Key result
XGBoost best predicts in-hospital adverse events after AMI with an AUROC of ~0.80.
Why the study?
In-hospital adverse events after AMI can occur abruptly and adversely affect short-term prognosis, motivating the development of explainable machine learning models using routinely available admission data to predict in-hospital AF, VF, CA, or death.
Can explainable machine learning models using routinely available admission clinical and laboratory data accurately predict a composite of in-hospital atrial fibrillation, ventricular fibrillation, cardiac arrest, or death in patients hospitalized with acute myocardial infarction?
Cohort (n=10,272)
Yes
Can explainable machine learning models using routinely available admission clinical and laboratory data accurately predict a composite of in-hospital atrial fibrillation, ventricular fibrillation, cardiac arrest, or death in patients hospitalized with acute myocardial infarction?
Explainable machine learning models using routine admission laboratory and clinical data can moderately to accurately stratify the risk of in-hospital adverse events—especially atrial fibrillation and mortality—in patients hospitalized with acute myocardial infarction.
Answers are grounded in this paper and cite their sources.
May support admission-based risk stratification after AMI; leaves open prospective validation before clinical adoption.
In-hospital adverse events after acute myocardial infarction (AMI) can occur abruptly and adversely affect short-term prognosis. We developed and externally validated explainable machine learning models to predict a composite of in-hospital atrial fibrillation (AF), ventricular fibrillation (VF), cardiac arrest (CA), or death using routinely available admission data. We retrospectively analyzed 7,496 patients from the MIMIC-IV database as the development cohort and 2,776 patients from Xuanwu Hospital as the external validation cohort. Predictors included demographics, medical history, and admission laboratory tests. Logistic regression, random forest, extreme gradient boosting (XGBoost), multilayer perceptron, and TabNet models were evaluated using five-fold cross-validation. Performance was assessed using discrimination, classification, calibration, and decision curve analysis. Latent class analysis identified three outcome clusters with distinct event-probability profiles. XGBoost achieved the best performance for the composite outcome in the development cohort (AUROC, 0.798). Predictive performance was moderate to good for AF and in-hospital death, with AUROCs of up to 0.834 and 0.870 in the development cohort and 0.803 and 0.849 in the external validation cohort, respectively. Discrimination was lower for VF and CA. SHapley Additive exPlanations highlighted neutrophil and leukocyte counts, N-terminal pro-B-type natriuretic peptide, renal function, glucose, glycated hemoglobin A1c, and prior AF as important predictors. These explainable models may support early risk stratification and help guide monitoring intensity and timely intervention in patients with AMI.
No takes yet. Share an insight, caveat, or question.
Tian et al. (2026) conducted a cohort in Acute myocardial infarction (n=10,272). Explainable machine learning models (XGBoost, Random Forest, Multilayer Perceptron, TabNet, Logistic Regression) vs. Alternative machine learning and statistical models evaluated via 5-fold cross-validation and external validation was evaluated on Composite of in-hospital atrial fibrillation (AF), ventricular fibrillation (VF), cardiac arrest (CA), or in-hospital death (AUROC 0.798 (development, XGBoost); AUROC 0.765 (external validation, Logistic Regression), 95% CI 0.788-0.809). XGBoost achieved the highest discrimination for predicting the composite of in-hospital adverse events after acute myocardial infarction in the development cohort.
Synapse has enriched 10 related papers. Consider them for comparative context: