Abstract
The quantity of data produced and captured in medicine today is unprecedented. Technological improvements and automation have expanded the traditional statistical methods and enabled the analysis of Big Data. This has permitted the discovery of new associations with a granularity that was previously hidden to human eyes. In the first part of this review, the authors would like to provide an overview of basic Machine Learning (ML) principles and techniques in order to better understand their application in recent publications about cardiac arrhythmias. In the second part, ML-enabled advances in disease detection and diagnosis, outcome prediction, and novel disease characterization in topics like electrocardiography, atrial fibrillation, ventricular arrhythmias, and cardiac devices are presented. Finally, the limitations and challenges of applying ML in clinical practice, such as validation, replication, generalizability, and regulatory issues, are discussed. More carefully designed studies and collaborations are needed for ML to become feasible, trustworthy, accurate, and reproducible and to reach its full potential for patient-oriented precision medicine.
Zusammenfassung
Die Menge generierter und erfasster Daten in der Medizin war noch nie so hoch wie heute. Der technologische Fortschritt und die Automatisierung haben die traditionellen statistischen Methoden erweitert und die Analyse von Big Data ermöglicht. Dies hat die Entdeckung neuer Assoziationen mit einer Granularität ermöglicht, die dem Menschen zuvor verborgen war. Der erste Teil dieser Übersichtsarbeit bietet einen Überblick der grundlegenden Prinzipien und Techniken des maschinellen Lernens (ML), um deren Anwendung in den neuesten Veröffentlichungen über Herzrhythmusstörungen besser zu verstehen. Der zweite Teil schildert ML-gestützte Fortschritte bei der Erkennung und Diagnose von Erkrankungen, bei der Vorhersage von Ergebnissen und bei der neuartigen Charakterisierung von Erkrankungen im Zusammenhang mit Themen wie Elektrokardiographie, Vorhofflimmern, ventrikulären Arrhythmien und kardialen Geräten. Schließlich werden die Grenzen und Herausforderungen der Anwendung von ML in der klinischen Praxis diskutiert, beispielsweise in Bezug auf Validierung, Replikation, Verallgemeinerbarkeit und regulatorische Fragen. Weitere sorgfältig konzipierte Studien und Kooperationen sind erforderlich, damit ML umsetzbar, verlässlich, präzise und reproduzierbar wird und um ihr volles Potenzial für eine patientenorientierte Präzisionsmedizin ausschöpfen zu können.
Similar content being viewed by others
Change history
30 March 2022
An Erratum to this paper has been published: https://doi.org/10.1007/s00399-022-00850-2
References
Austin C, Kusumoto F (2016) The application of big data in medicine: current implications and future directions. J Interv Card Electrophysiol 47:51–59
Andreu-Perez J, Poon CC, Merrifield RD, Wong ST, Yang GZ (2015) Big data for health. IEEE J Biomed Health Inform 19:1193–1208
Stevens LM, Mortazavi BJ, Deo RC, Curtis L, Kao DP (2020) Recommendations for reporting machine learning analyses in clinical research. Circ Cardiovasc Qual Outcomes 13:e6556
Beam AL, Kohane IS (2018) Big data and machine learning in health care. JAMA 319:1317–1318
Levy AE, Biswas M, Weber R, Tarakji K, Chung M, Noseworthy PA et al (2019) Applications of machine learning in decision analysis for dose management for dofetilide. PLoS ONE 14:e227324
Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484–489
Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP et al (2019) Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 25:65–69
He R, Wang K, Zhao N, Liu Y, Yuan Y, Li Q et al (2018) Automatic detection of atrial fibrillation based on continuous wavelet transform and 2D convolutional neural networks. Front Physiol 9:1206
Smith SW, Rapin J, Li J, Fleureau Y, Fennell W, Walsh BM et al (2019) A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation. Int J Cardiol Heart Vasc 25:100423
Huang D, Yamauchi K, Inden Y, Yang J, Jiang Z, Ida H et al (2005) Use of an artificial neural network to localize accessory pathways of Wolff-Parkinson-White syndrome with 12-lead electrocardiogram. Med Inform Internet Med 30:277–286
Mjahad A, Rosado-Munoz A, Bataller-Mompean M, Frances-Villora JV, Guerrero-Martinez JF (2017) Ventricular fibrillation and tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning. Comput Methods Programs Biomed 141:119–127
Zhou X, Zhu X, Nakamura K, Mahito N (2018) Premature ventricular contraction detection from ambulatory ECG using recurrent neural networks. Annu Int Conf IEEE Eng Med Biol Soc 2018:2551–2554
Asgari S, Mehrnia A, Moussavi M (2015) Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machine. Comput Biol Med 60:132–142
Attia ZI, Noseworthy PA, Lopez-Jimenez F, Asirvatham SJ, Deshmukh AJ, Gersh BJ et al (2019) An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet 394:861–867
Kashou AH, Rabinstein AA, Attia IZ, Asirvatham SJ, Gersh BJ, Friedman PA et al (2020) Recurrent cryptogenic stroke: a potential role for an artificial intelligence-enabled electrocardiogram? HeartRhythm Case Rep 6:202–205
Lee H, Shin SY, Seo M, Nam GB, Joo S (2016) Prediction of ventricular tachycardia one hour before occurrence using artificial neural networks. Sci Rep 6:32390
Attia ZI, Kapa S, Lopez-Jimenez F, McKie PM, Ladewig DJ, Satam G et al (2019) Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat Med 25:70–74
Sengupta PP, Kulkarni H, Narula J (2018) Prediction of abnormal myocardial relaxation from signal processed surface ECG. J Am Coll Cardiol 71:1650–1660
Adedinsewo D, Carter RE, Attia Z, Johnson P, Kashou AH, Dugan JL et al (2020) Artificial intelligence-enabled ECG algorithm to identify patients with left ventricular systolic dysfunction presenting to the emergency department with dyspnea. Circ Arrhythm Electrophysiol 13:e8437
Galloway CD, Valys AV, Shreibati JB, Treiman DL, Petterson FL, Gundotra VP et al (2019) Development and validation of a deep-learning model to screen for hyperkalemia from the electrocardiogram. JAMA Cardiol 4:428–436
Porumb M, Stranges S, Pescape A, Pecchia L (2020) Precision medicine and artificial intelligence: a pilot study on deep learning for hypoglycemic events detection based on ECG. Sci Rep 10:170
Simjanoska M, Gjoreski M, Gams M, Madevska Bogdanova A (2018) Non-invasive blood pressure estimation from ECG using machine learning techniques. Sensors (Basel) 18(4):1160. https://doi.org/10.3390/s18041160
Attia ZI, Friedman PA, Noseworthy PA, Lopez-Jimenez F, Ladewig DJ, Satam G et al (2019) Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ Arrhythm Electrophysiol 12:e7284
Kalscheur MM, Kipp RT, Tattersall MC, Mei C, Buhr KA, DeMets DL et al (2018) Machine learning algorithm predicts cardiac resynchronization therapy outcomes: lessons from the COMPANION trial. Circ Arrhythm Electrophysiol 11:e5499
Tokodi M, Schwertner WR, Kovacs A, Toser Z, Staub L, Sarkany A et al (2020) Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score. Eur Heart J 41:1747–1756
Feeny AK, Rickard J, Patel D, Toro S, Trulock KM, Park CJ et al (2019) Machine learning prediction of response to cardiac resynchronization therapy: improvement versus current guidelines. Circ Arrhythm Electrophysiol 12:e7316
Cikes M, Sanchez-Martinez S, Claggett B, Duchateau N, Piella G, Butakoff C et al (2019) Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy. Eur J Heart Fail 21:74–85
Tiwari P, Colborn KL, Smith DE, Xing F, Ghosh D, Rosenberg MA (2020) Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation. JAMA Netw Open 3:e1919396
