Objective:

To develop predictive models for 28-day in-hospital all-cause mortality risk in patients with acute myocardial infarction complicated by chronic obstructive pulmonary disease using machine learning algorithms.

Approach:

• Data Extraction: Retrospective data extraction from the MIMIC-IV database to identify ICU patients with AMI and COPD.
• Model Development: Five machine learning models (XGBoost, logistic regression, GBDT, LightGBM, AdaBoost) were developed and compared.
• Model Evaluation: Model discrimination assessed using AUC, calibration evaluated with calibration curves, and clinical utility examined using decision curve analysis.
• Interpretability: SHAP analysis was used to provide interpretable visualization of model predictions.

Key Findings:

• A total of 662 ICU patients with acute myocardial infarction and chronic obstructive pulmonary disease were included, of whom 185 (27.9%) died within 28 days of hospital admission.
• The logistic regression model demonstrated superior discriminative performance, with an AUC of 0.782 in the validation cohort.
• The AUCs of the other models were 0.739 for XGBoost, 0.761 for LightGBM, 0.767 for GBDT, and 0.764 for AdaBoost.
• Eight variables were ultimately selected to build the prediction model, including age, heart rate, respiratory rate, lactate dehydrogenase, blood urea nitrogen, sepsis, β-blocker use, and angiotensin-converting enzyme inhibitors/angiotensin receptor blockers.

Interpretation:

The logistic regression model developed may assist clinicians in identifying high-risk patients early, facilitating informed treatment decisions.

Limitations:

• The study is retrospective and relies on data from a single database.
• Findings may not be generalizable to other populations or settings.

Conclusion:

Using the logistic regression model, we developed a predictive model for 28-day in-hospital all-cause mortality in ICU patients with AMI and COPD.