The developed nomogram achieved an AUC of 0.800 for predicting ADL dysfunction in middle-aged and older adults with comorbid hypertension and diabetes.
A nomogram incorporating seven clinical and psychosocial predictors can accurately identify middle-aged and older adults with comorbid hypertension and diabetes at risk for activities of daily living dysfunction.
Absolute Event Rate: 0% vs 0%
To develop and validate an interpretable model for predicting activities of daily living (ADL) dysfunction in middle-aged and older adults with comorbid hypertension and diabetes. This is a cross-sectional study. Data were derived from wave 4 of the China Health and Retirement Longitudinal Study. After applying inclusion and exclusion criteria, 1,623 participants were included. Least absolute shrinkage and selection operator regression was used for feature selection, followed by multivariable logistic regression to construct a nomogram. Model performance was assessed using receiver operating characteristic curves, the area under the curve (AUC), calibration plots, and decision curve analysis. The final nomogram incorporated seven predictors: history of falls, stroke, psychiatric disorders, number of healthy children, Center for Epidemiologic Studies Depression Scale score, number of pain sites, and level of social participation. The model achieved an AUC of 0.800 in both training (95% CI: 0.772–0.828) and testing (95% CI: 0.758–0.842) sets. Calibration analysis indicated close agreement between predicted and observed outcomes. We developed and validated an interpretable model with good predictive performance. The model provides a practical basis for personalized interventions and may support clinical practice aimed at preserving functional health in aging populations with multimorbidity. Not applicable.
Lin et al. (Sat,) reported a other. The developed nomogram achieved an AUC of 0.800 for predicting ADL dysfunction in middle-aged and older adults with comorbid hypertension and diabetes.