Method and device for identifying brain region related to awakening and perceiving state based on electroencephalogram feature attribution

By constructing and training a classification model and combining feature attribution algorithms, brain regions related to awakening and awareness state are identified, which solves the problem of difficulty in identifying brain regions separately in the existing technology, improves the accuracy of recognition, and provides assistance in the design of related diagnosis and treatment equipment.

CN119679364AActive Publication Date: 2025-03-25WUHAN UNIV
4 Cites 0 Cited by

Patent Information

Application Number
CN202411631021.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-15
Publication Date
2025-03-25
Estimated Expiration
2044-11-15

AI Technical Summary

Technical Problem

The prior art is difficult to identify brain regions related to awakening and awareness states separately, and fails to effectively analyze the interaction between nonlinear correlation and multiple features.

Method used

By obtaining the EEG data sets under different awakening awareness states, preprocessing and feature extraction, constructing classification models and training, combining feature attribution algorithms to calculate the importance of brain region feature groups, and determining the brain regions related to awakening or awareness states.

Benefits of technology

The distinction between awakening and awareness state is achieved, and the brain areas related to awakening and awareness state are identified, which improves the accuracy of recognition and provides assistance in the design of diagnostic and treatment equipment in the field of anesthesia or consciousness disorders.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a method and a device for identifying brain regions related to awakening and perceiving states based on electroencephalogram feature attribution. The method comprises the following steps: acquiring electroencephalogram data sets in different awakening and perceiving states; performing preprocessing and feature extraction to obtain an electroencephalogram feature data set; a classification model is constructed, the classification model is trained through the electroencephalogram feature data set and the corresponding state labels, and a trained awakening state classification model and a trained perceiving state classification model are obtained; obtaining target electroencephalogram data, and performing preprocessing and feature extraction to obtain target electroencephalogram features; grouping to obtain a plurality of brain region feature groups, calculating the importance between each brain region feature group and the awakening state classification model or the perceived state classification model through a feature attribution algorithm, and determining the brain region corresponding to the brain region feature group as the brain region related to the awakening state or the perceived state based on the importance. According to the method, the awakening state and the perceiving state of the subject can be distinguished, and the brain regions related to the awakening state and the perceiving state can be recognized.
Need to check novelty before this filing date? Find Prior Art