Advertisement
Canadian Journal of Cardiology

The Role of Artificial Intelligence and Machine Learning in Clinical Cardiac Electrophysiology

      Abstract

      In recent years, numerous applications for artificial intelligence (AI) in cardiology have been found, due in part to large digitized data sets and the evolution of high-performance computing. In the discipline of cardiac electrophysiology (EP), a number of clinical, imaging, and electrical waveform data are considered in the diagnosis, prognostication, and management of arrhythmias, which lend themselves well to automation through AI. But equally relevant, AI offers a unique opportunity to discover novel EP concepts and improve clinical care through its inherent, hierarchical tenets of self-learning. In this review we focus on the application of AI in clinical EP and summarize state-of-the art, large, clinical studies in the following key domains: (1) electrocardiogram-based arrhythmia and disease classification; (2) atrial fibrillation source detection; (3) substrate and risk assessment for atrial fibrillation and ventricular tachyarrhythmias; and (4) predicting outcomes after cardiac resynchronization therapy. Many are small, single-centre, proof-of-concept investigations, but they still show ground-breaking performance of deep learning, a subdomain of AI, which surpasses traditional statistical analysis. Larger studies, for instance classifying arrhythmias from electrocardiogram recordings, have further provided external validation of their high accuracy. Ultimately, the performance of AI is dependent on the quality of the input data and the rigour of algorithm development. The field is still nascent and several barriers will need to be overcome, including prospective validation in large, well labelled data sets and more seamless information technology-based data collection/integration, before AI can be adopted into broader clinical EP practice. This review concludes with a discussion of these challenges and future work.

      Résumé

      Ces dernières années, de nombreuses applications relatives à l'intelligence artificielle (IA) en cardiologie ont été découvertes, en partie grâce aux vastes ensembles de données numérisées et à l'évolution du calcul haute performance. Dans la discipline de l'électrophysiologie cardiaque (EP), un certain nombre de données cliniques, d'imagerie et de types d'ondes électriques sont prises en compte dans le diagnostic, le pronostic et la prise en charge des arythmies, qui se prêtent bien à l'automatisation par l'IA. Mais de façon toute aussi pertinente, l'IA offre une occasion unique de découvrir de nouveaux concepts associés à l'EP et d'améliorer les soins cliniques grâce à ses principes inhérents et hiérarchiques d'auto-apprentissage. Dans cet article de revue, nous nous concentrons sur l'application de l'IA à l'EP clinique et synthétisons l'état de l'art, les grandes études cliniques dans les domaines clés suivants : (1) classification des arythmies et des pathologies basée sur l'électrocardiogramme; (2) détection de la source de la fibrillation auriculaire; (3) évaluation du substrat et du risque de fibrillation auriculaire et de tachyarythmie ventriculaire; et (4) prédiction du pronostic après une thérapie de resynchronisation cardiaque. Il s'agit souvent de petites études, monocentriques, de validation du concept, mais elles n'en présentent pas moins les performances révolutionnaires de l'apprentissage profond, un sous-domaine de l'IA, qui surpasse l'analyse statistique traditionnelle. Des études de plus grande envergure, portant par exemple sur la classification des arythmies à partir d'enregistrements d'électrocardiogrammes, ont fourni une validation externe de leur grande précision. En définitive, les performances de l'IA dépendent de la qualité des données d'entrée et de la rigueur du développement des algorithmes. Ce domaine en est encore à ses débuts et plusieurs obstacles devront être surmontés, notamment la validation prospective dans de grands ensembles de données bien identifiées et une collecte/intégration des données plus transparente basée sur les technologies de l'information, avant que l'IA ne puisse être adoptée plus largement dans la pratique clinique de l'EP. Cette revue se termine par une discussion sur ces défis et les développements futurs.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Canadian Journal of Cardiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Feeny A.K.
        • Chung M.K.
        • Madabhushi A.
        • et al.
        Artificial intelligence and machine learning in arrhythmias and cardiac electrophysiology.
        Circ Arrhythm Electrophysiol. 2020; 13e007952
        • Trayanova N.A.
        • Popescu D.M.
        • Shade J.K.
        Machine learning in arrhythmia and electrophysiology.
        Circ Res. 2021; 128: 544-566
        • Muthalaly R.G.
        • Evans R.M.
        Applications of machine learning in cardiac electrophysiology.
        Arrhythm Electrophysiol Rev. 2020; 9: 71-77
        • Somani S.
        • Russak A.J.
        • Richter F.
        • et al.
        Deep learning and the electrocardiogram: review of the current state-of-the-art.
        Europace. 2021; 23: 1179-1191
        • Goldberger A.L.
        • Amaral L.A.
        • Glass L.
        • et al.
        PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.
