Cardiac arrest & resuscitation

Artificial Intelligence-Assisted, Electrocardiogram-Derived, Sequential Rule-Based Decision Tree for Exclusion of Acute Coronary Syndrome as the Etiology of Out-of-Hospital Cardiac Arrest: A Single-Center Retrospective Cohort Study

ResuscitationPublished single-center retrospective study

Authors' conclusion

A rhythm-stratified, rule-based decision tree combining AI-assisted ECG-derived biomarkers classified approximately half of post-OHCA patients as "ACS not likely" with no adjudicated ACS case misclassified, principally in the non-shockable subgroup. This transparent, bedside-deployable framework warrants prospective multicenter evaluation.

Study context

Population
Adult patients with out-of-hospital cardiac arrest (OHCA) with post-ROSC 12-lead electrocardiogram (ECGs)329 (Development, 2020-2024) · 71 (Temporal validation, 2025)
Index test or model
Rhythm-stratified sequential decision tree compared with individual biomarkers
Target condition
acute coronary syndrome (ACS) as the arrest etiology
Methodological detailstemporal validation
  • Temporal validation

Performance

As reported in the abstract

Acute coronary syndrome (ACS) as the arrest etiology

Further findings

Exclusion of non-ACS cases, non-shockable subgroup

Non-ACS cases excluded by the model
169/261 (64.8%)
AUROC
0.824
Outperforming each individual biomarker

Retained as "acute coronary syndrome (ACS) not excluded", shockable subgroup

Patients retained as "ACS not excluded"
38/40 patients (95.0%)
  • Subgroup carries a high pretest probability of ACS

Original publication

Artificial Intelligence-Assisted, Electrocardiogram-Derived, Sequential Rule-Based Decision Tree for Exclusion of Acute Coronary Syndrome as the Etiology of Out-of-Hospital Cardiac Arrest: A Single-Center Retrospective Cohort Study. Resuscitation. Published 29 October 2026. doi:10.1016/j.resuscitation.2026.111373

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.