Study on Prediction and Biomarker Exploration of Sleep Disorders Using Physiological Data

Development of a Predictive Model and Biomarker Exploration for Sleep Disorders Based on Multidimensional Physiological Time-Series Data - MD-PBE Study

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000060746

Enrollment

4400

Registered

2026-02-27

Start date

2026-01-20

Completion date

Unknown

Last updated

2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Sleep Disorders

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Individuals whose multidimensional physiological time-series data, including PSG and MSLT recordings, were obtained at National Center Hospital, National Center of Neurology and Psychiatry between January 2013 and January 31, 2026.

Exclusion criteria

Exclusion criteria: Individuals who have declined the use or disclosure of their medical information. For minors, those who have declined such use or disclosure, or whose legally authorized representatives have declined on their behalf.

Design outcomes

Primary

Measure	Time frame
Cross-validated predictive performance of sleep disorder estimation models (accuracy, sensitivity, specificity, area under the curve (AUC), mean absolute error (MAE), and root mean square error (RMSE).	—

Secondary

Measure	Time frame
Quantification of the contribution of each physiological signal and temporal segment to model predictions using feature attribution analysis.	—

Countries

Japan

Contacts

Public ContactYusuke Fukazawa

National Center of Neurology and Psychiatry Department of Sleep-Wake Disorders, National Institute of Mental Health

ukazawa@sophia.ac.jp042-346-2014

Outcome results