US 12,424,337 B2
Method for processing drug-disease relevance relation, electronic device and non-transitory computer-readable storage medium
Zhenzhong Zhang, Beijing (CN); Hui Li, Beijing (CN); and Chenyin Shen, Beijing (CN)
Assigned to BOE TECHNOLOGY GROUP CO., LTD., Beijing (CN)
Filed by BOE TECHNOLOGY GROUP CO., LTD., Beijing (CN)
Filed on Apr. 12, 2021, as Appl. No. 17/228,502.
Application 17/228,502 is a continuation in part of application No. 15/952,582, filed on Apr. 13, 2018, granted, now 10,998,090.
Claims priority of application No. 201710642650.X (CN), filed on Jul. 31, 2017.
Prior Publication US 2021/0233667 A1, Jul. 29, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/00 (2006.01); G16H 20/10 (2018.01); G16H 50/50 (2018.01); G16H 70/40 (2018.01); G06F 16/245 (2019.01)
CPC G16H 70/40 (2018.01) [G16H 20/10 (2018.01); G06F 16/245 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A method for processing a drug-disease relevance relation applied to a terminal device, the method comprising:
receiving, by the terminal device, drug information;
analyzing, by the terminal device, the drug information and different disease information to obtain a disease in different diseases in the different disease information that has a relevance relation with a drug in the drug information, wherein the relevance relation includes a therapeutic relation between the drug and the disease and/or a side-effect relation between the drug and the disease; and
outputting, by the terminal device, the disease having the relevance relation with the drug;
wherein analyzing, by the terminal device, the drug information and the different disease information to obtain the disease in the different diseases in the different disease information that has the relevance relation with the drug in the drug information includes: analyzing, by the terminal device, the disease in the different diseases that has the relevance relation with the drug according to a pharmacodynamic relation model so as to obtain a relevance score of the drug-disease relevance relation, the pharmacodynamic relation model being a model constructed based on drug information, disease information and drug-disease relevance relation information;
wherein the pharmacodynamic relation model includes an evaluation function ƒ(d,r,s) for a drug-disease relevance relation, the evaluation function satisfies a relationship with vector space data in a real vector space: ƒ(d,r,s)=∥MR×dv−MR×sv−vR∥2;
the vector space data includes a k-dimensional column vector dv for the drug, a k-dimensional column vector sv for the disease in the different diseases, an n-dimensional column vector vR for the relevance relation between the drug and the disease, and an n×k-dimensional mapping matrix MR for the relevance relation between the drug and the disease, where d represents the drug, s represents the disease, ∥⋅∥2 represents L2 norm, and the n×k-dimensional mapping matrix MR for the relevance relation between the drug and the disease includes an n×k-dimensional mapping matrix Mc for the therapeutic relation between the drug and the disease and/or an n×k-dimensional mapping matrix Ms for the side-effect relation between the drug and the disease; the n-dimensional column vector vR for the relevance relation between the drug and the disease includes an n-dimensional column vector vr for the therapeutic relation between the drug and the disease and/or an n-dimensional column vector vs for the side-effect relation between the drug and the disease;
wherein the pharmacodynamic relation model is configured to provide recommendation with the relevance score of the drug-disease relevance relation, and a lower relevance score indicates higher significance of the drug-disease relevance relation.