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

Electronic equipment for determining risk factors of Alzheimer's disease

An electronic device and risk technology, applied in the computer field, can solve problems such as low AD diagnosis accuracy

Inactive Publication Date: 2022-07-01
HUNAN NORMAL UNIVERSITY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the accuracy of AD diagnosis based on the brain region network and gene network obtained by the current method analysis in the existing technology is relatively low. Towards Drug Development and Targeted Transcranial Magnetic Therapy

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
  • Electronic equipment for determining risk factors of Alzheimer's disease
  • Electronic equipment for determining risk factors of Alzheimer's disease
  • Electronic equipment for determining risk factors of Alzheimer's disease

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] Based on the above elements of the structural information aggregation model, Embodiment 1 of the present invention provides a structural information aggregation model based on generative adversarial networks, the internal structure of which is as follows figure 2 As shown, including: a generator 201 and a discriminator 202;

[0084] The generator 201 is used to obtain a first key structural sub-network after aggregating the structural information of the brain region-gene network, and then to diffuse the structural information of the first key structural sub-network to obtain a reconstructed brain region-gene network.

[0085] The discriminator 202 is used to aggregate the structural information of the reconstructed brain region-gene network to obtain a second key structure sub-network, and then extract the edge features of the second key structure sub-network and output the subject as an AD patient. Probability judgment results.

[0086] In the structural information a...

Embodiment 2

[0131] When training the structural information aggregation model based on generative adversarial network, there are two kinds of input to the discriminator: the real brain area-gene network and the reconstructed brain area-gene network by the generator; the discriminator has two functions. One is to judge the authenticity of the input brain region-gene network, and the second is to judge whether the input brain region-gene network is normal or AD. The discriminator and generator train each other and are continuously tuned until the generative adversarial network converges. At this time, the key structure sub-network can aggregate the characteristic information of the subject's brain region-gene network, so that AD judgment based on the key structure sub-network can assist in the accurate diagnosis of Alzheimer's disease.

[0132] Embodiment 2 of the present invention provides a specific method for training the above-mentioned generative adversarial network-based structural in...

Embodiment 3

[0172] Based on the structural information aggregation model obtained by pre-training, the third embodiment of the present invention provides a method for judging Alzheimer's disease. The specific process is as follows: Figure 15 shown, including the following steps:

[0173] Step S1501: Constructing the subject's brain region-gene network according to the subject's brain image data and gene data.

[0174]Step S1502: Input the brain region-gene network into the structural information aggregation model pre-trained by the above method.

[0175] Step S1503: Aggregate the structural information through the structural information aggregation model and extract the features of the edges, and output the judgment result of the probability that the subject is an Alzheimer's disease AD patient.

[0176] Specifically, through the above generator and discriminator in the structural information aggregation model, the subject's brain region-gene network is aggregated for structural informa...

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

The invention discloses electronic equipment for determining risk factors of Alzheimer's disease, which comprises a memory and a processor, when the processor executes the computer program, the processor is used for performing structure information aggregation on brain region-gene networks of a plurality of testees through a structure information aggregation model, extracting edge features and then outputting a judgment result of the probability that each testee is a patient with the Alzheimer's disease (AD); determining the importance degree of each node in the brain region-gene network of the AD patient according to the closeness degree of the output judgment result and the real situation; determining nodes serving as AD risk elements in the brain region-gene network according to the importance of the nodes; wherein the testees comprise a plurality of normal persons and AD patients. By applying the method, the lesion brain region and the risk gene of AD can be more accurately determined, so that targeted drug development and targeted transcranial magnetic therapy are facilitated.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an electronic device for determining risk factors of Alzheimer's disease. Background technique [0002] Alzheimer's disease (AD) is characterized by a striking array of dementia symptoms, often seen in older adults. The pathogenesis of AD is complex, and its pathogenesis spans from macroscopic to microscopic levels. For example, the lesions of brain function and structure are closely related to the abnormal expression of genes. Therefore, finding the correlation pattern between macroscopic lesions and microscopic variation in the brain will help to reveal The multilevel pathogenesis of Alzheimer's disease. Some researchers build networks that abstract genes or brain regions as nodes to study functional correlations between causative factors. Huang et al. defined the embedded representation of each brain region and proposed a new metric to evaluate the similarity betwe...

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 Applications(China)
IPC IPC(8): G16H50/20G16H50/30G06N3/04G06N3/08
CPCG16H50/20G16H50/30G06N3/08G06N3/045
Inventor 毕夏安王雅琴岳凌霞吴昊徐露允
Owner HUNAN NORMAL UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com