Cardiac arrest & resuscitation
Accuracy of remote, video-based supraventricular tachycardia detection in patients undergoing elective electrical cardioversion: a prospective cohort
Authors' conclusion
The machine learning model accurately identified sinus rhythm and arrhythmias using rPPG in real-world conditions.
Study context
- Population
- Patients undergoing elective electrical cardioversion (high prevalence of arrhythmias), before and after cardioversion72 screened
- Participants
- 51 patients
- Comparison
- rPPG-based machine learning model vs ECG reference
- Outcome
- Discrimination of sinus rhythm vs arrhythmias by rPPG-based machine learning model
Methodological detailsprospective, observational, leave-one-subject-out validation
- Prospective
- Observational
- Leave-one-subject-out validation
Performance
As reported in the abstract
Discrimination of sinus rhythm vs arrhythmias by the rPPG-based machine learning model
Model discrimination, AUC [CI]
0.95
0.93–0.96
Further findings
Pulse rate measurement, sinus rhythm (Bland-Altman)
- Bias [limits of agreement]
- 1.21 [- 8.60 to 11.02]
Pulse rate measurement, arrhythmia (Bland-Altman)
- Bias [limits of agreement]
- - 7.45 [- 35.75 to 20.86]
Original publication
Accuracy of remote, video-based supraventricular tachycardia detection in patients undergoing elective electrical cardioversion: a prospective cohort. J Clin Monit Comput. Published 29 January 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →