Polysomnography harmonization schemes: A multi-institutional sleep research resource

06/11/2026

AI Summary

Institutional structural heterogeneity in polysomnography data complicates multi-centre integration, increases preprocessing burden and limits reproducible large-scale algorithm validation.
A set of harmonization schemas formalises unified PSG structural specifications aligned with clinical guidelines to integrate biosignals, derived sleep parameters and demographics.
When applied across eight public datasets the schemas produced stable demographic and clinical distributions and enabled consistent algorithm evaluation and comparison.

TL;DR (AI Generated)

As artificial intelligence applications in sleep research expand, structural heterogeneity in PSG data across institutions complicates multi-center integration, increases preprocessing burden, and limits reproducible large-scale algorithm validation.

These schemas systematically integrate heterogeneous biosignals, derived sleep parameters, and demographic features to achieve consistent attribute selection and uniform preprocessing across datasets.

By addressing schema-level interoperability, the proposed framework facilitates consistent algorithm evaluation and comparison and provides a structured reference for reproducible, large-scale sleep research.

Basic summary

PLoS One. 2026 Nov 5;21(11):e0361116. doi: 10.1371/journal.pone.0361116. eCollection 2026.

ABSTRACT

Sleep disorders are associated with cardiovascular diseases and cognitive decline worldwide, highlighting the need for effective therapeutic strategies. Polysomnography (PSG) is the gold standard diagnostic tool for sleep disorders. However, long examination times, high costs, specialized biosignal equipment and controlled settings requirements hinder large-scale data collection. As artificial intelligence applications in sleep research expand, structural heterogeneity in PSG data across institutions complicates multi-center integration, increases preprocessing burden, and limits reproducible large-scale algorithm validation. We investigated biosignals, sleep parameters, and demographic features from eight publicly available PSG datasets. A set of schemas for PSG harmonization is proposed to formalize unified structural specifications aligned with established clinical guidelines. These schemas systematically integrate heterogeneous biosignals, derived sleep parameters, and demographic features to achieve consistent attribute selection and uniform preprocessing across datasets. When applied to construct an integrated dataset, the schemas demonstrated stable demographic and clinical distributions through repeated sampling. By addressing schema-level interoperability, the proposed framework facilitates consistent algorithm evaluation and comparison and provides a structured reference for reproducible, large-scale sleep research.

PMID:42986902 | DOI:10.1371/journal.pone.0361116

Document this CPD