Calculation system, calculation method, and calculation program

Abstract

The present invention calculates the risk of contracting a specific disease. This calculation system comprises: a metabolite data acquisition unit that acquires subject metabolite data pertaining to the amounts or concentrations of a plurality of metabolites in a subject; a metabolite data extraction unit that, on the basis of the correspondence between the metabolites and the disease, extracts, from the acquired subject metabolite data, subject metabolite data of at least one metabolite corresponding to a target disease for which a score is calculated; a score calculation unit that calculates a disease score pertaining to the risk of the target disease for the subject on the basis of statistical relevance between the extracted subject metabolite data and a reference person data group including reference person metabolite data that is acquired in advance and pertains to the amount or concentration of the at least one metabolite in a plurality of reference people; and a score output unit that outputs the disease score.

Description

Calculation system, calculation method, and calculation program

[0001] This application is based on Japanese Patent Application No. 2024-009325, filed on January 25, 2024, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a calculation system, a calculation method, and a calculation program.

[0003] Conventionally, techniques for analyzing biological samples collected from subjects have been known. For example, Patent Literature 1 discloses an information processing system including an intestinal environment data acquisition unit that acquires intestinal environment data of a user, an intestinal environment evaluation unit that evaluates the intestinal environment of the user based on the acquired intestinal environment data, and an information provision unit that provides information including the evaluation to the user.

[0004] International Publication No. 2021 / 153574

[0005] The information processing system described in Patent Document 1 provides a subject with information regarding the subject's dietary habits. As a result, the subject can understand the subject's dietary habits, but cannot understand the subject's own risk of contracting a specific disease.

[0006] Therefore, the present disclosure aims to calculate the risk of contracting a specific disease.

[0007] A calculation system according to one aspect of the present disclosure includes a metabolite data acquisition unit that acquires subject metabolite data relating to the amount or concentration of multiple metabolites in a subject; a metabolite data extraction unit that extracts subject metabolite data of at least one metabolite corresponding to a target disease of a subject for which a score is to be calculated from the acquired subject metabolite data based on the correspondence between metabolites and diseases; a score calculation unit that calculates a disease score relating to the risk of the target disease in the subject based on the statistical correlation between the extracted subject metabolite data and a reference subject data group that includes reference subject metabolite data relating to the amount or concentration of at least one metabolite in multiple reference subjects that has been acquired in advance; and a score output unit that outputs the disease score.

[0008] According to the present disclosure, the risk of contracting a particular disease can be calculated.

[0009] 1 is a diagram showing an overview of processing in a calculation system 100 according to an embodiment of the present disclosure. FIG. 2 is a diagram showing a configuration of a calculation system 100 according to an embodiment of the present disclosure. FIG. 3 is a diagram showing an example of correspondence data stored in a storage unit 110. FIG. 4 is a diagram showing an example of a reference individual data group stored in a storage unit 110. FIG. 5 is a diagram showing an example of subject metabolite data stored in a storage unit 110. FIG. 6 is a diagram showing an example of a message template stored in a storage unit 110. FIG. 7 is a diagram showing an example of a report output by the calculation system 100. FIG. 8 is a diagram showing an example of a report output by the calculation system 100. FIG. 9 is a flowchart showing an example of processing in the calculation system 100. FIG. 10 is a diagram showing an example of the hardware configuration of a computer 1100.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present disclosure will be described with reference to the accompanying drawings, in which: Fig. 1 is a diagram showing an overview of processing in a calculation system 100 according to an embodiment of the present disclosure.

[0011] The calculation system 100 is an information processing system realized by a calculation program. The calculation system 100 is an information processing system that calculates and outputs a disease score related to the disease risk of a subject and a total score based on multiple disease scores, based on the subject's metabolite data and a reference subject data group.

[0012] First, the calculation system 100 acquires metabolite data of the subject from the measurement system 200 (S101). Next, the calculation system 100 extracts, from the acquired metabolite data, metabolite data for at least one metabolite corresponding to the target disease for which a score is to be calculated, and calculates a first disease score based on the extracted metabolite data for at least one metabolite and the reference subject data group (S102). The calculation system 100 similarly calculates disease scores for other target diseases (e.g., second disease scores) (S103).

[0013] The calculation system 100 then calculates a total score based on the multiple disease scores (e.g., the first disease score and the second disease score) (S104). The calculation system 100 outputs the multiple disease scores (e.g., the first disease score and the second disease score) and the total score to the output destination system 300.

[0014] 2 is a diagram showing the configuration of a calculation system 100 according to an embodiment of the present disclosure. The calculation system 100 is communicably connected to a measurement system 200 and an output destination system 300 via a network such as the Internet. Details of the calculation system 100 will be described later. Note that the calculation system 100 and the measurement system 200 may exchange information via an interface such as a USB (Universal Serial Bus) without being communicably connected via a network such as the Internet.

[0015] The measurement system 200 is an information processing system that measures subject metabolite data relating to a plurality of metabolites of a subject.

[0016] The measurement system 200, for example, acquires a predetermined sample (e.g., the subject's stool, urine, blood, saliva, etc.) from the subject, analyzes the predetermined sample using a predetermined technique (e.g., mass spectrometry), and measures subject metabolite data of multiple metabolites contained in the predetermined sample. The measurement system 200 outputs the measured subject metabolite data to the calculation system 100.

[0017] When the calculation system 100 and the measurement system 200 are not connected to each other via a network such as the Internet, but exchange information via an interface such as a USB, the measurement system 200 may output the subject's metabolite data measured via the interface such as a USB to the calculation system 100.

[0018] The measurement system 200 measures, for example, subject metabolite data of a plurality of metabolites included in the correspondence data described below.

[0019] The output destination system 300 is an information processing system to which the calculation system 100 outputs scores (disease scores and total scores) and messages.

[0020] The output destination system 300 may be a medical institution system used by a medical institution (e.g., a doctor). That is, the calculation system 100 may output the scores (disease score and total score) and a message to the medical institution system, thereby notifying the doctor of the scores (disease score and total score) and a message.

[0021] The output destination system 300 may also be an information processing device used by the subject, which allows the subject to easily check the scores (disease score and total score) and messages without going through a third party (for example, a medical institution).

[0022] Although one measurement system 200 and one output destination system 300 are shown in FIG. 2, there may be a plurality of measurement systems 200 and a plurality of output destination systems 300.

[0023] Next, details of the calculation system 100 will be described. The calculation system 100 includes a storage unit 110, a correspondence data acquisition unit 120, a reference subject data group acquisition unit 130, a metabolite data acquisition unit 140, a metabolite data extraction unit 150, a score calculation unit 160, a score output unit 170, a message output unit 180, an object output unit 190, and a report output unit 195. Each unit shown in Fig. 2 can be realized, for example, by using a storage area or by a processor executing a program stored in the storage area.

[0024] The storage unit 110 stores information processed in the calculation system 100. The storage unit 110 can store, for example, correspondence data, a reference subject data group, subject metabolite data, a disease score, a total score, and a message template, which will be described later.

[0025] The correspondence data acquisition unit 120 acquires correspondence data indicating the correspondence between metabolites and diseases, and stores the acquired correspondence data in the storage unit 110 .

[0026] Here, examples of diseases include obesity / diabetes, allergic diseases (particularly, for example, atopic dermatitis, food allergies, allergic rhinitis (including hay fever), and bronchial asthma), intestinal diseases (particularly, for example, constipation, enteritis, and irritable bowel syndrome), cardiovascular diseases (particularly, for example, heart disease and ischemic heart disease), and non-alcoholic steatohepatitis. However, diseases are not limited to these.

