This analysis identifies metabolic syndrome's impact on coronary artery disease severity, suggesting focused interventions based on machine learning models.
Key Points
XGBoost achieved 83.12% accuracy in predicting coronary artery disease severity with metabolic syndrome features included, emphasizing its effectiveness.
Significant aggravating factors identified included HDL, HBG, and LWS, which highlight the complexity of diagnosing coronary artery disease.
The analytical methods employed included correlation analysis and odds ratio calculations to evaluate risk factor significance in patients.
Findings may guide future personalized treatment strategies for coronary artery disease, indicating the need for further validation in diverse populations.