John R Giudicessi1, Matthew Schram2, J Martijn Bos3, Conner D Galloway2, Jacqueline B Shreibati2, Patrick W Johnson4, Rickey E Carter4, Levi W Disrud5, Robert Kleiman6, Zachi I Attia5, Peter A Noseworthy5, Paul A Friedman5, David E Albert2, Michael J Ackerman5,3,7. 1. Clinician-Investigator Training Program (J.R.G.), Mayo Clinic, Rochester, MN. 2. AliveCor Inc., Mountain View, CA. (M.S., C.D.G., J.B.S., D.E.A.). 3. Department of Cardiovascular Medicine; Windland Smith Rice Sudden Death Genomics Laboratory, Department of Molecular Pharmacology and Experimental Therapeutics (J.M.B., M.J.A.), Mayo Clinic, Rochester, MN. 4. Department of Health Sciences Research (Biomedical Statistics and Informatics), Mayo Clinic, Jacksonville, FL (P.W.J., R.E.C.). 5. Division of Heart Rhythm Services, Windland Smith Rice Genetic Heart Rhythm Clinic (L.W.D., Z.I.A., P.A.N., P.A.F., M.J.A.), Mayo Clinic, Rochester, MN. 6. eResearch Technology Inc, Philadelphia, PA (R.K.). 7. Division of Pediatric Cardiology, Department of Pediatric and Adolescent Medicine (M.J.A.), Mayo Clinic, Rochester, MN.
Abstract
BACKGROUND: Heart rate-corrected QT interval (QTc) prolongation, whether secondary to drugs, genetics including congenital long QT syndrome, and/or systemic diseases including SARS-CoV-2-mediated coronavirus disease 2019 (COVID-19), can predispose to ventricular arrhythmias and sudden cardiac death. Currently, QTc assessment and monitoring relies largely on 12-lead electrocardiography. As such, we sought to train and validate an artificial intelligence (AI)-enabled 12-lead ECG algorithm to determine the QTc, and then prospectively test this algorithm on tracings acquired from a mobile ECG (mECG) device in a population enriched for repolarization abnormalities. METHODS: Using >1.6 million 12-lead ECGs from 538 200 patients, a deep neural network (DNN) was derived (patients for training, n = 250 767; patients for testing, n = 107 920) and validated (n = 179 513 patients) to predict the QTc using cardiologist-overread QTc values as the "gold standard". The ability of this DNN to detect clinically-relevant QTc prolongation (eg, QTc ≥500 ms) was then tested prospectively on 686 patients with genetic heart disease (50% with long QT syndrome) with QTc values obtained from both a 12-lead ECG and a prototype mECG device equivalent to the commercially-available AliveCor KardiaMobile 6L. RESULTS: In the validation sample, strong agreement was observed between human over-read and DNN-predicted QTc values (-1.76±23.14 ms). Similarly, within the prospective, genetic heart disease-enriched dataset, the difference between DNN-predicted QTc values derived from mECG tracings and those annotated from 12-lead ECGs by a QT expert (-0.45±24.73 ms) and a commercial core ECG laboratory [10.52±25.64 ms] was nominal. When applied to mECG tracings, the DNN's ability to detect a QTc value ≥500 ms yielded an area under the curve, sensitivity, and specificity of 0.97, 80.0%, and 94.4%, respectively. CONCLUSIONS: Using smartphone-enabled electrodes, an AI DNN can predict accurately the QTc of a standard 12-lead ECG. QTc estimation from an AI-enabled mECG device may provide a cost-effective means of screening for both acquired and congenital long QT syndrome in a variety of clinical settings where standard 12-lead electrocardiography is not accessible or cost-effective.