[0027] Furthermore, metabolites are preferably, for example, intestinal bacterial metabolites, and may be, for example, fatty acid metabolites, short-chain fatty acids, and amino acid metabolites. Fatty acid metabolites may be, for example, linoleic acid metabolites, particularly, for example, HYA (10-hydroxy-cis-12-octadecenoic acid), KetoA (10-oxo-cis-12-octadecenoic acid), and KetoC (10-oxo-trans-11-octadecenoic acid). Short-chain fatty acids include, for example, acetic acid, propionic acid, and butyric acid. Amino acid metabolites include, for example, trimethylamine. However, metabolites are not limited to these. The reference subject data group may be composed of any combination of fatty acid metabolites, short-chain fatty acids, and amino acid metabolites, and the necessary reference subject data group may be referenced depending on the disease. The subject's metabolite data may also be metabolite data corresponding to the reference subject data group, but may be measured and selected appropriately depending on the disease.

[0028] The correspondence data is data indicating the correspondence between a disease and at least one metabolite that is thought to affect the risk of contracting the disease (disease risk).

[0029] The correspondence between a disease and a metabolite may be arbitrarily determined by, for example, an administrator of the calculation system 100. In this case, the administrator of the calculation system 100 may determine the correspondence between a disease and a metabolite by referring to a predetermined academic paper. In other words, the correspondence data may be data indicating the correspondence between a disease and a metabolite that is academically considered to affect the risk of contracting the disease (disease risk).

[0030] The correspondence data acquiring unit 120 may acquire correspondence data created by an administrator of the calculation system 100. Furthermore, the correspondence data acquiring unit 120 may acquire the correspondence data from, for example, an administrator terminal of the administrator of the calculation system 100.

[0031] 3 is a diagram showing an example of correspondence data stored in the storage unit 110. The correspondence data stored in the storage unit 110 includes, for example, disease name data and metabolite name data. The disease name data is data indicating the name of a target disease for which the calculation system 100 calculates a disease score (described later). The metabolite name data is data indicating the name of a metabolite corresponding to the disease name data.

[0032] The correspondence data stored in the storage unit 110 may include, in place of the disease name data and metabolite name data, a disease ID for identifying the disease name and a metabolite ID for identifying the metabolite name, in association with each other.

[0033] The reference individual data group acquiring unit 130 acquires a reference individual data group including reference individual metabolite data of at least one metabolite for a plurality of reference individuals, and stores the acquired reference individual data group in the storage unit 110.

[0034] Here, the reference subject may include, for example, a healthy subject (e.g., a person who does not have a specific disease (e.g., a disease indicated by the disease name data included in the correspondence data)). In other words, the reference subject data group may include, for example, metabolite data obtained by analyzing samples obtained from multiple healthy subjects. This allows the calculation system 100 to calculate the disease score of the subject by comparing the metabolite data of the subject and the healthy subjects.

[0035] Furthermore, the reference individuals may include, for example, unhealthy individuals (e.g., individuals with a specific disease (e.g., individuals with a disease indicated by the disease name data included in the correspondence data)). In other words, the reference individual data group may include, for example, metabolite data obtained by analyzing samples obtained from multiple unhealthy individuals. This allows the calculation system 100 to calculate the disease score of the subject by comparing the metabolite data of the subject and the unhealthy individuals.

[0036] Furthermore, the reference subjects may include, for example, healthy subjects and unhealthy subjects. That is, the reference subject data group may include, for example, metabolite data obtained by analyzing samples obtained from a plurality of healthy subjects and unhealthy subjects. This allows the calculation system 100 to calculate the disease score of the subject by comparing the metabolite data of the subject with the metabolite data of the healthy subjects and unhealthy subjects.

[0037] When the reference individuals include both healthy and unhealthy individuals, the reference individual data group may include data (e.g., a flag or label) indicating whether the reference individuals are healthy or unhealthy. This allows the calculation system 100 to evaluate whether the reference individuals are healthy or unhealthy.

[0038] The reference subject data group includes at least one reference subject metabolite data for each of a plurality of reference subjects. The at least one reference subject metabolite data included in the reference subject data group may be metabolite data for a metabolite corresponding to the metabolite name data included in the correspondence data. In this case, the metabolites include, for example, fatty acid metabolites, short-chain fatty acids, and amino acid metabolites, particularly, for example, linoleic acid metabolites (e.g., HYA, KetoA, and KetoC), acetic acid, propionic acid, butyric acid, and trimethylamine.

