This is an online demo for automated sleep staging of paediatric polysomnography (PSG) in children aged 2-18 years. It utilises trained machine learning models to classify all stages of sleep (including Stage Wake, N1, N2, N3, and REM) using EEG, EOG, and Chin EMG derivations. Sleep staging data, including detailed per-epoch analysis, may be visualised through this platform and downloaded in various formats for analysis.

Learn more about the machine learning models used, including peer-reviewed validation studies.

Substantial emphasis is placed on explainable AI. Measures of uncertainty, global and local explanations, and data visualisation accompany ML-generated predictions. Furthermore, models include clinically relevant features that are familiar to sleep paediatricians.

Accepted uploads are EDF files exported from PSG recording software and must include EEG, EOG, and Chin EMG. EDF files should be fully anonymised prior to upload. All pre-processing of EEG data is handled automatically by this platform.

No suitable PSG data on-hand? Sample open source PSG data are available to try.

This service is currently for academic and non-commercial purposes only. It is not approved for clinical use.

Models were trained and evaluated on PSG of children aged 2-18 years. Performance cannot be guaranteed in children aged less than two years, children with atypical EEG, for poor quality recordings, or in adults.