Automated detection of low ejection fraction from a one-lead electrocardiogram: application of an AI algorithm to an electrocardiogram-enabled Digital Stethoscope
Open accessAbstract
Aims: Electrocardiogram (ECG)-enabled stethoscope (ECG-Scope) acquires a single-lead ECGs during cardiac auscultation and may facilitate real-time screening for pathologies not routinely identified by cardiac auscultation alone. We previously demonstrated an artificial intelligence (AI) algorithm can identify left ventricular dysfunction (LVSD) [defined as ejection fraction (EF) ≤ 40%] with an area under the curve (AUC) of 0.91 using a 12-lead ECG. Methods and results: One hundred patients referred for clinically indicated echocardiography were prospectively recruited. ECG-Scope recordings with the patient supine and sitting were obtained in multiple electrode locations at the time of the echocardiogram. The AI algorithm for the detection of LVSD was retrained using single leads from ECG-12 and validated against ECG-Scope to determine accuracy for low EF detection (≤35%, <40%, or <50%). We evaluated the algorithm with respect to body position and lead location. Amongst 100 patients (aged 61.3 ± 13.8; 61% male, BMI: 30.0 ± 5.4), eight had EF≤40%, and six had EF 40–50%. The best single recording position was V2 with the patient supine [AUC: 0.88 (CI: 0.80–0.97) for EF≤35%, 0.85 (CI: 0.75–0.95) for EF≤40%, and 0.81 (CI: 0.71–0.90) for EF < 50%]. When using an AI model to select the recording automatically, AUC was 0.91 (CI: 0.84–0.97) for EF≤35%, 0.89 (CI: 0.83–0.96) for EF≤40%, and 0.84 (CI: 0.73–0.94) for EF < 50%. Conclusion: An AI algorithm applied to an ECG-enabled stethoscope recording in standard auscultation positions reliably detected the presence of a low EF in this prospective study of patients referred for echocardiography. The ability to screen patients with a possible low EF during routine physical examination may facilitate rapid detection of LVSD.
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.
Integrity signals
Registry
Cites
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.
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 trained on clinical ECGs have been applied to wearable device ECGs, but have traditionally shown significantly lower performance on wearable device ECGs than on held-out clinical ECG test sets.
“Models trained on clinical ECGs have been applied to wearable device ECGs, but have traditionally shown significantly lower performance on wearable device ECGs than on held-out clinical ECG test sets14,15.”
From Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices (2023) · cites this paper as [15]
The Methods (Construction of neural network for use on single-lead electrocardiogram; page unavailable) confirm that a model trained on clinical 12-lead ECGs was adapted for single-lead use and report an AUC of 0.90 on the original clinical test set. The Results (Accuracy of single-lead digital stethoscope-enabled electrocardiogram; page unavailable) report an AUC of 0.91 for the optimal stethoscope ECG at the same EF threshold—not significantly lower performance. This study does not establish a broader historical trend. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe performance of models for detecting LVSD from portable device ECGs may degrade in the real-world setting, with lower performance than observed in the original single-lead derivatives of the clinical development studies.
“Consequently, the performance of models for detecting LVSD from portable device ECGs may degrade in the real-world setting, with lower performance than observed in the original single-lead derivatives of the clinical development studies14,15.”
From Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices (2023) · cites this paper as [15]
The Discussion (page unavailable) says poorer-quality stethoscope recordings may produce inaccurate predictions, supporting the possibility of degraded performance with portable-device ECGs. But the paper does not show a general real-world decline relative to the clinical derivation study: Methods reports an AUC of 0.90 for its original-cohort test, while Results reports an AUC of 0.91 for optimally selected stethoscope ECGs. The study was conducted in patients referred for echocardiography, not a routine real-world screening population. (LLM, conf=0.82)
Experimental — accuracy not yet measuredModels 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 [15]
The Methods section describes an automated algorithm that selects the highest-quality ECG recording from those acquired with a digital stethoscope. The Results section reports higher AUCs for that selection than for scores averaged across all leads. This supports the comparison for this device, but not the broader claim that wearable-device ECG models generally rely on such selection or that performance was evaluated on all collected ECGs without selection. (LLM, conf=0.86)
Experimental — accuracy not yet measuredModels demonstrate poorer performance when tested on all available wearable ECG data as opposed to selected high-quality subsets.
“as models demonstrate poorer performance when tested on all available wearable ECG data as opposed to selected high-quality subsets15.”
From Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices (2023) · cites this paper as [15]
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
Galloway, C. D., Valys, A. V., Shreibati, J. B., Treiman, D. L., Petterson, F. L., Gundotra, V. P., Albert, D. E., Attia, Z. I., Carter, R. E., Asirvatham, S. J., et al. (2019) · JAMA Cardiology · doi:10.1001/jamacardio.2019.0640 · Cited by 318 · see citing works
Self-citationThe Epidemiology of Asymptomatic Left Ventricular Systolic Dysfunction: Implications for Screening
Wang, T. J., Levy, D., Benjamin, E. J., & Vasan, R. S. (2003) · Annals of Internal Medicine · doi:10.7326/0003-4819-138-11-200306030-00012 · Cited by 229 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- [2]Attia ZI, Friedman PA, Noseworthy PA, Lopez-Jimenez F, Ladewig DJ, Satam G, Pellikka PA, Munger TM, Asirvatham SJ, Scott CG, Carter RE, Kapa S. Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ Arrhythm Electrophysiol 2019; 12: e007284. 31450977 PMC7661045
- [3]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. Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram. Nat Med 2019; 25: 70– 74. 30617318
- [5]Varma N, Marrouche NF, Aguinaga L, Albert CM, Arbelo E, Choi JI, et al HRS/EHRA/APHRS/LAHRS/ACC/AHA worldwide practice update for telehealth and arrhythmia monitoring during and after a pandemic. Circ Arrhythm Electrophysiol 2020; 13: e009007. 32692972 PMC7482618
- [6]Sprague HB, Ongley PA. The clinical value of phonocardiography. Circulation 1954; 9: 127– 34. 13116385
- [7]Orient JM. Sapira's Art & Scient of Bedside Diagnosis. Philadelphia: Lippincott Williams and Wilkins; 2009.
Cited by
Sorted by citations
Khunte, A., Sangha, V., Oikonomou, E. K., Dhingra, L. S., Aminorroaya, A., Mortazavi, B. J., Coppi, A., Brandt, C. A., Krumholz, H. M., & Khera, R. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00869-w · Cited by 95 · see citing works
Artificial Intelligence–Enabled Prediction of Heart Failure Risk From Single-Lead Electrocardiograms
Dhingra, L. S., Aminorroaya, A., Pedroso, A. F., Khunte, A., Sangha, V., McIntyre, D., Chow, C. K., Asselbergs, F. W., Brant, L. C. C., Barreto, S. M., et al. (2025) · JAMA Cardiology · doi:10.1001/jamacardio.2025.0492 · Cited by 65 · see citing works
Adedinsewo, D. A., Morales-Lara, A. C., Afolabi, B. B., Kushimo, O. A., Mbakwem, A. C., Ibiyemi, K. F., Ogunmodede, J. A., Raji, H. O., Ringim, S. H., Habib, A. A., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03243-9 · Cited by 63 · see citing works
Self-citationBjerkén, L. V., Rønborg, S. N., Jensen, M. T., Ørting, S. N., & Nielsen, O. W. (2022) · Heart Failure Reviews · doi:10.1007/s10741-022-10283-1 · Cited by 50 · see citing works
- Authors
- Attia, Z. I., Dugan, J., Rideout, A., Maidens, J. N., Venkatraman, S., Guo, L., Noseworthy, P. A., Pellikka, P. A., Pham, S. L., Kapa, S., Friedman, P. A., & Lopez-Jimenez, F.
- Affiliations
- Mayo Clinic (US)
- Eko Health, Inc. (United States) (US)
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine , Rochester, MN , USA
- ORCID
- Venue
- European Heart Journal - Digital Health
- Publisher
- Oxford University Press (OUP)
- Published
- 2022-05-23
- Volume
- 3
- Issue
- 3
- Pages
- 373-379
- ISSN
- 2634-3916 (ISSN-L)
- PMC
- PMC9708035
- OpenAlex
- W4281287149
- Cited by
- 46
- References
- 2
- Citations by year
- 2026: 9 · 2025: 17 · 2024: 12 · 2023: 5 · 2022: 3
- FWCI
- 6.44
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- European Heart Journal - Digital Health (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Funders
- Mayo Clinic
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- left ventricular dysfunction, reduced ejection fraction, single-lead ECG, artificial intelligence algorithms, cardiac auscultation, posture, automated screening, echocardiography referral, left ventricular systolic dysfunction
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
