Spirit inhibition medicine recommendation method and system based on mental disorder subtype classification
A technology for mental disorders and recommended methods, applied in the field of medicine, can solve problems such as confusion of classification logic, lack of classification standards, and inability to predict patient response to treatment, etc., and achieve good generalization, improved classification accuracy, and high stability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0040] The present invention is based on the Positive and Negative Symptom Scale (PANSS) of the first episode of schizophrenia collected by the China Antipsychotic Genomic Medicine Association. Contains 30 index components and 843 cases. 687 of the 843 cases had been treated with antipsychotic drugs for a period of 6 weeks. During the six weeks, each patient was (randomly) assigned an antipsychotic drug among several mainstream drugs and used it at the recommended dose. After 6 weeks, the Positive and Negative Symptom Scale assessment was performed again.
[0041] The present invention adopts the maximum modularization method to divide the community structure to carry out the bi-clustering subtype classification algorithm based on the assessment data of the Mental Disorder Scale. Specific steps are as follows:
[0042] First, the dependency network G=[V,W] is defined by the previous method. in, Separate the positive and negative elements of W and denote them as W ± , th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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