        Circulation. 2000; 101: E215-E220
        • Luz E.J.
        • Schwartz W.R.
        • Camara-Chavez G.
        • Menotti D.
        ECG-based heartbeat classification for arrhythmia detection: a survey.
        Comput Methods Programs Biomed. 2016; 127: 144-164
        • Johnson A.E.
        • Pollard T.J.
        • Shen L.
        • et al.
        MIMIC-III, a freely accessible critical care database.
        Sci Data. 2016; 3: 160035
        • Varma N.
        • Cygankiewicz I.
        • Turakhia M.P.
        • et al.
        2021 ISHNE/HRS/EHRA/APHRS expert collaborative statement on mHealth in arrhythmia management: digital medical tools for heart rhythm professionals: from the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia-Pacific Heart Rhythm Society.
        Circ Arrhythm Electrophysiol. 2021; 14e009204
        • Hannun A.Y.
        • Rajpurkar P.
        • Haghpanahi M.
        • et al.
        Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network.
        Nat Med. 2019; 25: 65-69
        • Chang K.C.
        • Hsieh P.H.
        • Wu M.Y.
        • et al.
        Usefulness of machine learning-based detection and classification of cardiac arrhythmias with 12-lead electrocardiograms.
        Can J Cardiol. 2021; 37: 94-104
        • Zhou S.
        • Sapp J.L.
        • AbdelWahab A.
        • Trayanova N.
        Deep learning applied to electrocardiogram interpretation.
        Can J Cardiol. 2021; 37: 17-18
        • van de Leur R.R.
        • Blom L.J.
        • Gavves E.
        • et al.
        Automatic triage of 12-lead ECGs using deep convolutional neural networks.
        J Am Heart Assoc. 2020; 9e015138
        • Selvaraju R.R.
        • Cogswell M.
        • Das A.
        • et al.
        Visual explanations from deep networks via gradient-based localization.
        Int J Comput Vis. 2020; 128: 336-359
        • Perez M.V.
        • Mahaffey K.W.
        • Hedlin H.
        • et al.
        Large-scale assessment of a smartwatch to identify atrial fibrillation.
        N Engl J Med. 2019; 381: 1909-1917
        • Guo Y.
        • Wang H.
        • Zhang H.
        • et al.
        Mobile photoplethysmographic technology to detect atrial fibrillation.
        J Am Coll Cardiol. 2019; 74: 2365-2375
        • Wasserlauf J.
        • You C.
        • Patel R.
        • et al.
        Smartwatch performance for the detection and quantification of atrial fibrillation.
        Circ Arrhythm Electrophysiol. 2019; 12e006834
        • Bumgarner J.M.
        • Lambert C.T.
        • Hussein A.A.
        • et al.
        Smartwatch algorithm for automated detection of atrial fibrillation.
        J Am Coll Cardiol. 2018; 71: 2381-2388
        • Attia Z.I.
        • Noseworthy P.A.
        • Lopez-Jimenez F.
        • et al.
        An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction.
        Lancet. 2019; 394: 861-867
        • Raghunath S.
        • Pfeifer J.M.
        • Ulloa-Cerna A.E.
        • et al.
        Deep neural networks can predict new-onset atrial fibrillation from the 12-lead ECG and help identify those at risk of atrial fibrillation-related stroke.
        Circulation. 2021; 143: 1287-1298
        • Attia Z.I.
        • Kapa S.
        • Lopez-Jimenez F.
        • et al.
        Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram.
        Nat Med. 2019; 25: 70-74
        • Attia Z.I.
        • Kapa S.
        • Yao X.
        • et al.
        Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction.
        J Cardiovasc Electrophysiol. 2019; 30: 668-674
        • Adedinsewo D.
        • Carter R.E.
        • Attia Z.
        • et al.
        Artificial intelligence-enabled ECG algorithm to identify patients with left ventricular systolic dysfunction presenting to the emergency department with dyspnea.
        Circ Arrhythm Electrophysiol. 2020; 13e008437
        • Attia I.Z.
        • Tseng A.S.
        • Benavente E.D.
        • et al.
        External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction.
        Int J Cardiol. 2021; 329: 130-135
        • Yao X.
        • McCoy R.G.
        • Friedman P.A.
        • et al.
        ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): rationale and design of a pragmatic cluster randomized trial.
        Am Heart J. 2020; 219: 31-36
        • Bleijendaal H.
        • Ramos L.A.
        • Lopes R.R.
        • et al.
        Computer versus cardiologist: is a machine learning algorithm able to outperform an expert in diagnosing a phospholamban p.Arg14del mutation on the electrocardiogram?.
        Heart Rhythm. 2021; 18: 79-87
        • van de Leur R.R.
        • Taha K.
        • Bos M.N.
        • et al.
        Discovering and visualizing disease-specific electrocardiogram features using deep learning: proof-of-concept in phospholamban gene mutation carriers.
        Circ Arrhythm Electrophysiol. 2021; 14e009056
        • Ko W.Y.
        • Siontis K.C.
        • Attia Z.I.
        • et al.
        Detection of hypertrophic cardiomyopathy using a convolutional neural network-enabled electrocardiogram.
        J Am Coll Cardiol. 2020; 75: 722-733
        • Giudicessi J.R.
        • Schram M.
        • Bos J.M.
        • et al.
        Artificial intelligence-enabled assessment of the heart rate corrected QT interval using a mobile electrocardiogram device.
        Circulation. 2021; 143: 1274-1286
        • Bos J.M.
        • Attia Z.I.
        • Albert D.E.
        • et al.
        Use of artificial intelligence and deep neural networks in evaluation of patients with electrocardiographically concealed long QT syndrome from the surface 12-lead electrocardiogram.
        JAMA Cardiol. 2021; 6: 532-538
        • Galloway C.D.
        • Valys A.V.
        • Shreibati J.B.
        • et al.
        Development and validation of a deep-learning model to screen for hyperkalemia from the electrocardiogram.
        JAMA Cardiol. 2019; 4: 428-436
        • Raghunath S.
        • Ulloa Cerna A.E.
        • Jing L.
        • et al.
        Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.
        Nat Med. 2020; 26: 886-891
        • Alhusseini M.I.
        • Abuzaid F.
        • Rogers A.J.
        • et al.
        Machine learning to classify intracardiac electrical patterns during atrial fibrillation: machine learning of atrial fibrillation.
        Circ Arrhythm Electrophysiol. 2020; 13e008160
        • Zolotarev A.M.
        • Hansen B.J.
        • Ivanova E.A.
        • et al.
        Optical mapping-validated machine learning improves atrial fibrillation driver detection by multi-electrode mapping.
        Circ Arrhythm Electrophysiol. 2020; 13e008249
        • Liao S.
        • Ragot D.
        • Nayyar S.
        • et al.
        Deep learning classification of unipolar electrograms in human atrial fibrillation: application in focal source mapping.
        Front Physiol. 2021; 12: 704122
        • Liu C.M.
        • Chang S.L.
        • Chen H.H.
        • et al.
        The clinical application of the deep learning technique for predicting trigger origins in patients with paroxysmal atrial fibrillation with catheter ablation.
        Circ Arrhythm Electrophysiol. 2020; 13e008518
        • Corrado C.
        • Williams S.
        • Roney C.
        • et al.
        Using machine learning to identify local cellular properties that support re-entrant activation in patient-specific models of atrial fibrillation.
        Europace. 2021; 23: i12-i20
        • Zahid S.
        • Cochet H.
        • Boyle P.M.
        • et al.
        Patient-derived models link re-entrant driver localization in atrial fibrillation to fibrosis spatial pattern.
        Cardiovasc Res. 2016; 110: 443-454
        • Shade J.K.
        • Ali R.L.
        • Basile D.
        • et al.
        Preprocedure application of machine learning and mechanistic simulations predicts likelihood of paroxysmal atrial fibrillation recurrence following pulmonary vein isolation.
        Circ Arrhythm Electrophysiol. 2020; 13e008213
        • Winkle R.A.
        • Jarman J.W.
        • Mead R.H.
        • et al.
        Predicting atrial fibrillation ablation outcome: the CAAP-AF score.
        Heart Rhythm. 2016; 13: 2119-2125
        • Mesquita J.
        • Ferreira A.M.
        • Cavaco D.
        • et al.
        Development and validation of a risk score for predicting atrial fibrillation recurrence after a first catheter ablation procedure - ATLAS score.
        Europace. 2018; 20: f428-f435
        • Firouznia M.
        • Feeny A.K.
        • LaBarbera M.A.
        • et al.
        Machine learning-derived fractal features of shape and texture of the left atrium and pulmonary veins from cardiac computed tomography scans are associated with risk of recurrence of atrial fibrillation postablation.
        Circ Arrhythm Electrophysiol. 2021; 14e009265
        • Varela M.
        • Bisbal F.
        • Zacur E.
        • et al.
        Novel computational analysis of left atrial anatomy improves prediction of atrial fibrillation recurrence after ablation.
        Front Physiol. 2017; 8: 68
        • Tiwari P.
        • Colborn K.L.
        • Smith D.E.
        • et al.
        Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation.
        JAMA Netw Open. 2020; 3e1919396
        • Rogers A.J.
        • Selvalingam A.
        • Alhusseini M.I.
        • et al.
        Machine learned cellular phenotypes in cardiomyopathy predict sudden death.
        Circ Res. 2021; 128: 172-184
        • Lee H.