[0039] The reference subject metabolite data may be, for example, quantitative data on metabolites, particularly data on the amount or concentration of a metabolite. The units of the values ​​indicated by the metabolite data may differ for each metabolite, and may be, for example, the amount (mg or μg) of the metabolite contained per 1 g of sample.

[0040] The reference individual data group acquisition unit 130 may acquire the reference individual data group from, for example, an administrator terminal.

[0041] Furthermore, the reference individual data group acquiring unit 130 may add the subject's metabolite data of the subject acquired by the metabolite data acquiring unit 140 (described later) to the reference individual data group to acquire the added reference individual data group. In this case, the reference individual data group acquiring unit 130 may determine whether the subject corresponds to a reference individual (e.g., a healthy individual or an unhealthy individual), and if the subject corresponds to the reference individual, may add the subject's metabolite data to the reference individual data group. This enables the calculation system 100 to expand the reference individual data group and improve the accuracy of the disease score.

[0042] 4 is a diagram showing an example of a data group of reference individuals stored in the storage unit 110. The data group of reference individuals stored in the storage unit 110 includes a reference individual sample ID and metabolite quantity data. The reference individual sample ID is data for identifying the sample of the reference individual. The metabolite quantity data included in the data group of reference individuals is data indicating the amount or concentration value of each of a plurality of metabolites included in the sample corresponding to the reference individual sample ID.

[0043] The metabolite data acquisition unit 140 acquires subject metabolite data relating to a plurality of metabolites in the subject, and stores the acquired subject metabolite data in the storage unit 110 .

[0044] The subject metabolite data is, for example, quantitative data of metabolites detected in a sample from the subject, particularly, for example, data relating to the amount or concentration of the metabolites. The units of the values ​​indicated by the metabolite data may differ for each metabolite, and may be, for example, the amount (mg or μg) of the metabolite contained per 1 g of sample.

[0045] The metabolite data acquiring unit 140 can acquire the subject's metabolite data, for example, from the measurement system 200. When the calculation system 100 and the measurement system 200 are not communicatively connected via a network such as the Internet, but exchange information via an interface such as a USB, the metabolite data acquiring unit 140 may acquire the subject's metabolite data from a predetermined device, such as a USB, that stores the subject's metabolite data.

[0046] 5 is a diagram showing an example of subject metabolite data stored in the storage unit 110. The subject metabolite data stored in the storage unit 110 includes, for example, a subject sample ID and metabolite quantity data. The subject sample ID is data that identifies the subject's sample. The metabolite quantity data included in the subject metabolite data is data that indicates the amount or concentration value of each of multiple metabolites included in the sample corresponding to the sample ID.

[0047] The metabolite data extraction unit 150 extracts subject metabolite data of at least one metabolite corresponding to the target disease for which the score is to be calculated from the acquired subject metabolite data based on the correspondence between metabolites and diseases.

[0048] Specifically, a case where the target disease is "obesity / diabetes" will be described. First, the metabolite data extraction unit 150 identifies the metabolites "HYA, KetoA, KetoC, acetic acid, propionic acid, and butyric acid" corresponding to the disease "obesity / diabetes" based on the correspondence data. Then, the metabolite data extraction unit 150 extracts the subject's metabolite data for the metabolites "HYA, KetoA, KetoC, acetic acid, propionic acid, and butyric acid" from the acquired subject's metabolite data.

[0049] Furthermore, when the target disease includes multiple target diseases, the metabolite data extraction unit 150 can extract the subject's metabolite data for each of the multiple target diseases. Specifically, when the target diseases are, for example, the disease "obesity / diabetes" and "allergic disease," the metabolite data extraction unit 150 extracts the subject's metabolite data of the metabolites "HYA, KetoA, KetoC, acetic acid, propionic acid, butyric acid" for the disease "obesity / diabetes" based on the correspondence data, and extracts the subject's metabolite data of the metabolites "HYA, acetic acid, propionic acid, butyric acid" for the disease "allergic disease."

