Development and validation of a nomogram for predicting depression risk in patients with chronic kidney disease based on NHANES 2005-2018

Abstract

Background: Depression is common among patients with chronic kidney disease (CKD) and is associated with poor outcomes. This study aims to develop and validate a nomogram for predicting depression risk in patients with CKD.

Methods: This cross-sectional study utilized data from the 2005-2018 National Health and Nutrition Examination Survey (NHANES) database. Participants were randomly divided into training and validation sets (7:3 ratio). A nomogram was developed based on predictors identified using Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariate logistic regression. Model performance was evaluated using ROC curves, calibration curves, and decision curve analysis.

Results: A total of 4414 participants were included. Gender, age, race, poverty-to-income ratio, diabetes mellitus, cardiovascular diseases, trouble sleeping, sleep hours, and smoking were included as predictors in the nomogram. The area under the curve (AUC) of the nomogram for predicting depression risk in patients with CKD was 0.785 (95% CI: 0.761-0.809) in the training set and 0.773 (95% CI: 0.737-0.810) in the validation set. The corrected C-index, calculated using bootstrap resampling, was 0.776, indicating good predictive performance. Calibration curves and decision curve analysis showed good calibration and clinical utility. Subgroup and sensitivity analyses further confirmed the robustness of the nomogram. A web-based risk calculator based on the nomogram was developed to enhance clinical applicability. A flowchart demonstrating the application of the nomogram for risk assessment and clinical decision-making in routine practice is provided.

Conclusions: This nomogram effectively predicts depression risk in patients with CKD and may serve as a user-friendly tool for the early identification of patients with CKD at high risk for depression using key demographic, comorbid, and lifestyle factors.

Keywords: Chronic kidney disease; Cross-sectional study; Depression; NHANES; Nomogram; Questionnaire; Sociodemographic characteristics.

Fig. 1

Flowchart of study participants

Fig. 2

Predictor selection using Lasso regression analysis. (A) Coefficient profiles show the change in variable coefficients across different values of λ. (B) The optimal λ was determined via 10-fold cross-validation, indicated by the right vertical line, corresponding to the minimum error within one standard error

Fig. 3

Nomogram for predicting depression risk in patients with chronic kidney disease. For each factor listed on the left side of the nomogram, locate the corresponding value on the horizontal axis and draw a vertical line upward to the points scale at the top of the nomogram. The number of points is determined by the position of the factor on its scale. After assigning points for each factor, sum them to obtain the total points. Then, draw a vertical line downward from the total points to the “Predicted risk of depression” scale to determine the patient’s predicted risk

Fig. 4

Evaluation of the nomogram’s predictive performance for depression risk in patients with chronic kidney disease. (A) ROC curve of the nomogram in the training set. (B) ROC curve in the validation set. (C) Calibration curve of the nomogram in the training set. (D) Calibration curve in the validation set. (E) Decision curve analysis of the nomogram in the training set. (F) Decision curve analysis in the validation set

Fig. 5

Flowchart demonstrating the application of the nomogram for risk assessment and clinical decision-making in routine practice