arXiv cs.AI· Yu Cao, Haiyan Xu, Xiaohan Li, Jian Yang, Yuqing Feng, Wei Wang, Haomin Li·· 4 小时前AI 评分44
成人 ECG 基础模型微调用于儿科心电图：下游任务与临床评估研究
Pediatric ECG foundation model via adult-to-pediatric fine-tuning: downstream tasks and clinical evaluation
AI 导读
一项 arXiv 研究将成人 ECG 基础模型微调适配儿科心电图，使用 238,189 名儿童的 339,563 份 12 导联 ECG 数据。微调后平均 AUC 达 0.9695，优于直接迁移（0.8256）和从头训练（0.9661），仅用 1% 训练数据即可达 0.9079；在 10,999 份外部 ECG 上跨 30 个标签平均 AUC 为 0.9385。
正文 · 原文
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.
| Comments: | 20 pages,3 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07717 [cs.AI] |
| (or arXiv:2611.07717v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07717 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haomin Li [view email]
[v1]
Thu, 5 Nov 2026 09:36:44 UTC (1,517 KB)
来源：arXiv cs.AI · arxiv.org