Sleep foundation models have recently demonstrated strong performance on in-domain polysomnography tasks, including sleep staging, apnea detection, and disease risk prediction. In this work, we investigate whether sleep biosignals can serve as an effective pretraining distribution for learning representations that transfer beyond sleep to adjacent domains. Following sleep foundation models, we perform sleep-only multimodal contrastive pretraining (with a leave-one-out objective) and evaluate transfer to non-sleep EEG and ECG, two well-benchmarked biosignal modalities with heterogeneous datasets and clinically meaningful downstream tasks. Across eight downstream tasks spanning multiple EEG and ECG datasets, sleep pretraining consistently improves performance relative to training from scratch. Moreover, on several tasks, we achieve performance competitive with or surpassing prior specialized state-of-the-art and foundation models.
@article{arxiv.2605.02500,
title = {Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks},
author = {William Lehn-Schiøler and Magnus Ruud Kjær and Phillip Hempel and Magnus Guldberg Pedersen and Rahul Thapa and Bryan He and Nicolai Spicher and Andreas Brink-Kjaer and Lars Kai Hansen and Emmanuel Mignot},
journal= {arXiv preprint arXiv:2605.02500},
year = {2026}
}