Machine Learning-Based Prediction of Early Left Ventricular Function After STEMI

Background: Left ventricular (LV) function and lactate dynamics are major prognostic markers after ST-segment elevation myocardial infarction (STEMI). Early identification of patients at risk for impaired LV function or systemic hypoperfusion may improve outcomes. Machine learning (ML) can enhance predictive accuracy beyond traditional statistical methods, yet most prior studies were limited by small sample sizes and categorical outcomes. Methods: We retrospectively analyzed 2132 consecutive STEMI patients admitted to LMU Hospital (2014-2023). After preprocessing, 1608 patients with complete data were included. Thirty-eight demographic, clinical, procedural, and laboratory variables were used to train Decision Tree, Random Forest, and XGBoost regression models for predicting continuous left ventricular ejection fraction (LVEF) at discharge and lactate levels during hospitalization. Model performance was evaluated using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R²), and mean absolute percentage error (MAPE). Feature importance and Shapley additive explanations (SHAP) were applied for interpretability. Results: Ensemble models outperformed single trees. XGBoost achieved the best performance for LVEF prediction (MSE = 0.008, RMSE = 0.086, MAE = 0.068, R² = 0.35). Lactate prediction showed moderate accuracy (R² = 0.42 for admission and 0.47 for peak levels). Key predictors included cardiogenic shock, left anterior descending (LAD) culprit lesions, and peak lactate. Conclusions: ML enables individualized prediction of LV function and lactate dynamics after STEMI using routinely available clinical and laboratory data. Ensemble models, particularly XGBoost, demonstrated consistent and clinically meaningful predictive performance and generalizability, supporting their potential for early, data-driven risk stratification in acute cardiac care.