Association Between Dietary Vitamin Intake and Severe Abdominal Aortic Calcification in U.S. Adults: A SHAP-Based Machine Learning Analysis of NHANES 2013–2014

Background: Severe abdominal aortic calcification (SAAC) significantly impacts families and society. Although vitamin intake is closely linked to SAAC, large-scale model-based dietary studies are scarce. This study compares machine learning models to analyze this association and support dietary strategies for SAAC prevention. Methods: There are 10 ways to build ML models. The best model for further analysis was selected based on accuracy, area under the subject operating characteristic curve (AUC), precision, recall, and F1 score. Shapley Additive Explanations (SHAP) method was used to explain the contribution of variables to ML models. Results: Logistic Regression (LR) exhibited the best performance in exploring the association between dietary vitamins and SAAC, with an AUC of 0.851. The SHAP values indicate that among dietary vitamins, vitamin A has the greatest contribution to the machine learning (ML) model. Age is the most important feature among all characteristics, while folate has the least impact on the ML model. Conclusion: LR algorithm performed best, vitamin A was the most significant factor, folic acid correlation was weak.The model is helpful for early screening and intervention of SAAC and improves patient prognosis.