Risk Prediction of Major Adverse Cardiovascular Events Occurrence Within 6 Months After Coronary Revascularization:...

Area of Science:

• Cardiology
• Medical Informatics
• Machine Learning

Background:

• Coronary heart disease incidence is rising globally.
• Coronary revascularization, including percutaneous coronary intervention, is crucial for treatment.
• Major adverse cardiovascular events (MACE) post-revascularization remain a significant clinical challenge.

Purpose of the Study:

• To develop and validate machine learning models for predicting MACE within six months post-coronary revascularization.
• To identify key factors influencing MACE occurrence.

Main Methods:

• A retrospective study of 1004 patients undergoing coronary revascularization.
• Utilized six machine learning algorithms: decision tree, random forest, logistic regression, naïve Bayes, support vector machine, and XGBoost.
• Employed an oversampling strategy, 70% training/30% validation split, and assessed performance using accuracy, precision, recall, F1-score, and AUC.

Main Results:

• XGBoost achieved the highest performance with an AUC of 0.8599, accuracy of 0.7788, precision of 0.8058, recall of 0.7345, and F1-score of 0.7685.
• Anticoagulant drug use and disease course were identified as top predictive factors for MACE.
• 21 patient characteristics were found to be statistically significant predictors of MACE.

Conclusions:

• Machine learning models provide acceptable performance for MACE prediction after coronary revascularization.
• The XGBoost model offers a valuable tool for targeted intervention and clinical decision-making.
• These models can aid in the prevention of MACE in patients undergoing coronary revascularization.