Development and Validation of a Risk Prediction Model for Depression in Patients with Stroke

Abstract Objective Stroke is the third leading cause of death and disability worldwide in 2019. In stroke patients, about one-third or more are affected by depression, which makes it a serious social and public health problem. This study aims to create and validate a nomogram for early prediction and identification of depression in stroke patients. Methods Cross-sectional data from 605 stroke survivors aged 60 and over in the CHARLS 2011, 2015 was used. Participants were split into training and testing groups. Predictive factors were identified using Least Absolute Shrinkage and Selection Operator (LASSO) and multivariable logistic regression, leading to the creation of a nomogram model. The model’s performance was assessed with Receiver Operating Characteristic (ROC) curves, the Concordance Index (C-index), calibration plots, and Decision Curve Analysis (DCA). Results It identified Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), sleep hours, uric acid, and Triglyceride-Glucose-Body Mass Index (TyG-BMI) as risk factors for depression post-stroke, which were integrated into the final model. The nomogram’s predictive performance was deemed acceptable, with ROC curve values of 0.7512 (95% CI: 0.705–0.798) for the training set and 0.723 (95% CI: 0.65–0.797) for the testing set. The calibration curve confirmed the model’s accuracy, and the DCA showed it had clinical utility. Conclusions Five key factors were chosen to create a nomogram predicting depression in stroke patients. This nomogram demonstrates evaluation performance and serves as a tool for forecasting depression in this population.