Machine Learning-Assisted Classification of Arrhythmias from Wearable ECG Patch Data
DOI:
https://doi.org/10.5281/zenodo.22501724Keywords:
arrhythmia classification, wearable ECG, deep learning, atrial fibrillation detection, ambulatory patch monitoringAbstract
Background: Wearable patch and smartwatch electrocardiogram (ECG) monitors now generate weeks of continuous single-lead data, motivating machine learning for automated arrhythmia classification. Objective: To review real, published evidence on deep learning-based arrhythmia classification and its clinical validation on wearable and patch ECG data. Methods: We synthesized peer-reviewed studies spanning benchmark datasets (MIT-BIH, PTB-XL, PhysioNet/CinC 2017), convolutional and recurrent neural network architectures, and prospective clinical validation of patch monitors (Zio), smartwatches (Apple Watch, Huawei, Fitbit), and handheld recorders (AliveCor KardiaMobile). Findings: Deep neural networks trained on ambulatory patch data have approached cardiologist-level multi-class rhythm classification, while large prospective cohorts (Apple Heart Study, mSToPS, Fitbit Heart Study, REHEARSE-AF) demonstrate high positive predictive value for atrial fibrillation detection at population scale, albeit with confirmatory-testing and signal-quality limitations. Conclusions: Machine learning-assisted arrhythmia classification from wearable ECG data is well supported by published algorithmic and clinical validation studies, but standardized benchmarking, outcome-linked trials, and clinical workflow integration remain needed before routine deployment.
References
Moody GB, Mark RG (2001). The impact of the MIT-BIH Arrhythmia Database. IEEE Engineering in Medicine and Biology Magazine, 20(3), 45-50. DOI: 10.1109/51.932724.
Wagner P, Strodthoff N, Bousseljot RD, Kreiseler D, Lunze FI, Samek W, Schaeffter T (2020). PTB-XL, a large publicly available electrocardiography dataset. Scientific Data, 7, 154. DOI: 10.1038/s41597-020-0495-6.
Clifford GD, Liu C, Moody B, Lehman LH, Silva I, Li Q, Johnson AE, Mark RG (2017). AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017. Computing in Cardiology, 44, 1-4. DOI: 10.22489/CinC.2017.065-469.
Turakhia MP, Hoang DD, Zimetbaum P, Miller JD, Froelicher VF, Kumar UN, Xu X, Yang F, Heidenreich PA (2013). Diagnostic Utility of a Novel Leadless Arrhythmia Monitoring Device. American Journal of Cardiology, 112(4), 520-524. DOI: 10.1016/j.amjcard.2013.04.017.
Perez MV, Mahaffey KW, Hedlin H, Rumsfeld JS, Garcia A, Ferris T, Balasubramanian V, Russo AM, Rajmane A, Cheung L, Hung G, Lee J, Kowey P, Talati N, Nag D, Gummidipundi SE, Beatty A, Hills MT, Desai S, Granger CB, Desai M, Turakhia MP; Apple Heart Study Investigators (2019). Large-Scale Assessment of a Smartwatch to Identify Atrial Fibrillation. New England Journal of Medicine, 381(20), 1909-1917. DOI: 10.1056/NEJMoa1901183.
Steinhubl SR, Waalen J, Edwards AM, Ariniello LM, Mehta RR, Ebner GS, Carter C, Baca-Motes K, Felicione E, Sarich T, Topol EJ (2018). Effect of a Home-Based Wearable Continuous ECG Monitoring Patch on Detection of Undiagnosed Atrial Fibrillation: The mSToPS Randomized Clinical Trial. JAMA, 320(2), 146-155. DOI: 10.1001/jama.2018.8102.
Lubitz SA, Faranesh AZ, Selvaggi C, Atlas SJ, McManus DD, Singer DE, Pagoto S, McConnell MV, Pantelopoulos A, Foulkes AS (2022). Detection of Atrial Fibrillation in a Large Population Using Wearable Devices: The Fitbit Heart Study. Circulation, 146(19), 1415-1424. DOI: 10.1161/CIRCULATIONAHA.122.060291.
Isakadze N, Martin SS (2020). How useful is the smartwatch ECG? Trends in Cardiovascular Medicine, 30(7), 442-448. DOI: 10.1016/j.tcm.2019.10.010.
Hong S, Zhou Y, Shang J, Xiao C, Sun J (2020). Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review. Computers in Biology and Medicine, 122, 103801. DOI:
1016/j.compbiomed.2020.103801. 10. Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, Ng AY (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature Medicine, 25(1), 65-69. DOI: 10.1038/s41591-018-0268-3.
Acharya UR, Fujita H, Lih OS, Hagiwara Y, Tan JH, Adam M (2017). Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Information Sciences, 405, 81-90. DOI: 10.1016/j.ins.2017.04.012.
Yıldırım Ö, Pławiak P, Tan RS, Acharya UR (2018). Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Computers in Biology and Medicine, 102, 411-420. DOI: 10.1016/j.compbiomed.2018.09.009.
Xiong Z, Nash MP, Cheng E, Fedorov VV, Stiles MK, Zhao J (2018). ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network. Physiological Measurement, 39(9), 094006. DOI: 10.1088/1361-6579/aad9ed.
Andersen RS, Peimankar A, Puthusserypady S (2019). A deep learning approach for real-time detection of atrial fibrillation. Expert Systems with Applications, 115, 465-473. DOI: 10.1016/j.eswa.2018.08.011.
Ribeiro AH, Ribeiro MH, Paixão GMM, Oliveira DM, Gomes PR, Canazart JA, Ferreira MPS, Andersson CR, Macfarlane PW, Meira W Jr, Schön TB, Ribeiro ALP (2020). Automatic diagnosis of the 12-lead ECG using a deep neural network. Nature Communications, 11(1), 1760. DOI: 10.1038/s41467-020-15432-4.
Attia ZI, Kapa S, Lopez-Jimenez F, McKie PM, Ladewig DJ, Satam G, Pellikka PA, Enriquez-Sarano M, Noseworthy PA, Munger TM, Asirvatham SJ, Scott CG, Carter RE, Friedman PA (2019). Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nature Medicine, 25(1), 70-74. DOI: 10.1038/s41591-018-0240-2.
Attia ZI, Noseworthy PA, Lopez-Jimenez F, Asirvatham SJ, Deshmukh AJ, Gersh BJ, Carter RE, Yao X, Rabinstein AA, Erickson BJ, Kapa S, Friedman PA (2019). An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. The Lancet, 394(10201), 861-867. DOI: 10.1016/S0140-6736(19)31721-0.
Guo Y, Wang H, Zhang H, Liu T, Liang Z, Xia Y, Yan L, Xing Y, Shi H, Li S, Liu Y, Liu F, Feng M, Chen Y, Lip GYH; MAFA II Investigators (2019). Mobile Photoplethysmographic Technology to Detect Atrial Fibrillation. Journal of the American College of Cardiology, 74(19), 2365-2375. DOI: 10.1016/j.jacc.2019.08.019.
Bumgarner JM, Lambert CT, Hussein AA, Cantillon DJ, Baranowski B, Wolski K, Lindsay BD, Wazni OM, Tarakji KG (2018). Smartwatch Algorithm for Automated Detection of Atrial Fibrillation. Journal of the American College of Cardiology, 71(21), 2381-2388. DOI: 10.1016/j.jacc.2018.03.003.
Tison GH, Sanchez JM, Ballinger B, Singh A, Olgin JE, Pletcher MJ, Vittinghoff E, Lee ES, Fan SM, Gladstone RA, Mikell C, Sohoni N, Hsieh J, Marcus GM (2018). Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch. JAMA Cardiology, 3(5), 409-416. 10.1001/jamacardio.2018.0136.
Halcox JPJ, Wareham K, Cardew A, Gilmore M, Barry JP, Phillips C, Gravenor MB (2017). Assessment of Remote Heart Rhythm Sampling Using the AliveCor Heart Monitor to Screen for Atrial Fibrillation: The REHEARSE-AF Study. Circulation, 136(19), 1784-1794. 10.1161/CIRCULATIONAHA.117.030583.
Wasserlauf J, You C, Patel R, Valys A, Albert D, Passman R (2019). Smartwatch Performance for the Detection and Quantification of Atrial Fibrillation. Circulation: Arrhythmia and Electrophysiology, 12(6), e006834. 10.1161/CIRCEP.118.006834.
Torres-Soto J, Ashley EA (2020). Multi-task deep learning for cardiac rhythm detection in wearable devices. NPJ Digital Medicine, 3, 116. DOI: 10.1038/s41746-020-00320-4.
Kwon S, Hong J, Choi EK, Lee E, Hostallero DE, Kang WJ, Lee B, Jeong ER, Koo BK, Oh S, Yi Y (2019). Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study. JMIR mHealth and uHealth, 7(6), e12770. DOI: 10.2196/12770. DOI: DOI: DOI:
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Ewa Zielinski, et al.

This work is licensed under a Creative Commons Attribution 4.0 International License.