Back

Foundation models for generalizable electrocardiogram interpretation: comparison of supervised and self-supervised electrocardiogram foundation models

2025-03-05 cardiovascular medicine Title + abstract only
View on medRxiv
Show abstract

BackgroundThe 12-lead electrocardiogram (ECG) remains a cornerstone of cardiac diagnostics, yet existing artificial intelligence (AI) solutions for automated interpretation often lack generalizability, remain closed-source, and are primarily trained using supervised learning, limiting their adaptability across diverse clinical settings. To address these challenges, we developed and compared two open-source foundational ECG models: DeepECG-SSL, a self-supervised learning model, and DeepECG-SL, a ...

Predicted journal destinations

1
European Heart Journal - Digital Health
15 training papers
#1 17.8%
2
Scientific Reports
701 training papers
Top 8% 14.7%
3
Circulation
37 training papers
Top 1% 9.0%
4
npj Digital Medicine
85 training papers
Top 2% 7.8%
5
Journal of the American Heart Association
92 training papers
Top 6% 6.0%
6
Frontiers in Cardiovascular Medicine
33 training papers
Top 4% 5.0%
7
Circulation: Genomic and Precision Medicine
30 training papers
Top 3% 4.2%
8
PLOS Digital Health
88 training papers
Top 7% 3.9%
9
Heart Rhythm
16 training papers
Top 2% 3.1%
10
Nature Communications
483 training papers
Top 32% 2.8%
11
eLife
262 training papers
Top 21% 1.9%
12
PLOS ONE
1737 training papers
Top 92% 1.9%
13
Computers in Biology and Medicine
39 training papers
Top 4% 1.9%
14
The American Journal of Cardiology
15 training papers
Top 4% 1.9%
15
Open Heart
18 training papers
Top 4% 1.9%
16
Frontiers in Physiology
18 training papers
Top 1% 1.3%
17
BMJ Open
553 training papers
Top 63% 0.9%
18
Hypertension
20 training papers
Top 5% 0.9%
19
Nature Genetics
72 training papers
Top 9% 0.9%
20
Atherosclerosis
16 training papers
Top 5% 0.7%
21
PLOS Computational Biology
141 training papers
Top 14% 0.7%
22
EBioMedicine
21 training papers
Top 1% 0.7%
23
Nature
58 training papers
Top 10% 0.7%
24
Nature Medicine
88 training papers
Top 25% 0.5%