Hill NR, Ayoubkhani D, McEwan P, Sugrue DM, Farooqui U, Lister S et al (2019) Predicting atrial fibrillation in primary care using machine learning. PLoS ONE 14:e224582
Yan BP, Lai WHS, Chan CKY, Chan SC, Chan LH, Lam KM et al (2018) Contact-free screening of atrial fibrillation by a smartphone using facial pulsatile photoplethysmographic signals. J Am Heart Assoc 7(8):e8585. https://doi.org/10.1161/JAHA.118.008585
Sanatkhani S, Nedios S, Menon PG, Bollmann A, Hindricks G, Shroff SG (2021) Subject-specific calculation of left atrial appendage blood-borne particle residence time distribution in atrial fibrillation. Front Physiol 12:633135
Han L, Askari M, Altman RB, Schmitt SK, Fan J, Bentley JP et al (2019) Atrial fibrillation burden signature and near-term prediction of stroke: a machine learning analysis. Circ Cardiovasc Qual Outcomes 12:e5595
Inohara T, Shrader P, Pieper K, Blanco RG, Thomas L, Singer DE et al (2018) Association of of atrial fibrillation clinical phenotypes with treatment patterns and outcomes: a multicenter registry study. JAMA Cardiol 3:54–63
Verma A, Jiang CY, Betts TR, Chen J, Deisenhofer I, Mantovan R et al (2015) Approaches to catheter ablation for persistent atrial fibrillation. N Engl J Med 372:1812–1822
Schilling C, Keller M, Scherr D, Oesterlein T, Haissaguerre M, Schmitt C et al (2015) Fuzzy decision tree to classify complex fractionated atrial electrograms. Biomed Tech (Berl) 60:245–255
Alhusseini MI, Abuzaid F, Rogers AJ, Zaman JAB, Baykaner T, Clopton P et al (2020) Machine learning to classify Intracardiac electrical patterns during atrial fibrillation: machine learning of atrial fibrillation. Circ Arrhythm Electrophysiol 13:e8160
Zolotarev AM, Hansen BJ, Ivanova EA, Helfrich KM, Li N, Janssen PML et al (2020) Optical mapping-validated machine learning improves atrial fibrillation driver detection by multi-electrode mapping. Circ Arrhythm Electrophysiol 13:e8249
Mesquita J, Ferreira AM, Cavaco D, Moscoso Costa F, Carmo P, Marques H et al (2018) Development and validation of a risk score for predicting atrial fibrillation recurrence after a first catheter ablation procedure—ATLAS score. Europace 20:f428–f435
Varela M, Bisbal F, Zacur E, Berruezo A, Aslanidi OV, Mont L et al (2017) Novel computational analysis of left atrial anatomy improves prediction of atrial fibrillation recurrence after ablation. Front Physiol 8:68
Nedios S, Sanatkhani S, Oladosu M, Seewoster T, Richter S, Arya A et al (2021) Association of low-voltage areas with the regional wall deformation and the left atrial shape in patients with atrial fibrillation: a proof of concept study. Int J Cardiol Heart Vasc 33:100730
Nedios S, Lindemann F, Heijman J, Crijns H, Bollmann A, Hindricks G (2021) Atrial remodeling and atrial fibrillation recurrence after catheter ablation : past, present, and future developments. Herz 46:312–317
Atta-Fosu T, LaBarbera M, Ghose S, Schoenhagen P, Saliba W, Tchou PJ et al (2021) A new machine learning approach for predicting likelihood of recurrence following ablation for atrial fibrillation from CT. BMC Med Imaging 21:45
Firouznia M, Feeny AK, LaBarbera MA, McHale M, Cantlay C, Kalfas N et al (2021) 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 14:e9265
Nedios S, Koutalas E, Sommer P, Arya A, Rolf S, Husser D et al (2017) Asymmetrical left atrial remodelling in atrial fibrillation: relation with diastolic dysfunction and long-term ablation outcomes. Europace 19:1463–1469
Shade JK, Ali RL, Basile D, Popescu D, Akhtar T, Marine JE et al (2020) Preprocedure application of machine learning and mechanistic simulations predicts likelihood of paroxysmal atrial fibrillation recurrence following pulmonary vein isolation. Circ Arrhythm Electrophysiol 13:e8213
