliance. Age, years on dialysis, educational level, dietary knowledge, social support, family support, and self-care ability significantly differed between the two groups (P<0.05). Seven variables selected by Lasso regression were entered into logistic analysis. Age, years on dialysis, and poor self-care ability were risk factors for non-adherence, whereas higher educational level, better dietary knowledge, stronger social support, and family support were protective factors (P<0.05). The internal validation yielded an AUC of 0.884 and an H-L χ Conclusion: Age, years on dialysis, educational level, dietary knowledge, social support, family support, and self-care ability are key factors influencing dietary adherence in HD patients. The nomogram based on these variables demonstrated good discrimination and clinical benefit, aiding early identification of high-risk patients and supporting individualized dietary management.