A method and system for guiding sleep disorder treatment using fnirs

CN122272013APending Publication Date: 2026-06-26XIA MEN SHI BEI YANG NAO JI JIE KOU YU ZHI HUI JIAN KANG CHUANG XIN YAN JIU YUAN
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIA MEN SHI BEI YANG NAO JI JIE KOU YU ZHI HUI JIAN KANG CHUANG XIN YAN JIU YUAN
Filing Date
2026-02-10
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing fNIRS-based sleep intervention techniques cannot achieve real-time brain oxygenation status decoding and multimodal arbitration during natural sleep, resulting in insufficient personalization and real-time adaptability of treatment.

Method used

By wearing a multimodal sensing device while the user is asleep, the system integrates motion, preliminary EEG and ambient light analysis, processes fNIRS and EEG signals in real time, generates an immediate treatment objective function, and optimizes treatment parameters based on a Gaussian process model of the user's historical response data to achieve closed-loop adaptive regulation.

Benefits of technology

It enables precise intervention during natural sleep, enhances the personalization and real-time adaptability of neuromodulation of sleep disorders, and overcomes the shortcomings of traditional offline assessment and fixed parameter intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure FT_1
    Figure FT_1
Patent Text Reader

Abstract

This invention discloses a method and system for guiding sleep disorder treatment using fNIRS, relating to the field of medical technology. The method includes: intelligently sensing a user's pre-sleep state using multimodal sensing devices and initiating full-bandwidth signal acquisition; parallel processing of fNIRS and EEG signals to extract cerebral blood oxygenation characteristics and sleep stage information in real time; generating a quantified, real-time treatment objective function based on the multimodal state through dynamic arbitration; calling a user-specific Gaussian process model and optimization algorithm to calculate and output personalized recommended treatment parameters; driving an execution unit to implement intervention, and collecting post-intervention signals for effect evaluation and model updating, forming a closed-loop adaptive control system of "perception-decision-intervention-learning". This invention solves the problem of existing technologies' difficulty in achieving real-time brain state decoding and precise intervention during natural sleep, improving the personalization and real-time adaptability of treatment.
Need to check novelty before this filing date? Find Prior Art