Diagnostic performance of the Myocardial-Ischaemic-Injury index machine-learning algorithm in patients with an initial indeterminate troponin

Sep 30, 2026

Uploaded by OmBimo

Background: Ruling out myocardial infarction (MI) after an initial indeterminate (detectable to mildly elevated) troponin is challenging. Myocardial-Ischaemic-Injury Index (MI3) is a machine-learning tool for MI diagnosis, but its performance in this troponin range remains unclear. Methods: Secondary analysis of a multi-hospital cohort classified patients by MI3 using initial and 3-hour high-sensitivity troponin I. Results: MI3 achieved an AUC of 0.882 and showed high specificity and strong negative likelihood ratio for 30-day MI. Conclusion: In emergency patients with initial indeterminate troponin, MI3 demonstrates high diagnostic accuracy for 30-day MI, with limited sensitivity to exclude MI.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusions

What is already known on this topic

What this study adds

How this study might affect research, practice or policy

Open access Coronary artery disease ► Additional supplemental material is published online only. To view, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[openhrt-2025-003767](openhrt-2025-003767)) . To cite: Snavely AC, Hunter CJ, Jackson L, et al. Diagnostic performance of the MyocardialIschaemic-Injury index machine-learning algorithm inpatients with an initial indeterminate troponin. Open Heart 2026;13:e003767 . doi:10.1136/ openhrt-2025-003767 Received 8 October 2025 Accepted 15 December 2025 © Author(s) (or their employer(s)) 2026. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ Group. 1Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA 2Core Diagnostic, Abbott, Lake Forest, Illinois, USA 3Abbott, Chicago, Illinois, USA 4Department of Emergency Medicine, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA 5Rapid Response Lab, University of Maryland Medical System, Baltimore, Maryland, USA Correspondence to Dr Simon A Mahler; smahler@ [wakehealth.edu](wakehealth.edu) Diagnostic performance of the Myocardial-Ischaemic-Injury index machine-learning algorithm in patients with an initial indeterminate troponin Anna C Snavely,1 Christian J Hunter,2 Laurel Jackson,3 Jason P Stopyra,4 Nicklaus P Ashburn,4 Michael W Supples,4 Robert Christenson,5 Chadwick D Miller,4 Simon A Mahler 4 ABSTRACT Background Ruling out myocardial infarction (MI) in patients with an initial indeterminate (detectable to mildly elevated) troponin measure is challenging. Myocardial-IschaemicInjury Index (MI3) is a machine-learning algorithm designed to diagnose MI, but its utility in patients with indeterminate troponins is unclear. This study seeks to evaluate its diagnostic performance in patients with an initial indeterminate troponin. Methods We conducted a secondary analysis of a cohort (Cardiovascular Magnetic Resonance-Invasive-based Strategies in Patients with Chest Pain and Detectable to Mildly Elevated Serum Troponin) of adult patients with symptoms suggestive of acute coronary syndrome and an initial clinical contemporary troponin of 0.006–1.0ng/mL across four US hospitals. Patients with initial and 3-hour high-sensitivity cardiac troponin I (Abbott Laboratories) measures were classified by MI3 into low-risk, intermediate-risk and high-risk groups. The primary outcome was adjudicated MI at 30 days. The sensitivity, specificity and negative likelihood ratio (−LR) of MI3 for MI at 30 days were calculated and reported with 95% CIs. A receiver operator characteristics curve for MI at 30 days was created and area under the curve (AUC) for MI3 was calculated. Results Among 207 patients, 34.3%(71/207) were female with a mean age of 61±11 years. MI at 30 days occurred in 43.5%(90/207). TheAUC for MI3 for the detection of MI at 30 days was 0.882 (95% CI 0.833 to 0.932). MI3 classified 34.8%(72/207) of patients as low-risk, of which 8.3%(6/72) had MI at 30 days, yielding a sensitivity of 93.3%(95% CI 86.1 to 97.5%) and −LR of 0.12 (95% CI 0.05 to 0.26). Among the 47.3%(98/207) classified as intermediate-risk, MI at 30 days occurred in 48.0%(47/98). MI3 classified 17.9%(37/207) as high-risk, among which 100%(37/37) had MI at 30 days, yielding a specificity of 100%(95% CI 96.9% to 100%). Conclusions Among emergency department patients with an initial indeterminate troponin measure, the MI3 machinelearning algorithm had high AUC and specificity for 30-day MI. INTRODUCTION Each year, approximately 7–9 million patients with symptoms of possible acute coronary syndrome (ACS) present to US emergency departments (EDs) .1 For the initial evaluation WHAT IS ALREADY KNOWN ON THIS TOPIC | ⇒ The evaluation of patients with an indeterminate troponin measure is challenging and it is unclear whether machine-learning algorithms, like

FAQs

What clinical problem does the study address?

The study addresses difficulty ruling out myocardial infarction when patients have an initial indeterminate troponin level (detectable to mildly elevated).

How was MI3 evaluated in this research?

Researchers conducted a secondary analysis, classifying patients into low-, intermediate-, and high-risk groups using MI3 based on initial and 3-hour high-sensitivity troponin I measurements. The primary outcome was adjudicated MI at 30 days.

What were the main diagnostic performance findings for MI3?

MI3 showed strong discrimination for 30-day MI with an AUC of 0.882. It also demonstrated high specificity, including perfect classification of the high-risk group for 30-day MI.

Sep 30, 2026

Uploaded by OmBimo