cs.AINov 5, 2026

Pediatric ECG foundation model via adult-to-pediatric fine-tuning: downstream tasks and clinical evaluation

Authors: Yu Cao, Haiyan Xu, Xiaohan Li, Jian Yang, Yuqing Feng, Wei Wang, Haomin Li

Organizations: Clinical Data Center, Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescent's Health and Diseases, China · ECG Department, Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescent's Health and Diseases, China · The College of Biomedical Engineering and Instrument Science, Zhejiang University, China · Department of Cardiology, Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescent's Health and Diseases, China

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.

Explore similar work

CardsList
  1. Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignment

    May 1, 2026Xinran Liu, Yuwen Li, Hongxiang Gao +4ElectrocardiographyCross-Modal Alignment

  2. Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment

    Jul 17, 2026Xinran Liu, Yuwen Li, Hongxiang Gao +4ElectrocardiographyCross-Modal Alignment

  3. Domain-Adapted Fine-Tuning of ECG Foundation Models for Multi-Label Structural Heart Disease Screening

    Apr 25, 2026Duc N. Do, Minh N. Do, Dang Nguyen +14Unsupervised Domain AdaptationEchocardiography