Machine Learning-Based Risk Prediction for Coronary Heart Disease Complicated by Hyperhomocysteinemia: Retrospective Study - PubMed
7 hours ago
- #hyperhomocysteinemia
- #machine learning
- #coronary heart disease
- Hyperhomocysteinemia (HHcy) is an independent risk factor for coronary heart disease (CHD).
- The study developed and validated seven machine learning models to predict CHD risk in HHcy patients.
- Key predictors identified include age, activated partial thromboplastin time, hypertension, weight, carotid plaque, and continuous drinking history.
- The LightGBM model performed best with high accuracy (AUC=0.807) and interpretability.
- SHAP analysis highlighted age and activated partial thromboplastin time as the most influential predictors.
- The study suggests machine learning can improve early risk assessment and personalized interventions for CHD in HHcy patients.