Development and Validation of a Risk Prediction Model for Digestive Tract Diseases in Chinese Patients With Depression

ABSTRACT Objective To develop and validate a risk prediction model for digestive tract diseases in depressed individuals, facilitating early identification of high‐risk populations and guiding personalized preventive interventions. Methods This study utilized data from the China Health and Retirement Longitudinal Study (CHARLS) for the years 2011 and 2015. Depressed patients from the 2011 dataset were randomly split into a training group (70%) and a validation group (30%). Independent prognostic factors were identified via eXtreme Gradient Boosting (XGBoost), Least absolute shrinkage and selection operator (LASSO) regression, and multivariate logistic regression. A nomogram model was constructed based on the contribution of these predictive factors and subsequently evaluated using the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC). External validation was conducted using data from depressed patients in 2015. Results This study included 4006 patients with depression from the 2011 CHARLS, with a prevalence of gastrointestinal diseases of 31.4%. The final model included UA, HCT, sleep quality, difficulty running or jogging 1 km, hypertension, chest pain, chronic lung diseases, heart diseases, kidney diseases, and arthritis or rheumatism. The area under the curve (AUC) was 0.678 (95% CI: 0.657–0.699) in the training set, 0.651 (95% CI: 0.619–0.686) in internal validation, and 0.693 (95% CI: 0.674–0.713) in external validation. The ROC curve indicates that the model has good predictive accuracy, and the calibration curve shows a high consistency between the predicted and actual results. DCA and CIC confirm that the model has a high net clinical benefit. Conclusion The model developed in this study is effective in predicting the occurrence of gastrointestinal diseases in people with depression and can be used for early identification and targeted preventive measures in high‐risk populations to reduce the risk of gastrointestinal diseases.