Artificial Intelligence–Enhanced Electrocardiogram for the Early Detection of Cardiac Amyloidosis
Abstract
Objective To develop an artificial intelligence (AI)-based tool to detect cardiac amyloidosis (CA) from a standard 12-lead electrocardiogram (ECG). Methods We collected 12-lead ECG data from 2541 patients with light chain or transthyretin CA seen at Mayo Clinic between 2000 and 2019. Cases were nearest neighbor matched for age and sex, with 2454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with an internal validation set (n=999; 20%) and a randomly selected holdout testing set (n=999; 20%). We performed experiments using single-lead and 6-lead ECG subsets. Results The area under the receiver operating characteristic curve (AUC) was 0.91 (CI, 0.90 to 0.93), with a positive predictive value for detecting either type of CA of 0.86. By use of a cutoff probability of 0.485 determined by the Youden index, 426 (84%) of the holdout patients with CA were detected by the model. Of the patients with CA and prediagnosis electrocardiographic studies, the AI model successfully predicted the presence of CA more than 6 months before the clinical diagnosis in 59%. The best single-lead model was V5 with an AUC of 0.86 and a precision of 0.78, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.90 and a precision of 0.85. Conclusion An AI-driven ECG model effectively detects CA and may promote early diagnosis of this life-threatening disease.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
An AI-ECG model was developed for early detection of cardiac amyloidosis.
“Grogan et al. developed an AI-ECG model for early detection of cardiac amyloidosis, supporting the concept that infiltrative myocardial disease produces subtle ECG features that can be recognized computationally [32].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [32]
Infiltrative myocardial disease produces subtle ECG features that can be recognized computationally.
“Grogan et al. developed an AI-ECG model for early detection of cardiac amyloidosis, supporting the concept that infiltrative myocardial disease produces subtle ECG features that can be recognized computationally [32].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [32]
AI-ECG may help enrich the population selected for further evaluation with echocardiography, cardiac magnetic resonance imaging, nuclear scintigraphy, or serum and urine testing when clinical suspicion is present.
“AI-ECG may therefore help enrich the population selected for further evaluation with echocardiography, cardiac magnetic resonance imaging, nuclear scintigraphy, or serum and urine testing when clinical suspicion is present.”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [32]
The low prevalence of individual structural heart diseases limits the potential implementation of models for broad screening because of the low PPVs of the proposed models.
“While these models provide a strong foundation for the role of ECG-based detection of SHDs, the low prevalence of these individual diseases, their potential implementation for broad screening is limited by the low PPVs of the proposed models.10-12,16,32-34”
From Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images (2025) · cites this paper as [34]
Prior studies have reported the use of deep learning on 12-lead ECGs to detect individual structural cardiovascular conditions, including LVSD, hypertrophic cardiomyopathy, cardiac amyloidosis, and aortic stenosis.
“Prior studies have reported the use of deep learning on 12-lead ECGs to detect individual structural cardiovascular conditions, including LVSD,10,11,13 hypertrophic cardiomyopathy,16,32,33 cardiac amyloidosis,34,35 aortic stenosis,12 among others.15,35-37”
From Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images (2025) · cites this paper as [34]
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
References 26 · Cited by 166
- Authors
- Grogan, M., Lopez-Jimenez, F., Cohen-Shelly, M., Dispenzieri, A., Attia, Z. I., Abou Ezzedine, O. F., Lin, G., Kapa, S., Borgeson, D. D., Friedman, P. A., & Murphree, D. H.
- Affiliations
- Mayo Clinic (US)
- Corresponding author
- Grogan, Martha
- ORCID
- Venue
- Mayo Clinic Proceedings
- Publisher
- Elsevier BV
- Published
- 2021-11
- Volume
- 96
- Issue
- 11
- Pages
- 2768-2778
- ISSN
- 0025-6196 (ISSN-L)
- OpenAlex
- W3174081426
- Cited by
- 166
- References
- 26
- Citations by year
- 2026: 50 · 2025: 35 · 2024: 47 · 2023: 18 · 2022: 13 · 2021: 3
- FWCI
- 6.36
- Type
- journal article
- Language
- en
- Update notices
- erratum (2023-01-01)
- Open access
- closed
- Locations
- Mayo Clinic Proceedings (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Amyloidosis: Diagnosis, Treatment, Outcomes
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- cardiac amyloidosis, electrocardiogram, artificial intelligence, deep neural network, early diagnosis, AL amyloidosis, transthyretin amyloidosis, 12-lead ECG, single-lead ECG, bipolar leads
- MeSH terms
- Artificial Intelligence, Electrocardiography, Female, Humans, Male, Middle Aged, Cardiomyopathies, Predictive Value of Tests, Retrospective Studies, United States, Neural Networks, Computer, Area Under Curve, Amyloid Neuropathies, Familial, Early Diagnosis, Time-to-Treatment
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