        • Shin S.Y.
        • Seo M.
        • Nam G.B.
        • Joo S.
        Prediction of ventricular tachycardia one hour before occurrence using artificial neural networks.
        Sci Rep. 2016; 6: 32390
        • Okada D.R.
        • Miller J.
        • Chrispin J.
        • et al.
        Substrate spatial complexity analysis for the prediction of ventricular arrhythmias in patients with ischemic cardiomyopathy.
        Circ Arrhythm Electrophysiol. 2020; 13e007975
        • Feeny A.K.
        • Rickard J.
        • Patel D.
        • et al.
        Machine learning prediction of response to cardiac resynchronization therapy: improvement versus current guidelines.
        Circ Arrhythm Electrophysiol. 2019; 12e007316
        • Kalscheur M.M.
        • Kipp R.T.
        • Tattersall M.C.
        • et al.
        Machine learning algorithm predicts cardiac resynchronization therapy outcomes: lessons from the COMPANION trial.
        Circ Arrhythm Electrophysiol. 2018; 11e005499
        • Tokodi M.
        • Schwertner W.R.
        • Kovacs A.
        • et al.
        Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score.
        Eur Heart J. 2020; 41: 1747-1756
        • Noseworthy P.A.
        • Attia Z.I.
        • Brewer L.C.
        • et al.
        Assessing and mitigating bias in medical artificial intelligence: the effects of race and ethnicity on a deep learning model for ECG analysis.
        Circ Arrhythm Electrophysiol. 2020; 13e007988
        • Li D.C.
        • Hu S.C.
        • Lin L.S.
        • Yeh C.W.
        Detecting representative data and generating synthetic samples to improve learning accuracy with imbalanced data sets.
        PLoS One. 2017; 12e0181853
        • Han X.
        • Hu Y.
        • Foschini L.
        • et al.
        Deep learning models for electrocardiograms are susceptible to adversarial attack.
        Nat Med. 2020; 26: 360-363
      1. Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision. ECCV 2014. Lecture Notes in Computer Science, vol 8689. 2014;818-833.

        • Wang F.
        • Kaushal R.
        • Khullar D.
        Should health care demand interpretable artificial intelligence or accept “black box” medicine?.
        Ann Intern Med. 2020; 172: 59-60
        • He J.
        • Baxter S.L.
        • Xu J.
        • et al.
        The practical implementation of artificial intelligence technologies in medicine.
        Nat Med. 2019; 25: 30-36
        • Clerx M.
        • Heijman J.
        • Collins P.
        • Volders P.G.A.
        Predicting changes to INa from missense mutations in human SCN5A.
        Sci Rep. 2018; 8: 12797
        • Yang P.C.
        • DeMarco K.R.
        • Aghasafari P.
        • et al.
        A computational pipeline to predict cardiotoxicity: from the atom to the rhythm.
        Circ Res. 2020; 126: 947-964
        • Ironi L.
        • Tentoni S.
        Interplay of spatial aggregation and computational geometry in extracting diagnostic features from cardiac activation data.
        Comput Methods Programs Biomed. 2012; 107: 456-467
        • Yang T.
        • Yu L.
        • Jin Q.
        • Wu L.
        • He B.
        Localization of origins of premature ventricular contraction by means of convolutional neural network from 12-lead ECG.
        IEEE Trans Biomed Eng. 2018; 65: 1662-1671
        • Yan B.P.
        • Lai W.H.S.
        • Chan C.K.Y.
        • et al.
        Contact-free screening of atrial fibrillation by a Smartphone using facial pulsatile photoplethysmographic signals.
        J Am Heart Assoc. 2018; 7e008585
        • Sammani A.
        • Jansen M.
        • Linschoten M.
        • et al.
        UNRAVEL: big data analytics research data platform to improve care of patients with cardiomyopathies using routine electronic health records and standardised biobanking.
        Neth Heart J. 2019; 27: 426-434
        • Melero-Alegria J.I.
        • Cascon M.
        • Romero A.
        • et al.
        SALMANTICOR study. Rationale and design of a population-based study to identify structural heart disease abnormalities: a spatial and machine learning analysis.
        BMJ Open. 2019; 9e024605
        • Vollmer S.
        • Mateen B.A.
        • Bohner G.
        • et al.
        Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness.
        BMJ. 2020; 368: l6927
        • Cikes M.
        • Sanchez-Martinez S.
        • Claggett B.
        • et al.
        Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy.
        Eur J Heart Fail. 2019; 21: 74-85
        • Feeny A.K.
        • Rickard J.
        • Trulock K.M.
        • et al.
        Machine learning of 12-lead QRS waveforms to identify cardiac resynchronization therapy patients with differential outcomes.
        Circ Arrhythm Electrophysiol. 2020; 13e008210