Improved Diagnosis of Arrhythmogenic Right Ventricular Cardiomyopathy Using Electrocardiographic Deep Learning

Overview

Journal Heart Rhythm

Publisher Elsevier

Specialty Cardiology & Vascular Diseases

Date 2024 Aug 21

PMID 39168295

Authors

Richard T Carrick

Eric D Carruth

Alessio Gasperetti

Brittney Murray

Crystal Tichnell

Sean Gaine

James Sampognaro

Steven A Muller

Babken Asatryan

Chris Haggerty

David Thiemann

Hugh Calkins

Cynthia A James

Katherine C Wu

Affiliations

Soon will be listed here.

Abstract

Background: Arrhythmogenic right ventricular cardiomyopathy (ARVC) is a rare genetic heart disease associated with life-threatening ventricular arrhythmias. Diagnosis of ARVC is based on the 2010 Task Force Criteria (TFC), application of which often requires clinical expertise at specialized centers.

Objective: The purpose of this study was to develop and validate an electrocardiogram (ECG) deep learning (DL) tool for ARVC diagnosis.

Methods: ECGs of patients referred for ARVC evaluation were used to develop (n = 551 [80.1%]) and test (n = 137 [19.9%]) an ECG-DL model for prediction of TFC-defined ARVC diagnosis. The ARVC ECG-DL model was externally validated in a cohort of patients with pathogenic or likely pathogenic (P/LP) ARVC gene variants identified through the Geisinger MyCode Community Health Initiative (N = 167).

Results: Of 688 patients evaluated at Johns Hopkins Hospital (JHH) (57.3% male, mean age 40.2 years), 329 (47.8%) were diagnosed with ARVC. Although ARVC diagnosis made by referring cardiologist ECG interpretation was unreliable (c-statistic 0.53; confidence interval [CI] 0.52-0.53), ECG-DL discrimination in the hold-out testing cohort was excellent (0.87; 0.86-0.89) and compared favorably to that of ECG interpretation by an ARVC expert (0.85; 0.84-0.86). In the Geisinger cohort, prevalence of ARVC was lower (n = 17 [10.2%]), but ECG-DL-based identification of ARVC phenotype remained reliable (0.80; 0.77-0.83). Discrimination was further increased when ECG-DL predictions were combined with non-ECG-derived TFC in the JHH testing (c-statistic 0.940; 95% CI 0.933-0.948) and Geisinger validation (0.897; 95% CI 0.883-0.912) cohorts.

Conclusion: ECG-DL augments diagnosis of ARVC to the level of an ARVC expert and can differentiate true ARVC diagnosis from phenotype-mimics and at-risk family members/genotype-positive individuals.

References

Liao S, Bokhari M, Chakraborty P, Suszko A, Jones G, Spears D . Use of Wearable Technology and Deep Learning to Improve the Diagnosis of Brugada Syndrome. JACC Clin Electrophysiol. 2022; 8(8):1010-1020. DOI: 10.1016/j.jacep.2022.05.003. View

Carrick R, Te Riele A, Gasperetti A, Bosman L, Muller S, Pendleton C . Longitudinal Prediction of Ventricular Arrhythmic Risk in Patients With Arrhythmogenic Right Ventricular Cardiomyopathy. Circ Arrhythm Electrophysiol. 2022; 15(11):e011207. PMC: 9669260. DOI: 10.1161/CIRCEP.122.011207. View

Lopes R, Bleijendaal H, Ramos L, Verstraelen T, Amin A, Wilde A . Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An application to phospholamban p.Arg14del mutation carriers. Comput Biol Med. 2021; 131:104262. DOI: 10.1016/j.compbiomed.2021.104262. View

Sampognaro J, Gaine S, Sharma A, Tichnell C, Murray B, Shaik Z . Diagnostic pitfalls in patients referred for arrhythmogenic right ventricular cardiomyopathy. Heart Rhythm. 2023; 20(12):1720-1726. DOI: 10.1016/j.hrthm.2023.08.035. View

Carrick R, De Marco C, Gasperetti A, Bosman L, Gourraud J, Trancuccio A . Implantable cardioverter defibrillator use in arrhythmogenic right ventricular cardiomyopathy in North America and Europe. Eur Heart J. 2024; 45(7):538-548. PMC: 11024811. DOI: 10.1093/eurheartj/ehad799. View

Moons K, Altman D, Reitsma J, Ioannidis J, Macaskill P, Steyerberg E . Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015; 162(1):W1-73. DOI: 10.7326/M14-0698. View

Haggerty C, Murray B, Tichnell C, Judge D, Tandri H, Schwartz M . Managing Secondary Genomic Findings Associated With Arrhythmogenic Right Ventricular Cardiomyopathy: Case Studies and Proposal for Clinical Surveillance. Circ Genom Precis Med. 2018; 11(7):e002237. DOI: 10.1161/CIRCGEN.118.002237. View

