An Artificial Intelligence-enabled ECG Algorithm for Comprehensive ECG Interpretation: Can It Pass the 'Turing Test'?

Overview

Journal Cardiovasc Digit Health J

Specialty Cardiology & Vascular Diseases

Date 2022 Mar 10

PMID 35265905

Authors

Anthony H Kashou

Siva K Mulpuru

Abhishek J Deshmukh

Wei-Yin Ko

Zachi I Attia

Rickey E Carter

Paul A Friedman

Peter A Noseworthy

Affiliations

Soon will be listed here.

Abstract

Objective: To develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) algorithm capable of comprehensive, human-like ECG interpretation and compare its diagnostic performance against conventional ECG interpretation methods.

Methods: We developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, changes needed), (2) acceptable (ie, edits needed), or (3) unacceptable (ie, edits needed).

Results: Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively.

Conclusion: An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.

Citing Articles

Artificial Intelligence-Based Clinical Decision Support Systems in Cardiovascular Diseases.

Bozyel S, Simsek E, Burunkaya D, Guler A, Korkmaz Y, Seker M Anatol J Cardiol. 2024; .

PMID: 38168009 PMC: 10837676. DOI: 10.14744/AnatolJCardiol.2023.3685.

Impact of Computer-Interpreted ECGs on the Accuracy of Healthcare Professionals.

Kashou A, Noseworthy P, Beckman T, Anavekar N, Cullen M, Angstman K Curr Probl Cardiol. 2023; 48(11):101989.

PMID: 37482286 PMC: 10800643. DOI: 10.1016/j.cpcardiol.2023.101989.

Electrocardiogram to Determine Mitral and Aortic Valve Opening and Closure.

Aufan M, Jost Z, Miller N, Sharifov O, Gupta H, Perry G Cardiovasc Eng Technol. 2023; 14(3):447-456.

PMID: 36971975 DOI: 10.1007/s13239-023-00664-4.

Personalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6.

Shyam Kumar P, Ramasamy M, Kallur K, Rai P, Varadan V Sensors (Basel). 2023; 23(3).

PMID: 36772426 PMC: 9920327. DOI: 10.3390/s23031389.

Interpretable Machine Learning Techniques in ECG-Based Heart Disease Classification: A Systematic Review.

Ayano Y, Schwenker F, Dufera B, Debelee T Diagnostics (Basel). 2023; 13(1).

PMID: 36611403 PMC: 9818170. DOI: 10.3390/diagnostics13010111.

References

Poon K, Okin P, Kligfield P . Diagnostic performance of a computer-based ECG rhythm algorithm. J Electrocardiol. 2005; 38(3):235-8. DOI: 10.1016/j.jelectrocard.2005.01.008. View

Ribeiro A, Horta Ribeiro M, Paixao G, Oliveira D, Gomes P, Canazart J . Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun. 2020; 11(1):1760. PMC: 7145824. DOI: 10.1038/s41467-020-15432-4. View

Zhu H, Cheng C, Yin H, Li X, Zuo P, Ding J . Automatic multilabel electrocardiogram diagnosis of heart rhythm or conduction abnormalities with deep learning: a cohort study. Lancet Digit Health. 2020; 2(7):e348-e357. DOI: 10.1016/S2589-7500(20)30107-2. View

Kashou A, Ko W, Attia Z, Cohen M, Friedman P, Noseworthy P . A comprehensive artificial intelligence-enabled electrocardiogram interpretation program. Cardiovasc Digit Health J. 2022; 1(2):62-70. PMC: 8890098. DOI: 10.1016/j.cvdhj.2020.08.005. View

Martinez-Losas P, Higueras J, Gomez-Polo J, Brabyn P, Ferrer J, Canadas V . The influence of computerized interpretation of an electrocardiogram reading. Am J Emerg Med. 2016; 34(10):2031-2032. DOI: 10.1016/j.ajem.2016.07.029. View

Schlapfer J, Wellens H . Computer-Interpreted Electrocardiograms: Benefits and Limitations. J Am Coll Cardiol. 2017; 70(9):1183-1192. DOI: 10.1016/j.jacc.2017.07.723. View

Anh D, Krishnan S, Bogun F . Accuracy of electrocardiogram interpretation by cardiologists in the setting of incorrect computer analysis. J Electrocardiol. 2006; 39(3):343-5. DOI: 10.1016/j.jelectrocard.2006.02.002. View

Novotny T, Bond R, Andrsova I, Koc L, Sisakova M, Finlay D . The role of computerized diagnostic proposals in the interpretation of the 12-lead electrocardiogram by cardiology and non-cardiology fellows. Int J Med Inform. 2017; 101:85-92. DOI: 10.1016/j.ijmedinf.2017.02.007. View

Shah A, Rubin S . Errors in the computerized electrocardiogram interpretation of cardiac rhythm. J Electrocardiol. 2007; 40(5):385-90. DOI: 10.1016/j.jelectrocard.2007.03.008. View

10.

RIKLI A, TOLLES W, STEINBERG C, CARBERY W, FREIMAN A, Abraham S . Computer analysis of electrocardiographic measurements. Circulation. 1961; 24:643-9. DOI: 10.1161/01.cir.24.3.643. View

11.

Lindow T, Kron J, Thulesius H, Ljungstrom E, Pahlm O . Erroneous computer-based interpretations of atrial fibrillation and atrial flutter in a Swedish primary health care setting. Scand J Prim Health Care. 2019; 37(4):426-433. PMC: 6883419. DOI: 10.1080/02813432.2019.1684429. View

12.

Bogun F, Anh D, Kalahasty G, Wissner E, Bou Serhal C, Bazzi R . Misdiagnosis of atrial fibrillation and its clinical consequences. Am J Med. 2004; 117(9):636-42. DOI: 10.1016/j.amjmed.2004.06.024. View

13.

Guglin M, Thatai D . Common errors in computer electrocardiogram interpretation. Int J Cardiol. 2005; 106(2):232-7. DOI: 10.1016/j.ijcard.2005.02.007. View

14.

Hannun A, Rajpurkar P, Haghpanahi M, Tison G, Bourn C, Turakhia M . Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med. 2019; 25(1):65-69. PMC: 6784839. DOI: 10.1038/s41591-018-0268-3. View

15.

CACERES C, STEINBERG C, Abraham S, CARBERY W, McBride J, TOLLES W . Computer extraction of electrocardiographic parameters. Circulation. 1962; 25:356-62. DOI: 10.1161/01.cir.25.2.356. View