Objective  To develop and validate a prediction model to assess the risk of depression in patients with chronic kidney disease (CKD) based on National Health and Nutrition Examination Survey (NHANES) database. Methods  Data on patients with CKD were selected from the NHANES 2005–2018 cycles. Participants were randomly divided into a training set and a validation set in a 7∶3 ratio for model development and validation, respectively. Multivariable logistic regression was used in the training set to identify independent risk factors associated with depression in CKD patients, with stepwise selection applied to determine the final predictors. Model performance was assessed using receiver operating characteristic curve (ROC), calibration plots, and decision curve analysis (DCA). Internal validation was performed through bootstrap resampling, and a predictive model was ultimately established. Results  A total of 4413 CKD patients were included, including 2112 males (47.86%) and 2301 females (52.14%). Among them, 3089 patients were assigned to the training set and 1324 to the validation set. In the training set, 332 patients (10.75%) presented with depressive symptoms, while 143 patients (10.80%) in the validation set had depressive symptoms. Multivariate logistic regression analysis showed that other hispanic, current smoking, and sleep disorders were risk factors (P＜0.05); Male, middle or high-income, high school grad/ged or above, married or widowed were protective factors (P＜0.05). Finally, 7 variables were included to construct a prediction model, including gender, poverty income ratio, education level, marital status, smoking status, body mass index, and sleep disorders. The ROC curve showed that the AUC=0.773 [95%CI (0.747, 0.799)] in the training set, the internal validation was evaluated by 1000 Bootstrap resampling methods, and the corrected C-index=0.763. The validation set AUC=0.778 [95%CI(0.740, 0.815)], showed good discrimination ability. The calibration curve showed that the model’s predicted probability was highly consistent with the actual occurrence. Decision curve analysis showed that the model provides a significant net benefit for clinical decision-making at a threshold probability of 20%～50%. Conclusions  The prediction model constructed in this study can effectively predict the risk of depression in patients with CKD and can provide guidance for early screening and personalized intervention for high-risk groups. However, the external validation and localization of the model still needed further research.

Copyright © the editorial department of West China Medical Journal of West China Medical Publisher. All rights reserved