PaperarXiv:2611.07717
Pediatric ECG foundation model via adult-to-pediatric fine-tuning (Cao, Xu, Li et al., arXiv 2611.07717)
arXiv 2611.07717v1 (submitted 2026-11-05); 20 pages
TL;DR
Adult ECG foundation model adapted to pediatric 12-lead ECGs (0–18 y) by comparing direct transfer, pediatric fine-tuning, and training from scratch under the same 1-D architecture (net1d.py). Preprocessing: 500 Hz, 50 Hz notch, 0.5–75 Hz band-pass, per-lead Z-score.
- Form factor: 12-lead clinical ECG
Abstract
Pediatric electrocardiogram (ECG) interpretation is complicated by age-dependent electrophysiological changes that limit direct transfer of adult AI models. We asked whether an adult ECG foundation model could be adapted to pediatric ECGs. Using 339,563 12-lead ECGs from 238,189 children, we compared direct application, pediatric fine-tuning, and training from scratch under an identical architecture. Direct transfer was poor (mean AUC 0.8256). Fine-tuning reached 0.9695, above de novo training (0.9661), and attained 0.9079 using only 1% of training data. On 10,999 external ECGs, fine-tuning achieved a mean AUC of 0.9385 across 30 labels. It generalized to age regression (MAE 1.12 years) and congenital heart disease classification (AUC 0.9562). Across 17 clinicians and 100 cases, diagnostic accuracy rose from 56.8% to 65.4% (p < 0.001) and did not decline when AI erred. Adult ECG foundation models require pediatric adaptation; fine-tuning offers a data-efficient route to scalable pediatric ECG AI.
Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)
Results on ChatPPG leaderboards · 2
All leaderboards| Leaderboard | Method | Result | Rank |
|---|---|---|---|
| zju-pediatric-ecg-external-10999 AUROCEcg diagnosis | Pediatric ECG FMvia model Pediatric ECG FM | 0.9385AUROC, higher is better | #1 of 1 |
| zju-pediatric-ecg-internal AUROCEcg diagnosis | Pediatric ECG FMvia model Pediatric ECG FM | 0.9695AUROC, higher is better | #1 of 1 |
No row is credited to the paper itself; 2 more belong to models it introduces or evaluates. Ranks apply within each leaderboard only, as reported by the source.
Tasks & signals
Tasks
Signals
Keywords
Models
How it works
Cite this paper
Pediatric ECG foundation model via adult-to-pediatric fine-tuning (Cao, Xu, Li et al., arXiv 2611.07717). (2026). arXiv 2611.07717v1. https://arxiv.org/abs/2611.07717
@misc{caopediatricecgf2026pediatric,
title = {{Pediatric ECG foundation model via adult-to-pediatric fine-tuning (Cao, Xu, Li et al., arXiv 2611.07717)}},
year = {2026},
howpublished = {arXiv 2611.07717v1},
eprint = {2611.07717},
archivePrefix = {arXiv}
}Added to the ChatPPG research hub
