Machine learning framework for atherosclerotic cardiovascular disease risk assessment

Introduction: Atherosclerotic cardiovascular disease (ASCVD) is the first leading cause of mortality globally. To identify the individual risk factors of ASCVD utilizing the machine learning (ML) approaches. Materials & methods: This cohort-based cross-sectional study was conducted on data of 500 participants with ASCVD among Tabriz University Medical Sciences employees, during 2020. The data with ML methods were developed and validated to predict ASCVD risk with naive Bayes (NB), spurt vesture machines (SVM), regression tree (RT), k-nearest neighbors (KNN), artificial neural networks (ANN), generalized additive models (GAM), and logistic regression (LR). Results: Accuracy of the models ranged from 95.7 to 98.1%, with a sensitivity of 50.0 to 97.3%, specificity of 74.3 to 99.1%, positive predictive value (PPV) of 0.0 to 98.0%, negative predictive value (NPV) of 68.4 to 100.0%, positive likelihood ratio (LR +) of 13.8 to 96.4%, negative likelihood ratio (LR-) of 3.6 to 51.9%, and area under ROC curve (AUC) of 62.5 to 99.4%. The ANN fit the data best with an accuracy of 98.1% (95% CI: 96.5–99.1), a specificity of 99.1% (95% CI: 97.7–99.9), a LR + of 96.4% (95% CI: 36.2–258.8), and AUC of 99.4% (95% CI: 85.2–97.0). Based on the optimal model, sex (females), age, smoking, and metabolic syndrome were shown to be the most important risk factors of ASCVD. Conclusion: Sex (females), age, smoking, and metabolic syndrome were predictors obtained by ANN. Considering the ANN as the optimal model identified, more accurate prevention planning may be designed.