Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Schizophrenia Early Detection System Based on Graph Neural Network and Brain Network

A technology of schizophrenia and neural network, applied in the field of early detection of schizophrenia, to achieve the effect of improving recognition accuracy and accuracy

Active Publication Date: 2022-06-14
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The current diagnosis of schizophrenia mainly relies on the detection and identification of the symptoms described by medical staff after the clinical symptoms appear, which is highly subjective.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Schizophrenia Early Detection System Based on Graph Neural Network and Brain Network
  • Schizophrenia Early Detection System Based on Graph Neural Network and Brain Network
  • Schizophrenia Early Detection System Based on Graph Neural Network and Brain Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] According to a preferred embodiment of the present invention, see Figure 1-3 , provides an early detection system for schizophrenia based on graph neural network and brain network, which is characterized by comprising:

[0037] The EEG signal acquisition unit is used to collect the 128-channel EEG signal of the tester during the auditory stimulation of the MMN paradigm;

[0038] The traceability analysis unit is used to divide the EEG signal into four frequency bands: delta (1.5-4Hz), theta (4-8Hz), alpha (8-13Hz) and beta (13-30Hz), and analyze the EEG signals of each frequency band respectively. The traceability analysis was reconstructed as the endogenous electrical activity of the cortical layer in the brain;

[0039] a brain network construction unit, configured to construct a brain network of each frequency band (ie, a brain network topology map) according to the endogenous electrical activity of the cortical layer in the brain;

[0040] The graph neural networ...

Embodiment approach

[0041] According to yet another preferred embodiment of the present invention, the demographic characteristics include the test subject's age, years of education and IQ.

[0042] According to yet another preferred embodiment of the present invention, the event-related potential characteristics include the amplitude and latency of mismatched negative waves in the EEG signal.

[0043] According to another preferred embodiment of the present invention, the early detection system for schizophrenia based on graph neural network and brain network further includes a complete set of test units for cognitive function of schizophrenia, for acquiring the cognitive characteristics.

[0044] According to another preferred embodiment of the present invention, the early detection system for schizophrenia based on the graph neural network and the brain network further includes a detection result output unit, and the fully connected neural network module outputs four frequency bands according t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Provides a system and method for early detection of schizophrenia based on graph neural network and brain network, including an EEG signal collection unit for collecting 128-channel EEG signals of testers during auditory stimulation in the MMN paradigm; traceability analysis unit , for dividing the EEG signal into four frequency bands, and performing traceability analysis on the EEG signals of each frequency band to reconstruct the endogenous electrical activity of the brain cortex; the brain network construction unit is used for according to the brain cortex The endogenous electrical activity constructs the brain network of each frequency band; the graph neural network unit is used to extract the corresponding brain network features of each frequency band from the brain network of each frequency band, and the graph neural network unit includes a fully connected neural network module, The fully connected neural network module is used to receive and classify demographic characteristics, cognitive characteristics, event-related potential characteristics and the brain network characteristics, and output classification results as detection results. The detection system can improve the accuracy of early identification of schizophrenia.

Description

technical field [0001] The invention relates to the field of early detection of schizophrenia, in particular to a system for early detection of schizophrenia based on a graph neural network and a brain network. Background technique [0002] Schizophrenia is the most common type of mental illness characterized by disorders of thinking, emotion, behavior, and incoordination of mental activities. At present, the etiology of schizophrenia is still unclear, lack of biological indicators, and cannot be identified early. Its onset process is slow, insidious, and often recurring. If it is not detected as soon as possible, the best time to seek a doctor will be delayed, and it may even cause damage to oneself and others. harm. [0003] The main symptoms of schizophrenia include negative symptoms, positive symptoms and cognitive impairment, and the appearance of cognitive impairment occurs earlier before the onset of the disease. Research on cognitive impairment in schizophrenia has...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/369A61B5/38A61B5/374A61B5/00A61B5/16
CPCA61B5/369A61B5/38A61B5/374A61B5/165A61B5/7235A61B5/7267A61B5/4088
Inventor 张冀聪常琪
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products