[0050] The score calculation unit 160 calculates a disease score related to the risk of the target disease in the subject based on the statistical correlation between the extracted subject metabolite data and the reference subject data group, and stores the calculated disease score in the memory unit 110.

[0051] When the target diseases include multiple target diseases, the score calculation unit 160 can calculate a disease score for each of the multiple target diseases based on the subject's metabolite data extracted for each of the multiple target diseases. Specifically, when the target diseases are, for example, the diseases "obesity / diabetes" and "allergic diseases," the score calculation unit 160 can calculate a disease score for the disease "obesity / diabetes" based on the subject's metabolite data for the metabolites "HYA, KetoA, KetoC, acetic acid, propionic acid, and butyric acid" corresponding to the disease "obesity / diabetes" based on the correspondence data, and can calculate a disease score for the disease "allergic diseases" based on the subject's metabolite data for the metabolites "HYA, acetic acid, propionic acid, and butyric acid" corresponding to the disease "allergic diseases."

[0052] Next, a specific calculation method by the score calculation unit 160 will be described. The score calculation unit 160 can calculate a disease score, for example, based on a statistical association (including, for example, a ranking in the distribution of a data group). Specifically, based on the extracted subject metabolite data and the reference subject data group, the disease score can be calculated according to the ranking of the subject having the extracted subject metabolite data in the distribution of the reference subject data group.

[0053] More specifically, if the extracted subject metabolite data is ranked in the top 20% of the reference subject data group, the score calculation unit 160 can calculate the disease score as, for example, 80 points (i.e., a score equivalent to 80% of a perfect score of 100 points). In this case, if multiple subject metabolite data are extracted for one target disease, the score calculation unit 160 can calculate, for example, the average value of the scores (metabolite scores) calculated based on each of the multiple subject metabolite data as the disease score for the target disease.

[0054] In this case, the score calculation unit 160 may calculate the disease score by assigning a predetermined weight to each of the multiple metabolite scores. This allows the calculation system 100 to calculate a disease score that takes specific metabolites into greater consideration. More specifically, for example, among the multiple subject metabolite data, a disease score can be calculated in which a higher weight is assigned to a metabolite that has a greater impact on the risk of the target disease. Note that the weighting may be different for each target disease.

[0055] In this way, the calculation system 100 calculates a disease score using statistical correlation, particularly, for example, a ranking in a distribution. This calculation method allows the calculation system 100 to calculate a disease score based on both metabolite data for metabolites for which the higher the amount, the lower the disease risk is assessed, and metabolite data for metabolites for which the lower the amount, the lower the disease risk is assessed. Furthermore, this calculation method allows the metabolite amounts of the subject and the reference subject to be evaluated relatively, rather than absolutely, even though the amounts and concentrations (scales) of multiple metabolites in vivo differ. This allows the disease score to be easily calculated by evaluating multiple metabolites with different amounts and concentrations.

[0056] Furthermore, the score calculation unit 160 can calculate a total score for the subject's health condition based on the multiple disease scores. For example, the score calculation unit 160 can calculate an average value of the multiple disease scores as the total score.

[0057] At this time, the score calculation unit 160 can calculate a total score by assigning a predetermined weight to each of the multiple disease scores. This allows the calculation system 100 to calculate a total score that takes a specific target disease into greater consideration. More specifically, for example, the total score can be calculated such that the greater the impact of a disease on the subject's health status among the multiple target diseases, the higher the weighting.

[0058] Furthermore, the score calculated by the score calculation unit 160 may be a score out of 100 points, but is not limited to this and may be, for example, a score on a five-point scale.

[0059] The score output unit 170 outputs the disease score and the total score.

[0060] The score output unit 170 can output the disease score and the total score to, for example, the output destination system 300. This allows a person using the output destination system 300 (for example, a medical institution, a subject, etc.) to obtain the disease score and the total score. The disease score and the total score may be provided alone or together with information indicating other conditions of the subject, and may be viewable, for example, on the output destination system 300 or may be viewable as a list on paper or a sheet together with other information.

[0061] The message output unit 180 outputs a message to the subject, including content regarding the subject's risk of the target disease corresponding to the calculated disease score, based on multiple message templates that are set in advance according to the disease score.

[0062] The calculation system 100 stores in advance a plurality of message templates including content related to the risk of a target disease in a subject according to the disease score in the storage unit 110. The message output unit 180 outputs a message corresponding to the calculated disease score by referring to the plurality of message templates stored in the storage unit 110. The message output process by the message output unit 180 will be described later.

[0063] The plurality of message templates are stored in advance in the storage unit 110. The plurality of message templates are set in advance by, for example, an administrator of the calculation system 100 and stored in the storage unit 110.

[0064] The message may, for example, indicate that the disease risk for each target disease is "high," "slightly high," "average," "slightly low," or "low" according to the disease score. This allows the subject or the medical institution to understand the subject's disease risk for each target disease.

[0065] Specifically, the multiple message templates corresponding to the disease score for each target disease may be configured to output, for example, a message indicating a high disease risk when the disease score is less than 20 points (e.g., "Your risk of allergic disease tends to be high"); a message indicating a slightly high disease risk when the disease score is 20 points or more but less than 40 points (e.g., "Your risk of allergic disease tends to be slightly high"); a message indicating an average disease risk when the disease score is 40 points or more but less than 60 points (e.g., "Your risk of allergic disease is average"); a message indicating a slightly low disease risk when the disease score is 60 points or more but less than 80 points (e.g., "Your risk of allergic disease tends to be slightly low"); and a message indicating a low disease risk when the disease score is 80 points or more (e.g., "Your risk of allergic disease tends to be low").

[0066] Furthermore, a message may be set for each metabolite, for example. In this case, the message for each metabolite may be set, for example, according to the magnitude relationship between the metabolite data (e.g., the amount or concentration of the metabolite indicated by the metabolite data) and a predetermined threshold. The predetermined threshold may be, for example, a statistical value (e.g., median, average, etc.) of the reference subject metabolite data corresponding to the metabolite included in the reference subject data group. This allows the subject or a medical institution to understand the condition of the subject compared to the reference subject for each metabolite.

[0067] Specifically, the message template according to the magnitude relationship between the metabolite data and a predetermined threshold may be configured to output, for example, the message "Your level of metabolite HYA is higher than that of the reference subject data group" when the metabolite amount of metabolite HYA indicated by the subject's metabolite data is higher than the statistical value (e.g., median, average, etc.) of the metabolite amount of metabolite HYA indicated by the reference subject metabolite data included in the reference subject data group, or the message "Your level of metabolite HYA is lower than that of the reference subject data group" when the metabolite amount of metabolite HYA indicated by the subject's metabolite data is lower than the statistical value (e.g., median, average, etc.) of the metabolite amount of metabolite HYA indicated by the reference subject metabolite data included in the reference subject data group.

[0068] Furthermore, the message for each metabolite may be set according to a predetermined range of values ​​(e.g., 80 points or more, or 60 points or more and less than 80 points, etc.) to which the metabolite score corresponding to the metabolite belongs. In this case, the message output unit 180 extracts and outputs a corresponding message according to the predetermined range of values ​​to which the metabolite score belongs.

[0069] Furthermore, when a message is set for each metabolite, the message may further include content related to the metabolite (e.g., content related to the function of the metabolite). Specifically, the message may be, for example, a message related to the function of the metabolite, such as "HYA is known to have anti-allergic effects," or a message encouraging lifestyle improvements, such as "Try to increase or supplement these metabolites." This allows the subject or medical institution to understand the function of the metabolite, and may motivate the subject, in particular, to improve their health.

[0070] The message containing the metabolite-related content may be set, for example, according to the magnitude relationship between the metabolite data and a predetermined threshold, or according to a predetermined value range to which the disease score corresponding to the metabolite belongs. In this case, the message containing the metabolite-related content may be output when the metabolite amount of the metabolite indicated by the subject's metabolite data is equal to or less than a predetermined threshold, or when the disease score corresponding to the metabolite is equal to or less than a predetermined value (e.g., 50 points). In this way, the calculation system 100 can output a message that motivates a subject whose metabolite amount is, for example, low in the distribution of the reference subject data group, to improve their health.

