Acute cardiac care & 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
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 return of spontaneous circulation (ROSC)development and temporal validation cohorts · development (2020-2024) 329 · temporal validation (2025) 71
- Index test or model
- Its performance was compared with that of individual biomarkers and validated in the temporal cohort
- Target condition
- acute coronary syndrome (ACS) as the arrest etiology
Methodological detailsdevelopment and temporal validation cohorts, zero false-negative constraint, rhythm-stratified
- Development and temporal validation cohorts
- Zero false-negative constraint
- Rhythm-stratified
Performance
As reported in the abstract
Development cohort classified "acute coronary syndrome (ACS) not likely"
171 of 329
52.0%
Validation cohort classified "ACS not likely"
32 of 71
45.1%
Further findings
Non-ACS cases excluded, non-shockable subgroup
- Non-ACS cases excluded (of non-shockable non-ACS cases)
- 169/261 (64.8%)
- AUROC
- 0.824
- Outperforming each individual biomarker
Shockable subgroup retained as "ACS not excluded"
- Shockable patients retained as "ACS not excluded"
- 38/40 patients (95.0%)
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.
Composed by AI from the published abstract and checked against it. How Briefs are made →