JMIR Publications

ABSTRACT

Background:

The risk of developing atherosclerotic cardiovascular disease (ASCVD) varies among individuals and is related to a variety of lifestyle factors in addition to the presence of chronic diseases.

Objective:

We aimed to assess the predictive accuracy of machine learning (ML) models incorporating lifestyle risk behaviors for ASCVD risk using Korean nationwide database.

Methods:

Utilizing data from the Korea National Health and Nutrition Examination Survey, five ML algorithms were employed for the prediction of high ASCVD risk: logistic regression, support vector machine, random forest, extreme gradient boosting (XGB), and light gradient boosting (LGB) models. ASCVD risk was assessed using the Pooled Cohort Equations, with a high-risk threshold of ≥7.5% over 10 years. Among the 8,573 participants aged 40–79 years, propensity score matching (PSM) was used to adjust for demographic confounders. We divided the dataset into a training and a test dataset in an 8:2 ratio. We also used bootstrapping to train the ML model with the area under the receiver operating characteristics curve (AUROC) score. Shapley additive explanations was used to identify the models’ important variables in assessing high ASCVD risks. In sensitivity analysis, we additionally performed binary logistic regression analysis, in which the ML model’s results were consistent with conventional statistical model.

Results:

Of 8,573 participants, 41.7% had high ASCVD risk. Before PSM, age and sex differed significantly between groups. PSM (1:1) yielded 1,976 patients with balanced demographics. After PSM, the high ASCVD risk group had higher alcohol/tobacco use, lower omega-3 intake, higher BMI, less physical activity, and spent less time sitting. In 5 ML models, XGB model showed high AUROC values, with LGB model outperforming in accuracy, recall, and F1 score. Variable importance analysis using Shapley additive explanations identified smoking and age as the strongest predictors, while BMI, sodium or omega-3 intake, and LDL cholesterol also had significant variables. Sensitivity analysis using multivariable LR analysis also confirmed these findings, showing that smoking, BMI, and LDL cholesterol increased ASCVD risk, whereas omega-3 intake and physical activity were associated with lower risk.

Conclusions:

Analyzing lifestyle behavioral factors in ASCVD risk with ML improves predictive performance compared to traditional models. Personalized prevention strategies tailored to an individual’s lifestyle can effectively reduce ASCVD risk.