Artificial Intelligence Applied to Nocturnal and Daytime Neurophysiology and Actigraphy in Central Disorders of Hypersomnolence.

Authors

Mads Olsen, Tugdual Adam, Brian Tracey, Lucie Barateau, Dmitri Volfson, Yves Dauvilliers

Published in

Sleep medicine clinics. Volume 21. Issue 4. Pages 521-533. Epub Sep 30, 2026.

Abstract

Central disorders of hypersomnolence including narcolepsy type 1 and 2 (NT1 and NT2) and idiopathic hypersomnia (IH), are characterized by excessive daytime sleepiness and assessed using complex multimodal data (polysomnography, multiple sleep latency test, actigraphy, biomarkers). These features make hypersomnolence disorders well suited for machine learning approaches. Recent advances show high diagnostic performance for NT1, but lower accuracy for NT2 and IH due to heterogeneity and lack of biomarkers. Unsupervised methods challenge current classifications. This review summarizes artificial intelligence applications, highlights key limitations (small datasets, diagnostic instability), and outlines future directions, emphasizing multimodal, longitudinal, and self-supervised approaches toward data-driven phenotyping.

PMID:
42977361
Bibliographic data and abstract were imported from PubMed on 04 Nov 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.