Information processing system and information processing method

Patent metadata

Field	Value
Publication number	US-2024153640-A1
Application number	US-202218548929-A
Country	US
Kind code	A1
Filing date	Feb 24, 2022
Priority date	Mar 11, 2021
Publication date	May 9, 2024
Grant date	—

Abstract

An information processing system includes: a machine learning model learned using learning data including two or more types of modal information acquired from a patient or a subject; a setting unit that sets input data to be used as input to the machine learning model from the learning data; and an output unit that inputs the input data to the machine learning model and outputs an estimation result of efficacy of a medicine or a health condition for the patient or the subject, in which the setting unit sets the input data on the basis of the degree of influence given to estimation of a diagnosis result at the time of learning of the machine learning model, the degree of influence given by each piece of the modal information included in the learning data.

First claim

1 . An information processing system including:
a machine learning model learned using learning data including two or more types of modal information acquired from a patient or a subject; a setting unit that sets input data to be used as input to the machine learning model from the learning data; and an output unit that inputs the input data to the machine learning model and outputs an estimation result of efficacy of a medicine or a health condition for the patient or the subject, wherein the setting unit sets the input data on a basis of a degree of influence of each piece of the modal information included in the learning data on estimation of a diagnosis result at a time of learning of the machine learning model.

2 . The information processing system according to claim 1 ,
wherein the input data comprises at least one piece of modal information of a same type as a type of modal information included in the learning data.

3 . The information processing system according to claim 1 ,
wherein the input data comprises a number of types of modal information, the number being smaller than a number of types of the modal information included in the learning data.

4 . The information processing system according to claim 1 ,
wherein the input data comprises modal information of a type different from the types of the modal information included in the learning data.

5 . The information processing system according to claim 1 , further including:
an information acquiring unit that acquires one or more pieces of modal information included in the input data.

6 . The information processing system according to claim 5 ,
wherein the information acquiring unit acquires, as the input data, modal information acquired by a smaller number of types of information acquiring devices than two or more types of information acquiring devices used for acquisition of each piece of the modal information included in the learning data.

7 . The information processing system according to claim 5 ,
wherein the information acquiring unit acquires, as the input data, modal information acquired by a same number of types of information acquiring devices as two or more types of information acquiring devices used for acquisition of each piece of the modal information included in the learning data, and the setting unit selects modal information to be set as the input data from among two or more types of the modal information acquired by the information acquiring unit on a basis of the degree of influence.

8 . An information processing system including:
a generation unit that generates a machine learning model that outputs an estimation result of efficacy of a medicine or a health condition for a patient or a subject by using learning data including two or more types of modal information acquired from the patient or the subject; and a calculation unit that calculates a degree of influence of each piece of the modal information included in the learning data on the estimation result of the efficacy of the medicine or the health condition at the time of generating the machine learning model, wherein the generation unit changes the number of types of modal information included in the learning data to be used for generation of the machine learning model on a basis of the degree of influence.

9 . The information processing system according to claim 8 ,
wherein the generation unit sets, as the learning data, a predetermined number of pieces of modal information set in advance in descending order of values of the degrees of influence of the respective pieces of modal information.

10 . The information processing system according to claim 8 ,
wherein the generation unit sets, as the learning data, modal information of which degree of influence has a value equal to or greater than a preset threshold value among the degrees of influence of the respective pieces of modal information.

11 . The information processing system according to claim 8 ,
wherein the generation unit excludes, from the learning data, modal information of which degree of influence is included in a preset ratio in an ascending order among the plurality of pieces of modal information.

12 . The information processing system according to claim 8 ,
wherein the generation unit creates a management table that manages modal information of which input to the machine learning model is enabled and modal information of which input to the machine learning model is disabled among the plurality of pieces of modal information in a record for each piece of learning and manages, for each of records, estimation accuracy of the machine learning model when the machine learning model is learned by using the modal information enabled in each of the records of the management table.

13 . The information processing system according to claim 8 , further including:
an influence degree presenting unit that visualizes the influence degree of each piece of the modal information and presents the degree of influence to a user.

14 . The information processing system according to claim 13 ,
wherein the influence degree presenting unit visualizes and presents, to the user, a degree of influence of other modal information with respect to specific modal information in the two or more types of modal information included in the learning data.

15 . The information processing system according to claim 13 ,
wherein the influence degree presenting unit visualizes and presents to the user a region having affected derivation of the estimation result in at least one piece of modal information among the two or more types of modal information included in the learning data.

16 . The information processing system according to claim 13 ,
wherein meta-information is assigned to at least one of the two or more types of modal information included in the learning data, and the influence degree presenting unit visualizes and presents to the user meta-information that has affected derivation of the estimation result among the meta-information assigned to the at least one piece of modal information.

17 . The information processing system according to claim 13 ,
wherein the generation unit relearns the machine learning model using modal information selected by the user on a basis of the degree of influence presented by the influence degree presenting unit as the learning data.

18 . An information processing system including:
a generation unit that generates a machine learning model that outputs an estimation result of efficacy of a medicine or a health condition for a patient or a subject by using learning data including two or more types of modal information acquired from the patient or the subject; a calculation unit that calculates a degree of influence of each piece of the modal information included in the learning data on an estimation result of the efficacy of the medicine or the health condition at the time of generation of the machine learning model; a setting unit that sets input data as input to the machine learning model from the learning data on a basis of the degree of influence; and an output unit that inputs the input data to the machine learning model and outputs an estimation result of efficacy of a medicine or a health condition for the patient or the subject, wherein the generation unit changes the number of types of modal information included in the learning data to be used for generation of the machine learning model on a basis of the degree of influence, and the setting unit sets the input data on a basis of a degree

Assignees

• Sony Group Corp

Inventors

• Yoshioka Shigeatsu
• Kobayashi Yoshiyuki
• Kunihiro Takeshi
• Kobayashi Yohei
• SASADA Shiori
• KATSUKI Yugo
• Suzuki Kenji
• Ishii Masato

Classifications

• G06T11/26

  Drawing of charts or graphs · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06T11/206

  Physics · mapped topic

• G06T2210/41

  Medical · CPC title

• G16B20/00

  ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations · CPC title