PREDiction of Different Variants of Sleep Stages for the Diagnosis Support of Chronic Insomnia and Epilepsy

The objective of this study is to develop and validate deep learning algorithms for automated sleep stage and sub-stage classification using overnight polysomnography data. The models will be trained and evaluated on at least three independent datasets to ensure generalizability. \- Primary Outcome Measure : Accuracy of deep learning-based sleep stage classification compared to expert manual scoring (\>80% target agreement), evaluated across multiple polysomnography datasets including AP-HP (Assistance Publique - Hôpitaux de Paris) data. This is a retrospective, observational study.

NCT Number	NCT07547501
Lead Sponsor	Assistance Publique - Hôpitaux de Paris Collaborators: Idiap Research Institute, Switzerland
Conditions	Chronic Insomnia, Epilepsy, Sleep Disorders
Enrollment	1,500 participants
Start Date	2026-06
Primary Completion	2027-03 (estimated)
Study Completion	2027-03 (estimated)
Updated on ClinicalTrials.gov	2026-04-29