Ko W, Siontis K, Attia Z, Carter R, Kapa S, Ommen S . Detection of Hypertrophic Cardiomyopathy Using a Convolutional Neural Network-Enabled Electrocardiogram. J Am Coll Cardiol. 2020; 75(7):722-733. DOI: 10.1016/j.jacc.2019.12.030. View

Carey D, Fetterolf S, Davis F, Faucett W, Kirchner H, Mirshahi U . The Geisinger MyCode community health initiative: an electronic health record-linked biobank for precision medicine research. Genet Med. 2016; 18(9):906-13. PMC: 4981567. DOI: 10.1038/gim.2015.187. View

10.

Carruth E, Young W, Beer D, James C, Calkins H, Jing L . Prevalence and Electronic Health Record-Based Phenotype of Loss-of-Function Genetic Variants in Arrhythmogenic Right Ventricular Cardiomyopathy-Associated Genes. Circ Genom Precis Med. 2019; 12(11):e002579. PMC: 6876858. DOI: 10.1161/CIRCGEN.119.002579. View

11.

Stokke M, Castrini A, Astrom Aneq M, Jensen H, Madsen T, Hansen J . Absence of ECG Task Force Criteria does not rule out structural changes in genotype positive ARVC patients. Int J Cardiol. 2020; 317:152-158. DOI: 10.1016/j.ijcard.2020.05.095. View

12.

Bosman L, Cadrin-Tourigny J, Bourfiss M, Ghasabeh M, Sharma A, Tichnell C . Diagnosing arrhythmogenic right ventricular cardiomyopathy by 2010 Task Force Criteria: clinical performance and simplified practical implementation. Europace. 2020; 22(5):787-796. PMC: 7203633. DOI: 10.1093/europace/euaa039. View

13.

Carruth E, Beer D, Alsaid A, Schwartz M, McMinn M, Kelly M . Clinical Findings and Diagnostic Yield of Arrhythmogenic Cardiomyopathy Through Genomic Screening of Pathogenic or Likely Pathogenic Desmosome Gene Variants. Circ Genom Precis Med. 2021; 14(2):e003302. PMC: 8284375. DOI: 10.1161/CIRCGEN.120.003302. View

14.

Philips B, Madhavan S, James C, Te Riele A, Murray B, Tichnell C . Arrhythmogenic right ventricular dysplasia/cardiomyopathy and cardiac sarcoidosis: distinguishing features when the diagnosis is unclear. Circ Arrhythm Electrophysiol. 2014; 7(2):230-6. DOI: 10.1161/CIRCEP.113.000932. View

15.

Rautaharju P, Zhou S, Calhoun H . Ethnic differences in ECG amplitudes in North American white, black, and Hispanic men and women. Effect of obesity and age. J Electrocardiol. 1994; 27 Suppl:20-31. DOI: 10.1016/s0022-0736(94)80040-5. View

16.

Avula V, Wu K, Carrick R . Clinical Applications, Methodology, and Scientific Reporting of Electrocardiogram Deep-Learning Models: A Systematic Review. JACC Adv. 2024; 2(10). PMC: 10824530. DOI: 10.1016/j.jacadv.2023.100686. View

17.

Marcus F, McKenna W, Sherrill D, Basso C, Bauce B, Bluemke D . Diagnosis of arrhythmogenic right ventricular cardiomyopathy/dysplasia: proposed modification of the Task Force Criteria. Eur Heart J. 2010; 31(7):806-14. PMC: 2848326. DOI: 10.1093/eurheartj/ehq025. View

18.

Haq I, Liu K, Giudicessi J, Siontis K, Asirvatham S, Attia Z . Artificial intelligence-enhanced electrocardiogram for arrhythmogenic right ventricular cardiomyopathy detection. Eur Heart J Digit Health. 2024; 5(2):192-194. PMC: 10944679. DOI: 10.1093/ehjdh/ztad078. View

19.

Carrick R, Ahamed H, Sung E, Maron M, Madias C, Avula V . Identification of high-risk imaging features in hypertrophic cardiomyopathy using electrocardiography: A deep-learning approach. Heart Rhythm. 2024; 21(8):1390-1397. PMC: 11272903. DOI: 10.1016/j.hrthm.2024.01.031. View

20.

Zaidi A, Sheikh N, Jongman J, Gati S, Panoulas V, Carr-White G . Clinical Differentiation Between Physiological Remodeling and Arrhythmogenic Right Ventricular Cardiomyopathy in Athletes With Marked Electrocardiographic Repolarization Anomalies. J Am Coll Cardiol. 2015; 65(25):2702-11. DOI: 10.1016/j.jacc.2015.04.035. View