Author + information
- Received December 1, 2019
- Accepted December 4, 2019
- Published online February 17, 2020.
- Wei-Yin Ko, MS, MEnga,∗,
- Konstantinos C. Siontis, MDa,∗,
- Zachi I. Attia, MSEEa,
- Rickey E. Carter, PhDb,
- Suraj Kapa, MDa,
- Steve R. Ommen, MDa,
- Steven J. Demuth, BAc,
- Michael J. Ackerman, MD, PhDa,
- Bernard J. Gersh, MB, ChB DPhila,
- Adelaide M. Arruda-Olson, MD, PhDa,
- Jeffrey B. Geske, MDa,
- Samuel J. Asirvatham, MDa,
- Francisco Lopez-Jimenez, MDa,
- Rick A. Nishimura, MDa,
- Paul A. Friedman, MDa and
- Peter A. Noseworthy, MDa,∗ (, )@noseworthypeter
- aDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
- bHealth Sciences Research, Mayo Clinic College of Medicine, Jacksonville, Florida
- cInformation Technology, Mayo Clinic, Rochester, Minnesota
- ↵∗Address for correspondence:
Dr. Peter A. Noseworthy, Department of Cardiovascular Medicine, Mayo Clinic, 200 First Street SW, Rochester, Minnesota 55905.
Background Hypertrophic cardiomyopathy (HCM) is an uncommon but important cause of sudden cardiac death.
Objectives This study sought to develop an artificial intelligence approach for the detection of HCM based on 12-lead electrocardiography (ECG).
Methods A convolutional neural network (CNN) was trained and validated using digital 12-lead ECG from 2,448 patients with a verified HCM diagnosis and 51,153 non-HCM age- and sex-matched control subjects. The ability of the CNN to detect HCM was then tested on a different dataset of 612 HCM and 12,788 control subjects.
Results In the combined datasets, mean age was 54.8 ± 15.9 years for the HCM group and 57.5 ± 15.5 years for the control group. After training and validation, the area under the curve (AUC) of the CNN in the validation dataset was 0.95 (95% confidence interval [CI]: 0.94 to 0.97) at the optimal probability threshold of 11% for having HCM. When applying this probability threshold to the testing dataset, the CNN’s AUC was 0.96 (95% CI: 0.95 to 0.96) with sensitivity 87% and specificity 90%. In subgroup analyses, the AUC was 0.95 (95% CI: 0.94 to 0.97) among patients with left ventricular hypertrophy by ECG criteria and 0.95 (95% CI: 0.90 to 1.00) among patients with a normal ECG. The model performed particularly well in younger patients (sensitivity 95%, specificity 92%). In patients with HCM with and without sarcomeric mutations, the model-derived median probabilities for having HCM were 97% and 96%, respectively.
Conclusions ECG-based detection of HCM by an artificial intelligence algorithm can be achieved with high diagnostic performance, particularly in younger patients. This model requires further refinement and external validation, but it may hold promise for HCM screening.
↵∗ W-Y Ko and Dr. Siontis are joint first authors and contributed equally to this work.
Mr. Attia has equity in Eko, Inc.; and has served as an advisor to AliveCor. Dr. Kapa owns equity in Eko, Inc.; has served on the advisory boards of Myant, Inc. and Boston Scientific; and has received research grants form Abbott, Inc. and Toray, Inc. The funding source (The Louis V. Gerstner, Jr. Fund at Vanguard Charitable) had no role in the design study of the study, the collection, analysis, or interpretation of data, in the writing of the report or in the decision to submit the paper for publication. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
- Received December 1, 2019.
- Accepted December 4, 2019.
- 2020 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.