Reproduce “Pediatric ECG foundation model via adult-to-pediatric fine-tuning: downstream tasks and clinical evaluation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yu Cao, Haiyan Xu, Xiaohan Li, Jian Yang, Yuqing Feng, Wei Wang, Haomin Li
The authors adapt an adult-pretrained ECG model for pediatric diagnosis by fine-tuning it on children’s recordings and comparing it with direct transfer and training from scratch. On 33 shared labels, mean AUROC rose from 0.8256 to 0.9662 after fine-tuning, versus 0.9638 from scratch. Fine-tuning also reached 0.9079 with 1% of pediatric data, but external validation was in another Chinese cohort.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.