Key result
AI model differentiates PEA from VF in out-of-hospital arrest with ~0.68 AUC.
Why the study?
Sudden cardiac arrest manifesting as PEA has low survival and lacks specific treatments, and developing therapies requires clinical studies hindered by limited access to the true initial rhythm.
Does an artificial intelligence model using clinical and demographic variables predict whether sudden cardiac arrest will manifest as pulseless electric activity versus ventricular fibrillation?
Cohort (n=641)
Yes
Does an artificial intelligence model using clinical and demographic variables predict whether sudden cardiac arrest will manifest as pulseless electric activity versus ventricular fibrillation?
Machine learning utilizing existing prearrest clinical data can predict the initial rhythm of sudden cardiac arrest, revealing novel mechanistic predictors like anemia and older age for PEA.
May support pre-arrest SCA phenotyping with routine data; hypothesis-generating and requires prospective validation before clinical use.
BACKGROUND: There is no specific treatment for sudden cardiac arrest (SCA) manifesting as pulseless electric activity (PEA) and survival rates are low; unlike ventricular fibrillation (VF), which is treatable by defibrillation. Development of novel treatments requires fundamental clinical studies, but access to the true initial rhythm has been a limiting factor. METHODS: Using demographics and detailed clinical variables, we trained and tested an AI model (extreme gradient boosting) to differentiate PEA-SCA versus VF-SCA in a novel setting that provided the true initial rhythm. A subgroup of SCAs are witnessed by emergency medical services personnel, and because the response time is zero, the true SCA initial rhythm is recorded. The internal cohort consisted of 421 emergency medical services-witnessed out-of-hospital SCAs with PEA or VF as the initial rhythm in the Portland, Oregon metropolitan area. External validation was performed in 220 emergency medical services-witnessed SCAs from Ventura, CA. RESULTS: In the internal cohort, the artificial intelligence model achieved an area under the receiver operating characteristic curve of 0.68 (95% CI, 0.61-0.76). Model performance was similar in the external cohort, achieving an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.59-0.84). Anemia, older age, increased weight, and dyspnea as a warning symptom were the most important features of PEA-SCA; younger age, chest pain as a warning symptom and established coronary artery disease were important features associated with VF. CONCLUSIONS: The artificial intelligence model identified novel features of PEA-SCA, differentiated from VF-SCA and was successfully replicated in an external cohort. These findings enhance the mechanistic understanding of PEA-SCA with potential implications for developing novel management strategies.
No takes yet. Share an insight, caveat, or question.
Holmström et al. (2024) conducted a cohort in Out-of-hospital sudden cardiac arrest (n=641). Artificial intelligence model (clinical and demographic variables) vs. Artificial intelligence model (demographics only) was evaluated on Differentiation of PEA-SCA versus VF-SCA initial rhythm (Area under the ROC curve) (AUC 0.68, 95% CI 0.61-0.76, p=<0.001). An artificial intelligence model incorporating clinical and demographic variables successfully differentiated pulseless electric activity from ventricular fibrillation in out-of-hospital sudden cardiac arrest, achieving an AUC of 0.68 compared to 0.52 for demographics alone.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: