Method and system for constructing medical-oriented causality knowledge base
A technology of causality and knowledge base, applied in the field of medical informatization, can solve the problems of quantifying the causality of diseases and not being able to explain the causality of diseases
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] In the process of scientific research, literature is the most persuasive and convincing carrier for recording scientific research results. There is no doubt that most of the content of scientific research activities is recorded in the literature. A large number of documents record the relationship between diseases, but it is very difficult for doctors to consult a large number of documents to study the causal relationship between diseases. For example, in the medical world, there is no causal relationship between the conditions of the comorbidities, but there is a causal relationship between the conditions of the complications. Based on this, the present invention provides a method for constructing a knowledge base of complications or comorbidities in a quantitative manner through the processes of collecting, separating, extracting parameters, and judging documents containing various diseases, which can provide doctors with The decision-making of treatment methods prov...
Embodiment 2
[0078] This embodiment serves as a supplement to Embodiment 1. In order to be able to without affecting the causal relationship between disease pairs, the causal unit 3 simplifies the undirected graph constraints through the independence test. For example, the test of independence can use the chi-square test of independence.
[0079] In the present invention, the independence test can also adopt the following method:
[0080] For disease L m , obtained from the constructed undirected graph in the form of sequence and L m The connected nodes make up its node set. And calculate each node and disease L successively m The correlation between them, and select the node with the greatest correlation for independence assumption, delete the given subset D and L m independent nodes. In the present invention, entropy is used to measure the random variable pair L m uncertainty. For a given random variable L m In the case of the random variable L n The uncertainty of can be measu...
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