[0071] The message may also be a message according to the overall score. Examples of messages according to the overall score include a message indicating the overall score, such as "Your overall score is 80 points," a message regarding the amount of metabolites, such as "You have a very high amount of metabolites," a message regarding the position in the distribution of the reference data group, such as "You are ranked at the top of all subjects," and a message regarding the subject's health status, such as "Your current lifestyle and dietary habits are considered to be very good."

[0072] Fig. 6 is a diagram showing examples of message templates stored in the storage unit 110. The example message template shown in Fig. 6 shows examples of a plurality of message templates corresponding to disease scores. As shown in Fig. 6, the plurality of message templates corresponding to disease scores may, for example, indicate that the disease risk for each target disease is "high," "slightly high," "average," "slightly low," or "low" according to the disease score.

[0073] Next, a specific example will be described below regarding the message output process by the message output unit 180. The message output unit 180 outputs a message to the subject, including content related to the subject's risk of the target disease corresponding to the calculated disease score, based on a plurality of message templates set in advance according to the disease score.

[0074] In this case, first, the message output unit 180 extracts a message corresponding to a predetermined value range to which the disease score belongs, based on the disease score. More specifically, when the disease score is 80 points, the message output unit 180 extracts at least one message that is set to be output when the disease score is 80 points (i.e., for example, the message "Your risk of allergic disease tends to be low").

[0075] Then, the message output unit 180 outputs at least one of the extracted messages.

[0076] This allows the message output unit 180 to output, for example, a message according to the disease score (for example, "Your risk of allergic disease tends to be low").

[0077] In addition, the message output unit 180 can output a message that further includes content regarding at least one metabolite that corresponds to the magnitude relationship between the extracted subject metabolite data and a predetermined threshold, based on multiple message templates that correspond to the magnitude relationship between the metabolite data and a predetermined threshold.

[0078] In this case, the message output unit 180 determines the magnitude relationship between the metabolite amount indicated by the metabolite data of a certain metabolite A and a predetermined threshold (for example, a statistical value (for example, a median, an average, etc.) of the metabolite amount indicated by the metabolite data of metabolite A included in the reference individual data group). Then, the message output unit 180 extracts at least one message according to the determined magnitude relationship.

[0079] Then, message output unit 180 outputs at least one of the extracted message templates as a message.

[0080] This allows the message output unit 180 to output, for example, a different message for each metabolite (for example, "Your level of metabolite HYA is high compared to the reference individual data group." or "Your level of metabolite HYA is low compared to the reference individual data group.").

[0081] In addition, the message output unit 180 can output a message that further includes content regarding at least one metabolite that corresponds to the statistical correlation between the extracted subject metabolite data and the reference subject data group, based on multiple message templates corresponding to the statistical correlation.

[0082] In this case, first, the message output unit 180 extracts at least one message according to a predetermined value range to which the metabolite score corresponding to the metabolite belongs, based on the metabolite score and the message template.

[0083] Then, message output unit 180 outputs at least one of the extracted message templates as a message.

[0084] This allows the message output unit 180 to output, for example, a different message for each metabolite (for example, "Your level of metabolite HYA is high compared to the reference individual data group." or "Your level of metabolite HYA is low compared to the reference individual data group.").

[0085] Furthermore, the message output unit 180 can output a message according to the combination of the statistical association between the extracted subject metabolite data and the reference subject data group, and the disease score.

[0086] Specifically, first, the message output unit 180 extracts at least one message corresponding to the disease score and the metabolite score based on the disease score, the metabolite score, and the message template. At this time, the message output unit 180 extracts, for example, a message corresponding to a predetermined range of values ​​to which the disease score belongs and to which the metabolite score corresponding to the metabolite belongs.

[0087] Then, message output unit 180 outputs at least one of the extracted message templates as a message.