Shim J, Hwang M, Song JS, Lim B, Kim TH, Joung B et al (2017) Virtual in-Silico modeling guided catheter ablation predicts effective linear ablation lesion set for longstanding persistent atrial fibrillation: multicenter prospective randomized study. Front Physiol 8:792
Boyle PM, Zghaib T, Zahid S, Ali RL, Deng D, Franceschi WH et al (2019) Computationally guided personalized targeted ablation of persistent atrial fibrillation. Nat Biomed Eng 3:870–879
Aronis KN, Ali RL, Liang JA, Zhou S, Trayanova NA (2019) Understanding AF mechanisms through computational modelling and simulations. Arrhythm Electrophysiol Rev 8:210–219
Dagres N, Peek N, Leclercq C, Hindricks G (2020) The PROFID project. Eur Heart J 41:3781–3782
Okada DR, Miller J, Chrispin J, Prakosa A, Trayanova N, Jones S et al (2020) Substrate spatial complexity analysis for the prediction of ventricular arrhythmias in patients with ischemic cardiomyopathy. Circ Arrhythm Electrophysiol 13:e7975
Alis D, Guler A, Yergin M, Asmakutlu O (2020) Assessment of ventricular tachyarrhythmia in patients with hypertrophic cardiomyopathy with machine learning-based texture analysis of late gadolinium enhancement cardiac MRI. Diagn Interv Imaging 101:137–146
Rogers AJ, Selvalingam A, Alhusseini MI, Krummen DE, Corrado C, Abuzaid F et al (2021) Machine learned cellular phenotypes in cardiomyopathy predict sudden death. Circ Res 128:172–184
Marzec L, Raghavan S, Banaei-Kashani F, Creasy S, Melanson EL, Lange L et al (2018) Device-measured physical activity data for classification of patients with ventricular arrhythmia events: a pilot investigation. PLoS ONE 13:e206153
Yokokawa M, Liu TY, Yoshida K, Scott C, Hero A, Good E et al (2012) Automated analysis of the 12-lead electrocardiogram to identify the exit site of postinfarction ventricular tachycardia. Heart Rhythm 9:330–334
Sapp JL, Bar-Tal M, Howes AJ, Toma JE, El-Damaty A, Warren JW et al (2017) Real-time localization of ventricular tachycardia origin from the 12-lead electrocardiogram. JACC Clin Electrophysiol 3:687–699
Zhou S, AbdelWahab A, Horacek BM, MacInnis PJ, Warren JW, Davis JS et al (2020) Prospective assessment of an automated Intraprocedural 12-lead ECG-based system for localization of early left ventricular activation. Circ Arrhythm Electrophysiol 13:e8262
Gyawali PK, Horacek BM, Sapp JL, Wang L (2020) Sequential factorized autoencoder for localizing the origin of ventricular activation from 12-lead electrocardiograms. IEEE Trans Biomed Eng 67:1505–1516
Yang T, Yu L, Jin Q, Wu L, He B (2018) Localization of origins of premature ventricular contraction by means of convolutional neural network from 12-lead ECG. IEEE Trans Biomed Eng 65:1662–1671
Bogossian H, Panteloglou D, Karosiene Z, Macher-Heidrich S, Adomeit HJ, Lemke B et al (2021) Perioprocedural mortality after ICD implantation. Herz 46:581–588
Markewitz A (2021) Bundesfachgruppe Herzschrittmacher und D. [annual report 2019 of the German pacemaker and defibrillator registry-part 1: cardiac pacemakers : working group on cardiac pacemakers and cardioverter-defibrillators at IQTIG-institute for quality assurance and transparency in healthcare]. Herzschrittmacherther Elektrophysiol 32:510–523
Nowak B, Misselwitz B, Przibille O, Mehta RH (2017) Is mortality a useful parameter for public reporting in pacemaker implantation? Results of an obligatory external quality control programme. Europace 19:568–572
Dewland TA, Pellegrini CN, Wang Y, Marcus GM, Keung E, Varosy PD (2011) Dual-chamber implantable cardioverter-defibrillator selection is associated with increased complication rates and mortality among patients enrolled in the NCDR implantable cardioverter-defibrillator registry. J Am Coll Cardiol 58:1007–1013
Bogossian H, Frommeyer G, Hochadel M, Ince H, Spitzer SG, Eckardt L et al (2020) Single chamber implantable cardioverter defibrillator compared to dual chamber implantable cardioverter defibrillator: less is more! Data from the German device registry. Clin Res Cardiol 109:911–917
Shakibfar S, Krause O, Lund-Andersen C, Aranda A, Moll J, Andersen TO et al (2019) Predicting electrical storms by remote monitoring of implantable cardioverter-defibrillator patients using machine learning. Europace 21:268–274
Sanroman-Junquera M, Mora-Jimenez I, Almendral J, Garcia-Alberola A, Rojo-Alvarez JL (2015) Automatic supporting system for regionalization of ventricular tachycardia exit site in implantable defibrillators. PLoS ONE 10:e124514
Wegner FK, Kochhauser S, Ellermann C, Lange PS, Frommeyer G, Leitz P et al (2020) Prospective blinded evaluation of the smartphone-based AliveCor Kardia ECG monitor for atrial fibrillation detection: the PEAK-AF study. Eur J Intern Med 73:72–75
van de Leur RR, Boonstra MJ, Bagheri A, Roudijk RW, Sammani A, Taha K et al (2020) Big data and artificial intelligence: opportunities and threats in electrophysiology. Arrhythm Electrophysiol Rev 9:146–154
Howard JP, Fisher L, Shun-Shin MJ, Keene D, Arnold AD, Ahmad Y et al (2019) Cardiac rhythm device identification using neural networks. JACC Clin Electrophysiol 5:576–586
Hindricks G, Elsner C, Piorkowski C, Taborsky M, Geller JC, Schumacher B et al (2014) Quarterly vs. yearly clinical follow-up of remotely monitored recipients of prophylactic implantable cardioverter-defibrillators: results of the REFORM trial. Eur Heart J 35:98–105
Hindricks G, Varma N, Kacet S, Lewalter T, Sogaard P, Guedon-Moreau L et al (2017) Daily remote monitoring of implantable cardioverter-defibrillators: insights from the pooled patient-level data from three randomized controlled trials (IN-TIME, ECOST, TRUST). Eur Heart J 38:1749–1755
Rosier A, Mabo P, Temal L, van Hille P, Dameron O, Deleger L et al (2016) Personalized and automated remote monitoring of atrial fibrillation. Europace 18:347–352
Varma N, Cygankiewicz I, Turakhia MP, Heidbuchel H, Hu YF, Chen LY et al (2021) 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 14:e9204
Loring Z, Mehrotra S, Piccini JP (2019) Machine learning in ‘big data’: handle with care. Europace 21:1284–1285
Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK (2018) Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 15:e1002683
Obermeyer Z, Powers B, Vogeli C, Mullainathan S (2019) Dissecting racial bias in an algorithm used to manage the health of populations. Science 366:447–453
Parikh RB, Teeple S, Navathe AS (2019) Addressing bias in artificial intelligence in health care. JAMA 322:2377–2378
Hosny A, Aerts H (2019) Artificial intelligence for global health. Science 366:955–956
Chen IY, Pierson E, Rose S, Joshi S, Ferryman K, Ghassemi M (2021) Ethical machine learning in healthcare. Annu Rev Biomed Data Sci 4:123–144
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
S. Nedios, K. Iliodromitis, C. Kowalewski, A. Bollmann, G. Hindricks, N. Dagres, and H. Bogossian declare that they have no competing interests.
For this article no studies with human participants or animals were performed by any of the authors. All studies performed were in accordance with the ethical standards indicated in each case.
Additional information
Scan QR code & read article online
The original online version of this article was revised: The author name Christopher Kowalewski was incorrectly written as Christopher Kowaleski.
Rights and permissions
About this article
Cite this article
Nedios, S., Iliodromitis, K., Kowalewski, C. et al. Big Data in electrophysiology. Herzschr Elektrophys 33, 26–33 (2022). https://doi.org/10.1007/s00399-022-00837-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00399-022-00837-z