Related Experiment Videos
Integrating lipid-related composite indices and explainable machine learning for coronary heart disease risk
Yanchao Liu1, Xuli Chen1, Yuelin Hu1
1Department of Electrocardiology, The Second Affiliated Hospital of Wannan Medical University, Wuhu, China.
Insights
Lipid composite indices like TG/HDL, LDL/HDL, and AIP are strong indicators for coronary heart disease (CHD). These markers, when used with machine learning, improve individualized CHD risk classification.
Area of Science:
- Cardiovascular Medicine
- Biomarker Discovery
- Medical Diagnostics
Background:
- Composite indices combining inflammation and lipid metabolism are explored for coronary heart disease (CHD) risk assessment.
- The comparative performance of these indices in identifying CHD status requires further investigation.
Purpose of the Study:
- To evaluate the discriminative ability of various composite indices and C-reactive protein (CRP) for CHD.
- To develop and assess machine learning models for CHD classification using these markers.
Main Methods:
- A hospital-based study enrolled 270 patients (99 with CHD, 171 without).
- Evaluated composite indices (TG/HDL, LDL/HDL, AIP, CRP/HDL, CRP/TG) and CRP using logistic regression, restricted cubic splines, and subgroup analyses.
- Developed machine learning models (random forest, XGBoost) and interpreted using SHapley Additive exPlanations (SHAP).
Main Results:
- TG/HDL, LDL/HDL, and AIP were significantly associated with increased odds of CHD.
- C-reactive protein (CRP) and CRP-based indices did not show significant associations with CHD.
- Machine learning models, particularly ensemble tree-based methods, achieved good discrimination (AUC=0.748), with age and lipid indices being key predictors.
Conclusions:
- Lipid-related composite indices (TG/HDL, LDL/HDL, AIP) are reliable markers for CHD status.
- These indices can be effectively integrated into machine learning models for personalized CHD risk classification.
Background:
Composite indices integrating inflammation and lipid metabolism have emerged as promising markers for coronary heart disease (CHD), yet their comparative performance and discriminative ability for identifying CHD status remain incompletely understood.
Methods:
In this hospital-based study, 270 patients were enrolled, including 99 with CHD and 171 without CHD. Exposures included C-reactive protein (CRP) and composite indices (TG/HDL, LDL/HDL, AIP, CRP/HDL, and CRP/TG). Logistic regression, restricted cubic spline (RCS), and subgroup analyses were used to evaluate associations with CHD. Machine learning models were developed using significant predictors, and model performance was assessed by AUC, calibration, and decision curve analysis. SHapley Additive exPlanations (SHAP) were applied to interpret model outputs.
Results:
After multivariable adjustment, TG/HDL (OR = 2.74, 95% CI: 1.10-7.10), LDL/HDL (OR = 3.01, 95% CI: 1.21-7.81), and AIP (OR = 6.59, 95% CI: 1.61-28.51) were associated with increased odds of CHD, whereas CRP and CRP-based indices were not. RCS analyses indicated no significant nonlinearity, suggesting monotonic associations. Subgroup analyses showed generally consistent results across key strata. In classification modeling, ensemble tree-based methods performed best, with random forest and XGBoost achieving the highest discrimination ability (AUC = 0.748). SHAP analysis identified age and lipid-related composite indices as the primary contributors to CHD classification.
Conclusion:
Lipid-related composite indices, particularly TG/HDL, LDL/HDL, and AIP, are robust markers associated with CHD status and can be effectively integrated into machine learning models for individualized CHD classification.
Related Concept Videos
01:30Coronary Artery Disease I: Introduction
01:26Coronary Artery Disease IV: Preventive Measures
01:26Coronary Artery Disease II: Pathophysiology
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT