CoChat
Sign Up
Cited by 154ECG Monitoring and AnalysisNon-Invasive Vital Sign MonitoringCardiac pacing and defibrillation studies

Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction

Open access
Attia, Zachi I., Harmon, David M., Dugan, Jennifer, Manka, Lukas, Lopez-Jimenez, Francisco, Lerman, Amir, Siontis, Konstantinos C., Noseworthy, Peter A. +8 more·2022·Nature Medicine
DOI 10.1038/s41591-022-02053-1PMC PMC9805528
Open this paper in CoChat — free account

Abstract

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823-0.946) and 0.881 (0.815-0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41591-022-02053-1

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Models which have successfully generalized to wearable device ECGs have relied on automated algorithms to select high-quality subsets of available ECG data, with reduced performance when evaluated on all collected ECGs.

    “Additionally, models which have successfully generalized to wearable device ECGs have relied on automated algorithms to select high-quality subsets of available ECG data, with reduced performance when evaluated on all collected ECGs15,26.”

    From Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices (2023) · cites this paper as [26]

    The Discussion (page not available) reports that an automated filter selected clean smartwatch ECG tracings and improved AUC to 0.88, compared with 0.85 for the ECG closest in time to the echocardiogram. That supports the benefit of quality selection, but the lower-performance comparison was not an evaluation on all collected ECGs. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 37

  1. [1]Attia ZI, Harmon DM, Behr ER & Friedman PA Application of artificial intelligence to the electrocardiogram. Eur. Heart J. 42, 4717– 4730 (2021). 34534279 PMC8500024
  2. [2]Siontis KC, Noseworthy PA, Attia ZI & Friedman PA Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat. Rev. Cardiol. 18, 465– 478 (2021). 33526938 PMC7848866
  3. [3]Harmon DM, Attia ZI & Friedman PA Current and future implications of the artificial intelligence electrocardiogram: the transformation of healthcare and attendant research opportunities. Cardiovasc. Res. 118, e23– e25 (2022). 35187568 PMC9041336
  4. [4]Attia ZI Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat. Med. 25, 70– 74 (2019). 30617318
  5. [5]Kwon JM Deep learning-based algorithm for detecting aortic stenosis using electrocardiography. J. Am. Heart Assoc. 9, e014717 (2020). 32200712 PMC7428650
  6. [8]Kwon JM Artificial intelligence for detecting electrolyte imbalance using electrocardiography. Ann. Noninvasive Electrocardiol. 26, e12839 (2021). 33719135 PMC8164149
  7. [9]Attia ZI 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 (2019). 31378392
  8. [10]Echouffo-Tcheugui JB, Erqou S, Butler J, Yancy CW & Fonarow GC Assessing the risk of progression from asymptomatic left ventricular dysfunction to overt heart failure: a systematic overview and meta-analysis. JACC Heart Fail. 4, 237– 248 (2016). 26682794
  9. [11]Ammar KA Prevalence and prognostic significance of heart failure stages: application of the American College of Cardiology/American Heart Association heart failure staging criteria in the community. Circulation 115, 1563– 1570 (2007). 17353436
  10. [12]McDonagh TA, McDonald K & Maisel AS Screening for asymptomatic left ventricular dysfunction using B-type natriuretic peptide. Congest Heart Fail 14, 5– 8 (2008). 18772638
  11. [13]Attia ZI Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction. J. Cardiovasc. Electrophysiol. 30, 668– 674 (2019). 30821035
  12. [14]Attia IZ External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction. Int. J. Cardiol. 329, 130– 135 (2021). 33400971 PMC7955278
  13. [15]Adedinsewo D Artificial intelligence-enabled ECG algorithm to identify patients with left ventricular systolic dysfunction presenting to the emergency department with dyspnea. Circ. Arrhythm. Electrophysiol. 13, e008437 (2020). 32986471
  14. [16]Noseworthy PA 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. 13, e007988 (2020). 32064914 PMC7158877
  15. [17]Yao X Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial. Nat. Med. 27, 815– 819 (2021). 33958795
  16. [18]McDonagh TA 2021 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure. Eur. Heart J. 42, 3599– 3726 (2021). 34447992
  17. [19]Yancy CW 2017 ACC/AHA/HFSA focused update of the 2013 ACCF/AHA Guideline for the Management of Heart Failure: a report of the American College of Cardiology/American Heart Association Task Force on Cinical Practice Guidelines and the Heart Failure Society of America. Circulation 136, e137– e161 (2017). 28455343
  18. [20]Pisano ED Diagnostic performance of digital versus film mammography for breast-cancer screening. N. Engl. J. Med. 353, 1773– 1783 (2005). 16169887
  19. [21]Cárdenas-Turanzas M The accuracy of the Papanicolaou smear in the screening and diagnostic settings. J. Low. Genit. Trac. Dis. 12, 269– 275 (2008). 18820540
  20. [22]Bhalla V Diagnostic ability of B-type natriuretic peptide and impedance cardiography: testing to identify left ventricular dysfunction in hypertensive patients. Am. J. Hypertens. 18, 73s– 81s (2005). 15752936
  21. [24]Benjamin ZI Correction to: Heart disease and stroke statistics—2018 update: a report from the American Heart Association. Circulation 137, e493 (2018). 29555722
  22. [26]Dargie HJ Effect of carvedilol on outcome after myocardial infarction in patients with left-ventricular dysfunction: the CAPRICORN randomised trial. Lancet 357, 1385– 1390 (2001). 11356434
  23. [27]Pfeffer MA Effect of captopril on mortality and morbidity in patients with left ventricular dysfunction after myocardial infarction. Results of the survival and ventricular enlargement trial. The SAVE Investigators. N. Engl. J. Med. 327, 669– 677 (1992). 1386652
  24. [29]Grogan M Artificial intelligence-enhanced electrocardiogram for the early detection of cardiac amyloidosis. Mayo Clin. Proc. 96, 2768– 2778 (2021). 34218880
  25. [30]Ahn JC Development of the AI-cirrhosis-ECG score: an electrocardiogram-based deep learning model in cirrhosis. Am. J. Gastroenterol. 117, 424– 432 (2022). 35029163 PMC9727935
  26. [31]Bailey JJ Recommendations for standardization and specifications in automated electrocardiography: bandwidth and digital signal processing. A report for health professionals by an ad hoc writing group of the Committee on Electrocardiography and Cardiac Electrophysiology of the Council on Clinical Cardiology, American Heart Association. Circulation 81, 730– 739 (1990). 2297875
  27. [32]Shiner Z, Baharav A & Akselrod S Detection of different recumbent body positions from the electrocardiogram. Med. Biol. Eng. Comput. 41, 206– 210 (2003). 12691442
  28. [33]Nelwan SP, Meij SH, van Dam TB & Kors JA Correction of ECG variations caused by body position changes and electrode placement during ST-T monitoring. J. Electrocardiol. 34, 213– 216 (2001). 11781959
  29. [34]Williams GC The impact of posture on cardiac repolarization: more than heart rate? J. Cardiovasc. Electrophysiol. 17, 352– 358 (2006). 16643354
  30. [35]Schijvenaars BJ, Kors JA, van Herpen G, Kornreich F & van Bemmel JH Effect of electrode positioning on ECG interpretation by computer. J. Electrocardiol. 30, 247– 256 (1997). 9261733
  31. [36]Heidenreich PA Forecasting the impact of heart failure in the united states: a policy statement from the American Heart Association. Circ. Heart Fail. 6, 606– 619 (2013). 23616602 PMC3908895
  32. [37]Mozaffarian D Heart disease and stroke—2015 update: a report from the American Heart Association. Circulation 131, e29– e322 (2015). 25520374
  33. [38]Bahrami H Differences in the incidence of congestive heart failure by ethnicity: the multi-ethnic study of atherosclerosis. Arch. Intern. Med. 168, 2138– 2145 (2008). 18955644 PMC3038918
  34. [40]Steyerberg EW & Harrell FE Jr. Prediction models need appropriate internal, internal–external, and external validation. J. Clin. Epidemiol. 69, 245– 247 (2016). 25981519 PMC5578404
  35. [41]Tseng AS Cost effectiveness of an electrocardiographic deep learning algorithm to detect asymptomatic left ventricular dysfunction. Mayo Clinic Proc. 96, 1835– 1844 (2021). 34116837
  36. [42]Cohen-Shelly M Electrocardiogram screening for aortic valve stenosis using artificial intelligence. Eur. Heart J. 42, 2885– 2896 (2021). 33748852
  37. [43]Attia ZI Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ. Arrhythm. Electrophysiol. 12, e007284 (2019). PMC7661045 31450977

Cited by

Sorted by citations

Authors
Attia, Z. I., Harmon, D. M., Dugan, J., Manka, L., Lopez-Jimenez, F., Lerman, A., Siontis, K. C., Noseworthy, P. A., Yao, X., Klavetter, E. W., Halamka, J. D., Asirvatham, S. J., Khan, R., Carter, R. E., Leibovich, B. C., & Friedman, P. A.
Affiliations
Mayo Clinic (US)
Corresponding author
Friedman, Paul A.
ORCID
Venue
Nature Medicine
Publisher
Springer Science and Business Media LLC
Published
2022-11-14
Volume
28
Issue
12
Pages
2497-2503
ISSN
  • 1078-8956 (ISSN-L)
  • 1546-170X
DOI
10.1038/s41591-022-02053-1
PMC
PMC9805528
OpenAlex
W4308994163
Cited by
154
References
5
Citations by year
2026: 37 · 2025: 40 · 2024: 49 · 2023: 27 · 2022: 1
FWCI
20.37
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
  • U.S. Food and Drug Administration (U01FD006292)
  • Agency for Healthcare Research and Quality (R01 HS025402)
  • National Institute on Aging (R01AG062436, R21AG062580)
  • National Heart, Lung, and Blood Institute (R01HL143070, R01HL131535, R38HL150086)
Topics
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac pacing and defibrillation studies
Keywords
smartwatch ECG, left ventricular dysfunction, reduced ejection fraction, artificial intelligence, single-lead ECG, consumer health technology, echocardiography, mobile application, patient engagement, digital health
MeSH terms
Adult, Aged, Artificial Intelligence, Electrocardiography, Female, Heart Diseases, Humans, Male, Middle Aged, Prospective Studies, Ventricular Dysfunction, Left

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review