Abstract
BACKGROUND: High-risk chest pain is a critical presentation in emergency departments, frequently indicative of life-threatening cardiopulmonary conditions. Rapid and accurate diagnosis is pivotal for improving patient survival rates. METHODS: We developed a machine learning prediction model using the MIMIC-IV database (n = 14,716 patients, including 1,302 high-risk cases). To address class imbalance, we implemented feature engineering with SMOTE and under-sampling techniques. Model optimization was performed via Bayesian hyperparameter tuning. Seven algorithms were evaluated: Logistic Regression, Random Forest, SVM, XGBoost, LightGBM, TabTransformer, and TabNet. RESULTS: The LightGBM model demonstrated superior performance with accuracy = 0.95, precision = 0.95, recall = 0.95, and F1-score = 0.94. SHAP analysis revealed maximum troponin and creatine kinase-MB levels as the top predictive features. CONCLUSION: Our optimized LightGBM model provides clinically significant predictive capability for high-risk chest pain, offering emergency physicians a decision-support tool to enhance diagnostic accuracy and patient outcomes.