Establishment and validation of a machine learning-based predictive model for in-hospital mortality risk in acute myocardial infarction patients complicated with diabetes mellitus

1

A machine learning predictive model was developed to assess in-hospital mortality risk in acute myocardial infarction patients with diabetes mellitus complications.
2

The study identified seven key predictors, including heart rate and neutrophil count, using LASSO regression and the Boruta algorithm.
3

The XGBoost-based model demonstrated the highest AUC during performance evaluation and was selected as the preferred predictive model.
4

The SHAP method was utilized to enhance the interpretability of the model, providing insights into feature contributions to mortality risk.
5

This model serves as an auxiliary risk stratification tool for identifying high-risk patients in clinical settings similar to the study cohorts.

Frontiers In Cardiovascular Medicine

by Lang Zeng, Yangchun Li, Fenglin Wu, Shikang Li, Chenshi Rao, Yao Zhang, Yonghong Zhang, Xuefeng Ding, Houxiang Hu, Rongchuan Yue
June 1, 2026

1