A LightGBM-Based Predictive Model for Coronary Heart Disease: Integrating Machine Learning and Interpretability for Enhanced Clinical Decision-Making (Preprint)

<sec> <title>BACKGROUND</title> Coronary Heart Disease (CHD) is one of the major burdens of cardiovascular diseases worldwide. Traditional diagnostic methods, such as coronary angiography and electrocardiogram, face challenges including high costs, subjectivity, and high misdiagnosis rates. Objective: To address these issues, this study proposes a prediction framework for CHD based on the LightGBM algorithm, aiming to improve the accuracy and interpretability of CHD risk prediction. Methods: This study utilized three publicly available datasets: BRFSS_2015, Framingham, and Z-Alizadeh Sani. The BRFSS_2015 dataset was used for model training, while the Framingham and Z-Alizadeh Sani datasets were employed for validation. Data preprocessing included cleaning, feature engineering, and handling missing values. The LightGBM model was selected for its efficiency and performance, and SHAP (SHapley Additive exPlanations) values were used to enhance model interpretability. Model performance was evaluated using metrics such as accuracy, precision, recall, F1-score, and AUROC. A CHD scoring system was developed based on the model's predictions to assist clinicians in risk assessment. Results: The LightGBM model demonstrated excellent performance, achieving an accuracy of 90.60% and an AUROC of 81.06% on the BRFSS_2015 dataset. After parameter tuning, the model's accuracy improved to 90.61%, and the AUROC increased to 81.11%. On the Framingham dataset, the accuracy improved from 83.96% to 85.26%, and the AUROC increased from 62.86% to 67.37%. On the Z-Alizadeh Sani dataset, the accuracy improved from 78.69% to 80.33%, and the precision increased from 74.40% to 76.36%. SHAP analysis revealed that age, smoking status, diabetes, hypertension, and high cholesterol were the most influential features in predicting CHD risk. Conclusions: The developed CHD scoring system provided a user-friendly tool for clinicians to assess patient risk levels effectively. </sec> <sec> <title>OBJECTIVE</title> This study aims to develop a predictive model for Coronary Heart Disease (CHD) using LightGBM, integrating machine learning techniques with feature interpretability. The objective is to enhance clinical decision-making by providing an accurate, cost-effective, and interpretable risk assessment tool. </sec> <sec> <title>METHODS</title> A retrospective dataset of CHD patients was collected, including demographic, clinical, and laboratory features. Feature selection was performed using SHAP (Shapley Additive Explanations) to improve model interpretability. The LightGBM model was trained and validated using cross-validation, and its performance was compared with traditional machine learning models, such as logistic regression and random forests. Key evaluation metrics included accuracy, precision, recall, F1-score, and AUC-ROC. </sec> <sec> <title>RESULTS</title> The LightGBM model achieved superior predictive performance compared to baseline models, with an AUC-ROC of X.XX. Feature importance analysis revealed that risk factors such as age, cholesterol levels, and blood pressure had the highest predictive power. The model demonstrated high clinical applicability, offering real-time predictions with interpretability insights for decision support. </sec> <sec> <title>CONCLUSIONS</title> The proposed LightGBM-based model provides an effective tool for CHD risk prediction, balancing high predictive performance with interpretability. The integration of SHAP enhances the model’s transparency, making it more suitable for clinical adoption. Future research should focus on external validation and real-world deployment. </sec>