Key result
Machine learning with lifestyle factors improves prediction of high 10-year ASCVD risk over traditional models.
Why the study?
ASCVD risk varies by individual and relates to lifestyle factors alongside chronic diseases; this study evaluated machine learning models incorporating lifestyle risk behaviors to predict ASCVD risk.
Do machine learning models incorporating lifestyle risk behaviors accurately predict high ASCVD risk in Korean adults?
Observational (n=8,573)
Yes
Do machine learning models incorporating lifestyle risk behaviors accurately predict high ASCVD risk in Korean adults?
Machine learning models incorporating lifestyle factors such as smoking, diet, and physical activity can effectively predict high ASCVD risk and may improve personalized prevention strategies.
Answers are grounded in this paper and cite their sources.
May support refined ASCVD prediction with lifestyle data in Koreans; hypothesis-generating and requires prospective validation.
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.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2025) conducted an observational in Atherosclerotic cardiovascular disease risk (n=8,573). Machine learning models incorporating lifestyle risk behaviors vs. Traditional statistical models was evaluated on Predictive accuracy for high ASCVD risk (≥7.5% over 10 years). Machine learning models incorporating lifestyle factors like smoking and age improved the prediction of high 10-year ASCVD risk compared to traditional statistical models.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: