CoChat
Sign Up
Cited by 19ECG Monitoring and AnalysisCardiomyopathy and Myosin StudiesArtificial Intelligence in Healthcare and Education

Real-World Artificial Intelligence-Based Electrocardiographic Analysis to Diagnose Hypertrophic Cardiomyopathy

Open access
Desai, Milind Y., Jadam, Shada, Abusafia, Mohammed, Rutkowski, Katy, Ospina, Susan, Gaballa, Andrew, Sultana, Sanaa, Thamilarasan, Maran +2 more·2025·JACC: Clinical Electrophysiology
DOI 10.1016/j.jacep.2025.02.024
Open this paper in CoChat — free account

Abstract

BACKGROUND: There is an emerging interest in artificial intelligence-enhanced 12-lead electrocardiogram (AI-ECG) in detection of hypertrophic cardiomyopathy (HCM). OBJECTIVES: This study describes the initial real-world experience of using AI-ECG (Viz-HCM, developed using a convolutional neural network trained algorithm) in our center. METHODS: All patients undergoing 12-lead electrocardiograms at Cleveland Clinic, Cleveland, Ohio, between February 19, 2024, and November 1, 2024, were prospectively analyzed for potential HCM using AI-ECG. The numbers of patients flagged for potential HCM were recorded. Presence of confirmed HCM, a new diagnosis of HCM following AI-ECG assessment (with a negative prior clinical evaluation), and alternative non-HCM diagnosis were recorded. Assessment of AI-ECG diagnostic performance was done using various HCM probability thresholds (≥0.95, ≥0.90, and ≥0.85). RESULTS: Of 103,492 electrocardiograms analyzed in 45,873 patients, AI-ECG flagged potential HCM in 1,265 (2.7%) unique patients. Of these, 511 (40.4%) had confirmed HCM, 63 (5%) had new HCM diagnosis, and 691 (54.6%) had an alternate diagnosis. HCM probability threshold of ≥0.85 provided the highest sensitivity (95%) for diagnosis of HCM with high specificity and accuracy (all >98%). The positive predictive value was the highest (66%) at the cutoff ≥0.95 but with a lower sensitivity at 50%. The AI-ECG algorithm performed similarly in both men and women, and was more sensitive in individuals <50 years but more specific in individuals ≥50 years. CONCLUSIONS: Prospective real-world application of the AI-ECG algorithm to detect HCM was associated with a high degree of accuracy, varying with the chosen probability threshold. It also enabled the identification of 5% of patients with no prior HCM diagnosis.

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/j.jacep.2025.02.024

Cites

21 of 21 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?

  • HCM has shown consistently high discrimination, international external validation, and early real-world implementation, making it one of the more reproducible structural AI-ECG targets.

    “HCM has shown consistently high discrimination, international external validation, and early real-world implementation, making it one of the more reproducible structural AI-ECG targets.”

    From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [28]

    The Discussion reports an external-dataset AUC of 0.975, and the Conclusions describe real-world clinical implementation for HCM detection at one center. Our copy does not establish international external validation or compare HCM with other structural AI-ECG targets for reproducibility; the Discussion cautions that this single-center study may not generalize across geographic settings. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • AI-ECG-based HCM alerts can be deployed in routine care, although positive results still require clinical correlation and confirmatory imaging.

    “More recent real-world implementation studies suggest that AI-ECG-based HCM alerts can be deployed in routine care, although positive results still require clinical correlation and confirmatory imaging [28].”

    From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [28]

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
Desai, M. Y., Jadam, S., Abusafia, M., Rutkowski, K., Ospina, S., Gaballa, A., Sultana, S., Thamilarasan, M., Xu, B., & Popovic, Z. B.
Affiliations
Cleveland Clinic (US)
Corresponding author
Desai, Milind Y.
ORCID
Venue
JACC: Clinical Electrophysiology
Publisher
Elsevier BV
Published
2025-06
Volume
11
Issue
6
Pages
1324-1333
ISSN
2405-500X (ISSN-L)
DOI
10.1016/j.jacep.2025.02.024
OpenAlex
W4408527974
Cited by
19
References
21
Citations by year
2026: 12 · 2025: 7
FWCI
13.37
Type
journal article
Language
en
Open access
Licence
Locations
  • JACC. Clinical electrophysiology (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiomyopathy and Myosin Studies
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
hypertrophic cardiomyopathy, artificial intelligence, 12-lead ECG, convolutional neural networks, automated diagnosis, diagnostic accuracy, threshold probability, sex differences, age differences, real-world applications
MeSH terms
Adult, Aged, Algorithms, Artificial Intelligence, Cardiomyopathy, Hypertrophic, Electrocardiography, Female, Humans, Male, Middle Aged, Prospective Studies, Sensitivity and Specificity, Neural Networks, Computer

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