Acute cardiac care & resuscitationCase-control study
Clinical Triage of Individuals With Warning Symptoms of Imminent Cardiac Arrest
- case-control study
- 2 community-based studies of sudden cardiac arrest (SCA) in Oregon and California
- machine learning
- 5-fold cross-validation
Authors' conclusion
Combinations of warning symptoms and clinical features distinguished individuals with SCA from individuals without SCA with good accuracy (AUCs, 0.745-0.788). These findings have implications for clinical triage of ISCA warning symptoms in emergency settings and warrant investigation in larger studies.
Study context
- Population
- Individuals who called 911 with warning symptoms: survivors of SCA and control subjects who did not have SCAsurvivors of SCA who had experienced warning symptoms and called 911 364 · control subjects 313
- Participants
- 364 vs 313
- Comparison
- Combinations of warning symptoms and clinical features distinguishing individuals with SCA from individuals without SCA
- survivors of SCAn = 364
- control subjectsn = 313
Further findings
Prediction of imminent SCA (ISCA): chest pain combinations
- chest pain and known heart failure predicted ISCA among men, chest pain and known coronary artery disease among women (AUC)
- 0.788
Prediction of ISCA: dyspnea combinations
- With dyspnea, history of coronary artery disease and heart failure (AUC)
- 0.745
Prediction of ISCA in the absence of chest pain or dyspnea
- seizure-like symptoms, coronary artery disease, and heart failure (AUC)
- 0.775
Model stability
- 5-fold cross-validation produced consistent results
Original publication
Clinical Triage of Individuals With Warning Symptoms of Imminent Cardiac Arrest. Circ Arrhythm Electrophysiol. Published 8 July 2026. doi:10.1161/circep.125.014647
Summarised from the published abstract; every number is checked against it