Health AI Central
Share:
Peer-Reviewed Publication
Circ Arrhythm Electrophysiol2025;18(9):e013695.September 1, 2025Journal Article

Deep Learning Can Unmask Conduction Tissue Disease From an Ambulatory ECG.

Laurent Fiorina1,2, Tanner Carbonati3, Baptiste Maille4,5, Kumar Narayanan2,6,7, Pauline Porquet3, Christine Henry3, Jagmeet P Singh8, Eloi Marijon2,6,9, Jean-Claude Deharo4,5
1Ramsay Santé, Institut Cardiovasculaire Paris Sud, Hôpital privé Jacques Cartier, Massy, France (L.F.).
2Paris Cardiovascular Research Center, Santé et de la Recherche Médicale U970, Université Paris Cité, France (L.F., K.N., E.M.).
3Department of Cardiology, Cardiologs, Paris, France (T.C., P.P., C.H.).
4Department of Cardiology, Assistance Publique-Hôpitaux de Marseille, Centre Hospitalier Universitaire La Timone, Service de Cardiologie, France (B.M., J.-C.D.).
5C2VN, Aix Marseille University, France (B.M., J.-C.D.).
6Department of Cardiology, Paris-Sudden Death Expertise Center, France (K.N., E.M.).
7Cardiology Department, Medicover Hospitals, Hyderabad, India (K.N.).
8Department of Cardioilogy, Massachusetts General Hospital, Harvard Medical School, Boston (J.P.S.).
9Division of Cardiology, European Georges Pompidou Hospital, Paris, France (E.M.).
PubMed DOI

Abstract

BACKGROUND: Bradyarrhythmia is a common and potentially serious cause of syncope, often difficult to detect due to its intermittent nature. Traditional ECG monitoring methods either provide low diagnostic accuracy or delay diagnosis, increasing the risk of recurrence. We hypothesized that a deep learning-enabled, 24-hour, single-lead ECG could detect past episodes of bradyarrhythmia. METHODS: Usi…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.