Development and internal validation of a nomogram for identifying PHQ-9-defined depression in heart failure patients: A study based on NHANES data from 2005 to 2018.

BACKGROUND: Depression is common in patients with heart failure and may worsen quality of life and clinical outcomes. This study aimed to develop and internally validate a nomogram for identifying heart failure patients with a higher probability of PHQ-9-defined depression. METHODS: We included 856 participants with self-reported physician-diagnosed heart failure from NHANES 2005-2018. The sample was randomly divided into a training set (n = 598) and a validation set (n = 258). Depression was defined as a PHQ-9 score ≥ 10. Weighted univariate logistic regression, LASSO, and Boruta were used for feature selection. Model performance was assessed using ROC analysis, calibration, Hosmer-Lemeshow test, bootstrap validation, 10-fold cross-validation, and decision curve analysis. RESULTS: Nine predictors were included in the nomogram: gender, age, serum uric acid, asthma, poverty-income ratio, blood urea nitrogen, stroke history, memory problems, and sleep problems. The AUC was 0.806 in the training set and 0.683 in the validation set. At a cutoff probability of 0.232, sensitivity was 0.658 and specificity was 0.813. Ten-fold cross-validation yielded a mean AUC of 0.755. RCS analyses showed approximately linear relationships for poverty-income ratio, serum uric acid, and blood urea nitrogen. CONCLUSION: This internally validated nomogram may help classify PHQ-9-defined depression among patients with heart failure. Independent validation is still needed.