A machine learning model for predicting short-term in-hospital mortality in acute myocardial infarction with coexisting chronic obstructive pulmonary disease - Report - MDSpire
Advertisement
A machine learning model for predicting short-term in-hospital mortality in acute myocardial infarction with coexisting chronic obstructive pulmonary disease
Clinical Report: Predictive Machine Learning for In-Hospital Mortality in AMI and COPD
Overview
This study developed a machine learning framework to predict 28-day in-hospital mortality in ICU patients with acute myocardial infarction (AMI) and chronic obstructive pulmonary disease (COPD). The logistic regression model achieved an AUC of 0.782.
Background
Acute myocardial infarction is a leading cause of mortality, and its prognosis is significantly worsened by comorbidities such as chronic obstructive pulmonary disease. Accurate risk stratification is essential for guiding clinical decisions in this high-risk population. However, validated predictive models for this specific patient group remain limited.
Data Highlights
Model
AUC
Logistic Regression
0.782
XGBoost
0.739
LightGBM
0.761
GBDT
0.767
AdaBoost
0.764
Key Findings
185 out of 662 patients (27.9%) died within 28 days of hospital admission.
The logistic regression model showed an AUC of 0.782.
Key predictors included age, heart rate, respiratory rate, lactate dehydrogenase, blood urea nitrogen, sepsis, β-blocker use, and ACEI/ARB use.
SHAP analysis was utilized to enhance model interpretability.
The model demonstrated good calibration.
Clinical Implications
The logistic regression model can assist clinicians in identifying high-risk patients with AMI and COPD early in their hospital stay. This may facilitate more informed treatment decisions and better resource allocation.
Conclusion
The developed predictive model for in-hospital mortality in patients with AMI and COPD may enhance clinical decision-making and improve patient management in the ICU setting.
