Emergency Medicine

Comprehensive Summary

This study evaluated whether the machine learning–based Myocardial Ischemic Injury Index (MI³), in combination with N-terminal pro–B-type natriuretic peptide (NT-proBNP) and galectin-3 (Gal-3), could differentiate Type 1 from Type 2 myocardial infarction (MI). This was a secondary analysis of the multicenter CMR-IMPACT trial, which prospectively enrolled adults presenting with acute coronary syndrome symptoms and initial indeterminate high-sensitivity troponin I (hs-cTnI) results. MI diagnosis and classification were adjudicated by expert reviewers. Among 123 patients with adjudicated MI, 72 (58.5%) had Type 1 MI (plaque rupture/acute coronary thrombosis) and 51 (41.5%) had Type 2 MI (supply–demand mismatch without plaque rupture). The combined model of MI³ with NT-proBNP and Gal-3 achieved the highest discrimination (AUC 0.789, 95% CI 0.709–0.869, p = 0.0165), outperforming MI³ or the individual biomarkers alone. Clinical differentiation of Type 1 and Type 2 MI remains challenging, yet is critical because treatment strategies differ substantially. While prior biomarker studies have shown inconsistent results, this analysis suggests that integrating biomarkers with machine learning may improve diagnostic accuracy.

Outcomes and Implications

Accurately distinguishing MI types in the emergency department could improve patient outcomes by guiding management in line with type-specific recommendations. The findings are clinically relevant given the persistent challenges clinicians face in differentiating MI types. Adding biomarker analysis increased diagnostic accuracy and may support more precise treatment decisions. This is the first study to evaluate a machine learning algorithm combined with biomarkers for MI type differentiation, demonstrating encouraging potential that warrants validation in larger cohorts.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team