# US 2021/0233667 A1 · Method for processing drug-disease relevance relation, electronic device and non-transitory computer-readable storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0233667 A1
- Document ID: US20210233667A1
- Status: Published application
- Kind: A1
- Application number: 17/228,502
- Filed: 2021-04-12
- Published: 2021-07-29
- Earliest claimed: 2017-07-31
- Assignees: Boe Technology Group Co., Ltd.
- Applicants: Boe Technology Group Co., Ltd.
- Inventors: Zhenzhong ZHANG; Hui LI; Chenyin SHEN
- Web page: https://patentgrep.com/patent/US20210233667A1

## CPC

- G16H 70/40: relating to drugs, e.g. their side effects or intended usage
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G06F 16/245: Query processing
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for processing a drug-disease relevance relation includes receiving drug information; analyzing 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, the relevance relation including a therapeutic relation between the drug and the disease and/or a side-effect relation between the drug and the disease; and outputting the disease having the relevance relation with the drug.

## Claims

### Claim 1

A method for processing a drug-disease relevance relation, comprising:
receiving drug information;
analyzing 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 the disease having the relevance relation with the drug.

### Claim 2 (depends on 1)

The method for processing the drug-disease relevance relation according to claim 1, wherein analyzing the drug information and the different disease information to obtain the disease in the different diseases that has the relevance relation with the drug in the drug information includes:
analyzing the drug information and the different disease information to provide relevance scores of relevance relations between the drug and the different diseases; and
determining the disease in the different diseases in the different disease information that has the relevance relation with the drug according to the relevance scores, wherein the relevance scores include scores of therapeutic relations between the drug and the different diseases and/or scores of side-effect relations between the drug and the different diseases.

### Claim 3 (depends on 2)

The method for processing the drug-disease relevance relation according to claim 2, further comprising:
ranking the different diseases in sequence according to the relevance scores to obtain a sequence of effectivities for therapy of the drug on the different diseases, wherein outputting the disease having the relevance relation with the drug includes outputting diseases having therapeutic relations with the drug in sequence according to the ranked relevance scores;
and/or,
ranking the different diseases in sequence according to the relevance scores to obtain a sequence of intensities for side effect of the drug on the different diseases, wherein outputting the disease having the relevance relation with the drug includes outputting diseases having side-effect relations with the drug in sequence according to the ranked relevance scores.

### Claim 4 (depends on 1)

The method for processing the drug-disease relevance relation according to claim 1, wherein analyzing 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: obtaining the disease in the different diseases that has the relevance relation with the drug according to a pharmacodynamic relation model, the pharmacodynamic relation model being a model constructed based on drug information, disease information and drug-disease relevance relation information.

### Claim 5 (depends on 4)

The method for processing the drug-disease relevance relation according to claim 4, 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.

### Claim 6 (depends on 5)

The method for processing the drug-disease relevance relation according to claim 5, wherein an expression of the k-dimensional column vector dv for the drug, an expression of the k-dimensional column vector sv for the disease in the different diseases, an expression of the n-dimensional column vector vR for the relevance relation between the drug and the disease, an expression of the n×k-dimensional mapping matrix MR for the relevance relation between the drug and the disease, and an expression of the evaluation function ƒ(d,r,s) for the drug-disease relevance relation are solved by optimizing a target function L;
L
=
∑
(
di
,
r
,
sj
)
∈
T
⁢
∑
(
di
′
,
r
,
sj
′
)
∈
T
′
⁢
max
⁡
(
0
,
f
⁡
(
di
,
r
,
sj
)
-
f
⁡
(
di
′
,
r
,
sj
′
)
+
γ
)
where,
ƒ(di,r,sj)=∥MR×dvi−MR×svj−vR∥2
ƒ(di′,r,sj′)=∥MR×dvi′−MR×svj′−vR∥2
where, T represents a set with relevance, T′ represents a set without relevance, di represents a drug with relevance, sj represents a disease with relevance; dvi represents a k-dimensional column vector for the drug with correspondence, svj represents a k-dimensional column vector for the disease with correspondence; di′ represents a drug without relevance, sj′ represents a disease without relevance; dvi′ represents a k-dimensional column vector for the drug without correspondence, svj′ represents a k-dimensional column vector for the disease without correspondence: max(a,b) represents an operation of taking a maximum value of a and b, and γ represents a pre-defined margin and γ≥ƒ(di′,r,sj′)−ƒ(di,r,sj), a score of drug-disease with relevance being at most γ less than a score of drug-disease without relevance.

