AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts

U-Sleep-style U-Net encoder/decoder (12 enc + 12 dec blocks) with 13 channel-attention modules mid-network, so it takes any number and mix of EEG/EOG channels in one forward pass (≈3.16 M params, +1.4 % over U-Sleep). Trained on 30-s labels but pools output at inference down to 128 Hz (0.008 s) for high-resolution hypnograms. Data: 28 public datasets, 20,589 nights (~200k h); 13 in-distribution sets for train/val/test, 15 held out (8 for 30-s staging, 7 for high-res analysis). Splits follow U-Sleep.

• Form factor: clinical

Sleep is essential for health, yet studying its dynamics requires manual sleep staging, a labor-intensive step in research and clinical care. Across centers, polysomnography (PSG) recordings are traditionally scored in 30-s epochs for pragmatic, not physiological, reasons and vary in electrode count, montage, and subject characteristics. These constraints challenge harmonized multi-center studies and the discovery of robust biomarkers on shorter timescales. We present AnySleep, a deep neural network that scores sleep from any electroencephalography (EEG) or electrooculography (EOG) data at adjustable temporal resolutions. We trained and validated the model on over 20,000 overnight recordings (>200,000 h of EEG and EOG) from 28 datasets across multiple clinics to promote robust generalization across sites. The model attains state-of-the-art performance and surpasses or equals established baselines at 30-s epochs. Performance improves with more channels, yet remains strong when EOG is absent, or only EOG or single EEG derivations (frontal, central, or occipital) are available. On sub-30-s timescales, the model captures short wake intrusions consistent with arousals and improves the prediction of pathophysiological conditions (obstructive sleep apnea, narcolepsy type 1, insomnia) over 30-s scoring. We make the model publicly available to facilitate large-scale studies with heterogeneous electrode setups and accelerate biomarker discovery in sleep.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

• Cleveland Family Study (CFS)NSRR family sleep-apnea PSG2,284 subjects · PPG · PSG
• MESA SleepNSRR polysomnography + wrist actigraphy (Multi-Ethnic Study of Atherosclerosis)2,237 subjects · PPG · ECG · IMU
• MrOS Sleep Study (Osteoporotic Fractures in Men, NSRR)ECG · SpO₂ · Resp
• Sleep Heart Health Study (SHHS, NSRR)6,441 subjects · ECG · SpO₂ · Resp
• Sleep-EDF Database Expanded (PhysioNet)Resp · Temp · EEG

• AnySleep (FH Aachen; channel-agnostic EEG/EOG sleep stager, npj Digit Med 2026)cnnEEGEOG2026 · Open weights