BACKGROUND: Heart rate-corrected QT interval (QTc) prolongation, whether secondary to drugs, genetics including congenital long QT syndrome, and/or systemic diseases including SARS-CoV-2-mediated coronavirus disease 2019 (COVID-19), can predispose to ventricular arrhythmias and sudden cardiac death. Currently, QTc assessment and monitoring relies largely on 12-lead electrocardiography. As such, we sought to train and validate an artificial intelligence (AI)-enabled 12-lead ECG algorithm to determine the QTc, and then prospectively test this algorithm on tracings acquired from a mobile ECG (mECG) device in a population enriched for repolarization abnormalities. METHODS: Using >1.6 million 12-lead ECGs from 538 200 patients, a deep neural network (DNN) was derived (patients for training, n = 250 767; patients for testing, n = 107 920) and validated (n = 179 513 patients) to predict the QTc using cardiologist-overread QTc values as the "gold standard". The ability of this DNN to detect clinically-relevant QTc prolongation (eg, QTc ≥500 ms) was then tested prospectively on 686 patients with genetic heart disease (50% with long QT syndrome) with QTc values obtained from both a 12-lead ECG and a prototype mECG device equivalent to the commercially-available AliveCor KardiaMobile 6L. RESULTS: In the validation sample, strong agreement was observed between human over-read and DNN-predicted QTc values (-1.76±23.14 ms). Similarly, within the prospective, genetic heart disease-enriched dataset, the difference between DNN-predicted QTc values derived from mECG tracings and those annotated from 12-lead ECGs by a QT expert (-0.45±24.73 ms) and a commercial core ECG laboratory [10.52±25.64 ms] was nominal. When applied to mECG tracings, the DNN's ability to detect a QTc value ≥500 ms yielded an area under the curve, sensitivity, and specificity of 0.97, 80.0%, and 94.4%, respectively. CONCLUSIONS: Using smartphone-enabled electrodes, an AI DNN can predict accurately the QTc of a standard 12-lead ECG. QTc estimation from an AI-enabled mECG device may provide a cost-effective means of screening for both acquired and congenital long QT syndrome in a variety of clinical settings where standard 12-lead electrocardiography is not accessible or cost-effective.
Entities:
Keywords:
artificial intelligence; electrocardiography; long QT syndrome; machine learning
Authors: Diego Mannhart; Elisa Hennings; Mirko Lischer; Claudius Vernier; Jeanne Du Fay de Lavallaz; Sven Knecht; Beat Schaer; Stefan Osswald; Michael Kühne; Christian Sticherling; Patrick Badertscher Journal: Front Cardiovasc Med Date: 2022-06-23
Authors: Jacob J Mayfield; Neal A Chatterjee; Peter A Noseworthy; Jeanne E Poole; Michael J Ackerman; Jenell Stewart; Patricia J Kissinger; John Dwyer; Sybil Hosek; Temitope Oyedele; Michael K Paasche-Orlow; Kristopher Paolino; Paul A Friedman; Chloe Waters; Jessica Moreno; Hannah Leingang; Kate B Heller; Susan A Morrison; Meighan L Krows; Ruanne V Barnabas; Jared Baeten; Christine Johnston; Arun R Sridhar Journal: Commun Med (Lond) Date: 2021-12-20
Authors: Demilade A Adedinsewo; Amy W Pollak; Sabrina D Phillips; Taryn L Smith; Anna Svatikova; Sharonne N Hayes; Sharon L Mulvagh; Colleen Norris; Veronique L Roger; Peter A Noseworthy; Xiaoxi Yao; Rickey E Carter Journal: Circ Res Date: 2022-02-17 Impact factor: 23.213
Authors: Elaine Y Wan; Hamid Ghanbari; Nazem Akoum; Zachi Itzhak Attia; Samuel J Asirvatham; Eugene H Chung; Lilas Dagher; Sana M Al-Khatib; G Stuart Mendenhall; David D McManus; Rajeev K Pathak; Rod S Passman; Nicholas S Peters; David S Schwartzman; Emma Svennberg; Khaldoun G Tarakji; Mintu P Turakhia; Anthony Trela; Hirad Yarmohammadi; Nassir F Marrouche Journal: Cardiovasc Digit Health J Date: 2021-07-10
Authors: Georgios Petmezas; Leandros Stefanopoulos; Vassilis Kilintzis; Andreas Tzavelis; John A Rogers; Aggelos K Katsaggelos; Nicos Maglaveras Journal: JMIR Med Inform Date: 2022-08-15
Authors: John Stacy; Rachel Kim; Christopher Barrett; Balaviknesh Sekar; Steven Simon; Farnoush Banaei-Kashani; Michael A Rosenberg Journal: JMIR Form Res Date: 2022-08-11
Authors: Sara Chokshi; Gulzhan Tologonova; Rose Calixte; Vandana Yadav; Naveed Razvi; Jason Lazar; Stan Kachnowski Journal: JMIR Form Res Date: 2022-09-28