Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913086111219712 |
|---|---|
| author | Lehn-Schiøler, William Kjær, Magnus Ruud Hempel, Phillip Pedersen, Magnus Guldberg Thapa, Rahul He, Bryan Spicher, Nicolai Brink-Kjaer, Andreas Hansen, Lars Kai Mignot, Emmanuel |
| author_facet | Lehn-Schiøler, William Kjær, Magnus Ruud Hempel, Phillip Pedersen, Magnus Guldberg Thapa, Rahul He, Bryan Spicher, Nicolai Brink-Kjaer, Andreas Hansen, Lars Kai Mignot, Emmanuel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02500 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks Lehn-Schiøler, William Kjær, Magnus Ruud Hempel, Phillip Pedersen, Magnus Guldberg Thapa, Rahul He, Bryan Spicher, Nicolai Brink-Kjaer, Andreas Hansen, Lars Kai Mignot, Emmanuel Machine Learning Artificial Intelligence 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. |
| title | Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.02500 |