CoChat
Sign Up
Cited by 167ECG Monitoring and AnalysisArtificial Intelligence in HealthcareArtificial Intelligence in Healthcare and Education

Point-of-Care Screening for Heart Failure with Reduced Ejection Fraction Using Artificial Intelligence during ECG-Enabled Stethoscope Examination in London, UK: A Prospective, Observational, Multicentre Study

Open access
Bachtiger, Patrik, Petri, Camille F, Scott, Francesca E, Ri Park, Se, Kelshiker, Mihir A, Sahemey, Harpreet K, Dumea, Bianca, Alquero, Regine +13 more·2022·The Lancet Digital Health
DOI 10.1016/s2589-7500(21)00256-9PMC PMC8789562
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied to a single-lead ECG, recorded during ECG-enabled stethoscope examination, to validate a potential point-of-care screening tool for LVEF of 40% or lower. METHODS: We conducted an observational, prospective, multicentre study of a convolutional neural network (known as AI-ECG) that was previously validated for the detection of reduced LVEF using 12-lead ECG as input. We used AI-ECG retrained to interpret single-lead ECG input alone. Patients (aged ≥18 years) attending for transthoracic echocardiogram in London (UK) were recruited. All participants had 15 s of supine, single-lead ECG recorded at the four standard anatomical positions for cardiac auscultation, plus one handheld position, using an ECG-enabled stethoscope. Transthoracic echocardiogram-derived percentage LVEF was used as ground truth. The primary outcome was performance of AI-ECG at classifying reduced LVEF (LVEF ≤40%), measured using metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with two-sided 95% CIs. The primary outcome was reported for each position individually and with an optimal combination of AI-ECG outputs (interval range 0-1) from two positions using a rule-based approach and several classification models. This study is registered with ClinicalTrials.gov, NCT04601415. FINDINGS: Between Feb 6 and May 27, 2021, we recruited 1050 patients (mean age 62 years [SD 17·4], 535 [51%] male, 432 [41%] non-White). 945 (90%) had an ejection fraction of at least 40%, and 105 (10%) had an ejection fraction of 40% or lower. Across all positions, ECGs were most frequently of adequate quality for AI-ECG interpretation at the pulmonary position (979 [93·3%] of 1050). Quality was lowest for the aortic position (846 [80·6%]). AI-ECG performed best at the pulmonary valve position (p=0·02), with an AUROC of 0·85 (95% CI 0·81-0·89), sensitivity of 84·8% (76·2-91·3), and specificity of 69·5% (66·4-72·6). Diagnostic odds ratios did not differ by age, sex, or non-White ethnicity. Taking the optimal combination of two positions (pulmonary and handheld positions), the rule-based approach resulted in an AUROC of 0·85 (0·81-0·89), sensitivity of 82·7% (72·7-90·2), and specificity of 79·9% (77·0-82·6). Using AI-ECG outputs from these two positions, a weighted logistic regression with l2 regularisation resulted in an AUROC of 0·91 (0·88-0·95), sensitivity of 91·9% (78·1-98·3), and specificity of 80·2% (75·5-84·3). INTERPRETATION: A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG-enabled stethoscope can detect LVEF of 40% or lower. These findings highlight the potential for inexpensive, non-invasive, workflow-adapted, point-of-care screening, for earlier diagnosis and prognostically beneficial treatment. FUNDING: NHS Accelerated Access Collaborative, NHSX, and the National Institute for Health Research.

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 · 10.1016/s2589-7500(21)00256-9

Cites

31 of 31 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 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 [14]

    The Methods (AI-ECG algorithm; page unavailable) describe a model trained on clinical 12-lead ECG data and tested using single-lead recordings from an ECG-enabled stethoscope. The Discussion (page unavailable) reports an internal 12-lead validation AUROC of 0.93, but says the study’s single-lead findings compare favourably with an external 12-lead validation AUROC of 0.82. The paper does not establish a traditional, statistically significant performance drop on wearable-device ECGs relative to held-out clinical ECG test sets. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • 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 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 [14]

    The Results report an AUROC of 0.85 for the best single-lead stethoscope position in this prospective study. The Discussion gives a higher AUROC of 0.93 for the original internal validation, but that comparison used 12-lead ECGs, not the original single-lead derivatives specified in the claim. It also says the study’s single-lead findings compare favourably with a separate external 12-lead validation. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

  • A deep-learning model applied to single-lead ECGs obtained during ECG-enabled stethoscope examination could identify patients with a left ventricular ejection fraction of 40% or lower in a prospective multicenter study.

    “Separately, a prospective multicenter study showed that a deep-learning model applied to single-lead ECGs obtained during examination with an ECG-enabled stethoscope could identify patients with a left ventricular ejection fraction of 40% or lower [64].”

    From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [64]

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

Cited by

Sorted by citations

Related

Authors
Bachtiger, P., Petri, C. F., Scott, F. E., Ri Park, S., Kelshiker, M. A., Sahemey, H. K., Dumea, B., Alquero, R., Padam, P. S., Hatrick, I. R., Ali, A., Ribeiro, M., Cheung, W.-S., Bual, N., Rana, B., Shun-Shin, M., Kramer, D. B., Fragoyannis, A., Keene, D., Plymen, C. M., & Peters, N. S.
Affiliations
  • Imperial College London (GB)
  • Imperial College Healthcare NHS Trust (GB)
  • Beth Israel Deaconess Medical Center (US)
Corresponding author
Peters, Nicholas S
ORCID
Venue
The Lancet Digital Health
Publisher
Elsevier BV
Published
2022-02
Volume
4
Issue
2
Pages
e117-e125
ISSN
2589-7500 (ISSN-L)
DOI
10.1016/s2589-7500(21)00256-9
PMC
PMC8789562
OpenAlex
W4206756110
Cited by
167
References
31
Citations by year
2026: 40 · 2025: 48 · 2024: 46 · 2023: 18 · 2022: 14
FWCI
21.94
Type
journal article
Language
en
Open access
Licence
Locations
  • The Lancet Digital Health (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Spiral (Imperial College London) (submittedVersion, cc-by)
Funders
National Institute for Health Research
Topics
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
heart failure with reduced ejection fraction, point-of-care screening, artificial intelligence, single-lead ECG, convolutional neural networks, left ventricular ejection fraction, transthoracic echocardiography, cardiac auscultation, primary care, early diagnosis, model generalization, sex differences
MeSH terms
Aged, Artificial Intelligence, Electrocardiography, Female, United Kingdom, Heart Failure, Humans, Male, Middle Aged, Physical Examination, Prospective Studies, Neural Networks, Computer, Stethoscopes, Point-of-Care Systems

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