Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree

A recommendation method and correlation technology, applied in the direction of drugs or prescriptions, neural learning methods, biological neural network models, etc., can solve problems such as unformed technical solutions, and improve treatment efficiency and suitability, rapid generation, and applicability high effect

Active Publication Date: 2021-09-17
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technology has not proposed a specific implementation of how to screen out typical cases with symptoms similar to the target patient’s symptoms in a large number of medical records, how to use the prescription data of typical cases to generate the traditional Chinese medicine prescription for the target patient, and realize the recommendation of traditional Chinese medicine prescriptions. method, which also requires technical personnel in the field to develop and solve
[0005]However, there is no effective technical solution to the above problems

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
  • Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree
  • Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree
  • Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] This embodiment provides a method for recommending traditional Chinese medicine prescriptions based on the correlation degree of clinical phenotypes of cases, such as figure 1 shown, including steps:

[0075] S1. Obtain the case information corresponding to the target patient; the case information includes age, gender, TCM diagnosis results and corresponding symptom information;

[0076] S2. According to the age, gender, and TCM diagnosis results, search for multiple homogenized cases with the same sex and the same age group as the target patient from the preset database; where the homogenized cases have the same TCM diagnosis results as the target patient;

[0077] S3. Calculate the case clinical phenotype correlation between the symptom information of the target patient and the symptom information corresponding to the TCM diagnosis result of each homogeneous case, and obtain the clinical phenotype of multiple cases between the target patient and multiple homogeneous c...

Embodiment 2

[0143] A method for recommending prescriptions of traditional Chinese medicine based on the correlation degree of clinical phenotype provided in this example differs from Example 1 in that:

[0144] In this embodiment, the clinical phenotype correlation degree of the case can be obtained by cosine similarity, specifically including:

[0145] extracting the first feature vector of the symptom information of the target patient;

[0146] Extracting the second feature vector of the symptom information of each homogeneous case;

[0147] Calculate the cosine similarity between the first eigenvector of the symptom information of the target patient and the second eigenvector of each of the homogeneous case symptom information to obtain multiple cosine similarities, thereby obtaining the The clinical phenotype correlation of the cases. Wherein, the calculation method of the cosine similarity belongs to the prior art, therefore, the description will not be repeated.

Embodiment 3

[0149] A method for recommending prescriptions of traditional Chinese medicine based on the correlation degree of clinical phenotype provided in this example differs from Example 1 in that:

[0150] In this embodiment, the clinical phenotype correlation degree of the case can be obtained by the similarity based on the Euclidean distance, specifically including:

[0151] extracting the first feature vector of the symptom information of the target patient;

[0152] Extracting the second feature vector of the symptom information of each homogeneous case;

[0153] calculating the Euclidean distance between the first eigenvector of the target patient and the second eigenvector of each of the homogeneous cases;

[0154] Calculate the Euclidean distance-based similarity between the target patient's symptom information and each homogenized case symptom information according to each Euclidean distance, and obtain multiple Euclidean distance-based similarities.

[0155] In this embodi...

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 a traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree. The related method comprises the following steps: S1, acquiring case information corresponding to a target patient; S2, according to the age, the gender and the traditional Chinese medicine diagnosis result, searching a plurality of homogenized cases which have the same gender as the target patient and are in the same age group from a preset database; S3, calculating a case clinical phenotype correlation degree between the symptom information of the target patient and each piece of homogenized case symptom information to obtain a plurality of case clinical phenotype correlation degrees; S4, screening a plurality of homogenized cases with the similarity greater than a preset threshold value from the plurality of homogenized cases as reference cases according to the clinical phenotype correlation degree of the plurality of cases; S5, selecting one reference case from the plurality of reference cases as a target reference case, and obtaining a traditional Chinese medicine formula of the traditional Chinese medicine diagnosis result corresponding to the target reference case; and S6, calibrating the traditional Chinese medicine prescription of the target reference case according to the symptom information of the target patient to obtain the traditional Chinese medicine prescription of the target patient.

Description

technical field [0001] The invention relates to the field of clinical pharmacy of traditional Chinese medicines, in particular to a method and system for recommending prescriptions of traditional Chinese medicines based on the correlation degree of clinical phenotypes of cases. Background technique [0002] Traditional Chinese medicine is the basic unit of clinical prescriptions of traditional Chinese medicine, and it is the key for doctors of traditional Chinese medicine to provide diagnosis and treatment plans for patients. Among them, the functions and indications of traditional Chinese medicine and the individualized symptoms of patients are important basis and targets for clinical prescriptions and medications, and are important supports for syndrome differentiation and treatment of traditional Chinese medicine. With the development of information technology and artificial intelligence, how to introduce advanced intelligent recommendation technology into the field of tr...

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): G16H20/10G16H10/60G06N3/04G06N3/08
CPCG16H20/10G16H10/60G06N3/08G06N3/045
Inventor 洪东升楼燕卢晓阳吴佳莹陈婷婷刘晓健
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products