Acute cardiac care & resuscitation
Artificial Intelligence Model Predicts Sudden Cardiac Arrest Manifesting With Pulseless Electric Activity Versus Ventricular Fibrillation
Authors' conclusion
The artificial intelligence model identified novel features of PEA-SCA, differentiated from VF-SCA and was successfully replicated in an external cohort.
Study context
- Population
- EMS-witnessed out-of-hospital sudden cardiac arrest with pulseless electric activity (PEA) or ventricular fibrillation (VF) as initial rhythm
- Participants
- 421 vs 220
- Comparison
- AI model to differentiate PEA-SCA vs VF-SCA
- Internaln = 421
- Externaln = 220
- Outcome
- Discrimination of PEA-SCA vs VF-SCA (AUC)
Methodological detailsexternal validation
- External validation
Performance
As reported in the abstract
AUC for PEA-SCA vs VF-SCA
| Test or model | AUC |
|---|---|
| Internal | 0.68 (95% CI, 0.61-0.76) |
| External | 0.72 (95% CI, 0.59-0.84) |
AUC
Internal0.68 (95% CI, 0.61-0.76)
External0.72 (95% CI, 0.59-0.84)
Further findings
Most important model features
- PEA-SCA: anemia, older age, increased weight, dyspnea as warning symptom
- VF-SCA: younger age, chest pain as warning symptom, established CAD
Original publication
Artificial Intelligence Model Predicts Sudden Cardiac Arrest Manifesting With Pulseless Electric Activity Versus Ventricular Fibrillation. Circ Arrhythm Electrophysiol. Published 29 January 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →