Construction and Validation of Cardiovascular Disease Prediction Model for Dietary Macronutrients—Data from the China Health and Nutrition Survey

Abstract

Background: There are currently many studies on predictive models for cardiovascular disease (CVD) that do not use dietary macronutrients for prediction. This study aims to provide a non-invasive model incorporating dietary information to predict the risk of CVD in adults. Methods: The data for this study were obtained from the China Health and Nutrition Survey (CHNS) spanning the years 2004 to 2015. The dataset was divided into training and validation sets at ratio of 7:3. Variables were screened by LASSO, and the Cox proportional hazards regression model was used to construct the 10-year risk prediction model of CVD. The model’s performance was assessed using the concordance index (C-index), receiver operating characteristic (ROC) curve, calibration plots, and decision curve analysis (DCA) for discrimination, calibration, and clinical utility. Results: This study included 5,186 individuals, with males accounting for 48.1% and a mean age of 46.39 ± 13.74 years, and females accounting for 51.9% and a mean age of 47.36 ± 13.29 years. The incidence density was 10.84/1000 person years. The model ultimately incorporates 11 non-invasive predictive factors, including dietary-related, demographic indicators, lifestyle behaviors, and disease history. Performance measures for this model were significant (AUC = 0.808 [(95%CI: 0.778–0.837], C-index = 0.797 [0.765–0.829]). After applying the model to internal validation cohorts, the AUC and C-index were 0.799 (0.749–0.838), and 0.788 (0.737–0.838), respectively. The calibration and DCA curves showed that the non-invasive model has relatively high stability, with a good net return. Conclusions: We developed a simple and rapid non-invasive model predictive of CVD for the next 10 years among Chinese adults.