### Claim 7

A method for processing a drug-disease relevance relation, comprising:
receiving disease information;
analyzing the disease information and different drug information to obtain a drug in different drugs in the different drug information that has a relevance relation with a disease in the disease 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 the drug having the relevance relation with the disease.

### Claim 8 (depends on 7)

The method for processing the drug-disease relevance relation according to claim 7, wherein analyzing the disease information and the different drug information to obtain the drug in the different drugs in the different drug information that has the relevance relation with the disease in the disease information includes:
analyzing the disease information and the different drug information to provide relevance scores of relevance relations between the disease and the different drugs; and
determining the drug in the different drugs in the different drug information that has the relevance relation with the disease according to the relevance scores, wherein the relevance scores include scores of therapeutic relations between the disease and the different drugs and/or scores of side-effect relations between the disease and the different drugs.

### Claim 9 (depends on 8)

The method for processing the drug-disease relevance relation according to claim 8, further comprising:
ranking the different drugs in sequence according to the relevance scores to obtain a sequence of effectivities for therapy of the different drugs on the disease, wherein outputting the drug having the relevance relation with the disease includes outputting drugs having therapeutic relations with the disease in sequence according to the ranked relevance scores;
and/or,
ranking the different drugs in sequence according to the relevance scores to obtain a sequence of intensities for side effect of the different drugs on the disease, wherein outputting the drug having the relevance relation with the disease includes outputting drugs having side-effect relations with the disease in sequence according to the ranked relevance scores.

### Claim 10 (depends on 7)

The method for processing the drug-disease relevance relation according to claim 7, wherein analyzing the disease information and the different drug information to obtain the drug in the different drugs in the different drug information that has the relevance relation with the disease in the disease information includes: obtaining the drug in the different drugs that has the relevance relation with the disease according to a pharmacodynamic relation model, the pharmacodynamic relation model being a model constructed based on drug information, disease information and drug-disease relevance relation information;
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 disease, a k-dimensional column vector sv for the drug in the different drugs, 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.

### Claim 11 (depends on 10)

The method for processing the drug-disease relevance relation according to claim 10, wherein an expression of the k-dimensional column vector dv for the disease, an expression of the k-dimensional column vector sv for the drug, an expression of the n-dimensional column vector vR for the relevance relation between the drug and the disease, an expression of the n×k-dimensional mapping matrix MR for the relevance relation between the drug and the disease, and an expression of the evaluation function ƒ(d,r,s) for the drug-disease relevance relation are solved by optimizing a target function L;
L
=
∑
(
di
,
r
,
sj
)
∈
T
⁢
∑
(
di
′
,
r
,
sj
′
)
∈
T
′
⁢
max
⁡
(
0
,
f
⁡
(
di
,
r
,
sj
)
-
f
⁡
(
di
′
,
r
,
sj
′
)
+
γ
)
where,
ƒ(di,r,sj)=∥MR×dvi−MR×svj−vR∥2
ƒ(di′,r,sj′)=MR×dvi′−MR×svj′−vR∥2
where, T represents a set with relevance, T′ represents a set without relevance, di represents a drug with relevance, sj represents a disease with relevance; dvi represents a k-dimensional column vector for the drug with correspondence, svj represents a k-dimensional column vector for the disease with correspondence; di′ represents a drug without relevance, sj′ represents a disease without relevance; dvi′ represents a k-dimensional column vector for the drug without correspondence, svj′ represents a k-dimensional column vector for the disease without correspondence; max(a,b) represents an operation of taking a maximum value of a and b, and γ represents a pre-defined margin and γ≥ƒ(di′,r,sj′)−ƒ(di,r,sj), a score of drug-disease with relevance being at most γ less than a score of drug-disease without relevance.

### Claim 12

A method for processing a drug-disease relevance relation, comprising:
receiving drug information and disease information;
analyzing the drug information and the disease information to obtain a relevance relation between a drug in the drug information and a disease in the disease 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 the relevance relation between the drug and the disease.

### Claim 13 (depends on 12)

The method for processing the drug-disease relevance relation according to claim 12, wherein analyzing the drug information and the disease information to obtain the relevance relation between the drug in the drug information and the disease in the disease information includes:
analyzing the drug information and the disease information according to a pharmacodynamic relation model to obtain the relevance relation between the drug in the drug information and the disease in the disease information; and
providing a relevance score of the relevance relation between the drug and the disease, wherein
the pharmacodynamic relation model is a model constructed based on drug information, disease information and drug-disease relevance relation information, and the relevance score include a score of a therapeutic relation between the disease and the drug and/or a score of a side-effect relation between the disease and the drug;
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, 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.

### Claim 14 (depends on 13)

The method for processing the drug-disease relevance relation according to claim 13, wherein an expression of the k-dimensional column vector dv for the drug, an expression of the k-dimensional column vector sv for the disease, an expression of the n-dimensional column vector vR for the relevance relation between the drug and the disease, an expression of the n×k-dimensional mapping matrix MR for the relevance relation between the drug and the disease, and an expression of the evaluation function ƒ(d,r,s) for the drug-disease relevance relation are solved by optimizing a target function L;
L
=
∑
(
di
,
r
,
sj
)
∈
T
⁢
∑
(
di
′
,
r
,
sj
′
)
∈
T
′
⁢
max
⁡
(
0
,
f
⁡
(
di
,
r
,
sj
)
-
f
⁡
(
di
′
,
r
,
sj
′
)
+
γ
)
where,
ƒ(di,r,sj)=∥MR×dvi−MR×svj−vR∥2
ƒ(di′,r,sj′)=∥MR×dvi′−MR×svj′−vR∥2
where, T represents a set with relevance, T′ represents a set without relevance, di represents a drug with relevance, sj represents a disease with relevance; dvi represents a k-dimensional column vector for the drug with correspondence, svj represents a k-dimensional column vector for the disease with correspondence; di′ represents a drug without relevance, sj′ represents a disease without relevance; dvi′ represents a k-dimensional column vector for the drug without correspondence, svj′ represents a k-dimensional column vector for the disease without correspondence: max(a,b) represents an operation of taking a maximum value of a and b, and γ represents a pre-defined margin and γ≥ƒ(di′,r,sj′)−ƒ(di,r,sj), a score of drug-disease with relevance being at most γ less than a score of drug-disease without relevance.

### Claim 15 (depends on 1)

An electronic device, comprising at least one memory and at least one processor, the at least one memory storing executable instructions that, when executed by the at least one processor, cause the electronic device to perform the method for processing the drug-disease relevance relation according to claim 1.

### Claim 16 (depends on 7)

An electronic device, comprising at least one memory and at least one processor, the at least one memory storing executable instructions that, when executed by the at least one processor, cause the electronic device to perform the method for processing the drug-disease relevance relation according to claim 7.

### Claim 17 (depends on 12)

An electronic device, comprising at least one memory and at least one processor, the at least one memory storing executable instructions that, when executed by the at least one processor, cause the electronic device to perform the method for processing the drug-disease relevance relation according to claim 12.

### Claim 18 (depends on 1)

A non-transitory computer-readable storage medium storing executable instructions that, when executed by a terminal device, cause the terminal device to perform the method for processing the drug-disease relevance relation according to claim 1.

### Claim 19 (depends on 7)

A non-transitory computer-readable storage medium storing executable instructions that, when executed by a terminal device, cause the terminal device to perform the method for processing the drug-disease relevance relation according to claim 7.

### Claim 20 (depends on 12)

A non-transitory computer-readable storage medium storing executable instructions that, when executed by a terminal device, cause the terminal device to perform the method for processing the drug-disease relevance relation according to claim 12.