[0088] As a result, the message output unit 180 can output, for example, to a subject whose disease score is below a predetermined value, content related to metabolites among multiple metabolites that have a score below the predetermined value (for example, "HYA is known to have anti-allergic effects" or "Your level of the metabolite HYA is low compared to the reference subject data group."), while not outputting messages related to metabolites to a subject whose disease score is above the predetermined value.

[0089] It should be noted that the message output process by the message output unit 180 described in this embodiment is merely an example, and the message output process by the message output unit 180 is not limited to this.

[0090] In addition, the message output unit 180 can appropriately replace "disease score" with "total score" and output a message according to the total score, and in the message output process based on at least one of the disease score and metabolite score, it can also output a message taking into account the total score.

[0091] The message output unit 180 may also combine at least one extracted message template and output the combined message as one or more messages. The message output unit 180 may also combine a fixed message template that is set in advance and does not correspond to a score (at least one of the metabolite score, the disease score, and the total score) with the extracted message template and output the combined message as one or more messages.

[0092] The object output unit 190 is an object that displays the distribution of the reference subject data group, and can output an object that displays the portion of the object that corresponds to the disease score in a different manner.

[0093] The object output unit 190 can output, for example, a frequency distribution that displays the distribution of the reference individual data group as an object.

[0094] The report output unit 195 can generate and output a report including a total score, a disease score, a message, and an object. The report may be, for example, paper or electronic data (e.g., PDF (Portable Document Format)). The report may also be, for example, display data that displays the report on the output destination system 300 (e.g., a display unit of the output destination system).

[0095] Fig. 7 is a diagram showing an example of a report output by the calculation system 100. The report shown in Fig. 7 is, for example, a report including a disease score and a message. The report shown in Fig. 7 includes, for example, an area 710 for displaying data related to the target disease, an area 721 for displaying the disease score, an area 722 for displaying the disease scores from the previous and previous-previous periods, and an area 730 for displaying a message.

[0096] The message displayed in area 730 may further include, for example, an area for displaying a summary of the message as “Evaluation” and an area for displaying details of the message as “Comments.” The message displayed in area 730 may include, for example, a message including content related to the risk of the target disease according to the disease score, and a message including content related to at least one metabolite corresponding to the target disease.

[0097] Fig. 8 is a diagram showing an example of a report output by the calculation system 100. The report shown in Fig. 8 is, for example, a report including a total score and a message. The report shown in Fig. 8 includes, for example, an area 810 for displaying the title of the report, an area 821 for displaying the total score, an area 822 for displaying the total scores from the previous and previous previous times, and an area 830 for displaying a message.

[0098] The message displayed in area 830 may further include, for example, an area for displaying a summary of the message as “rating” and an area for displaying details of the message as “comments.” The message displayed in area 830 may include, for example, a message containing content related to the subject's health condition according to the overall score.

[0099] Fig. 9 is a diagram showing an example of a report output by the calculation system 100. The report shown in Fig. 9 is a report including an object displaying the distribution of the reference subject data group. The report shown in Fig. 9 includes, for example, an area 910 displaying an object displaying the distribution of the reference subject data group, and an area 920 displaying the numerical values ​​of the subject metabolite data and the statistical values ​​(e.g., median, mean, etc.) of the reference subject data group.

[0100] Region 910 further includes region 915, which displays the portion of the object corresponding to the disease score in a different manner. Region 920 further includes region 925, which displays the numerical values ​​of the subject's metabolite data, and region 925 is displayed in a different manner from the other regions.

[0101] In addition, different aspects include, for example, highlighting using a rectangle of a predetermined color, surrounding with a line of a predetermined color, displaying with letters of a predetermined color, displaying letters in bold or italics, etc., but are not limited to these.

[0102] Furthermore, the reports shown in FIGS. 7 to 9 are merely examples, and the layout of the reports and the displayed contents are not limited to these.

[0103] The report output unit 195 can output the report to, for example, a medical institution, allowing the subject to receive the score calculation service provided by the calculation system 100 as part of a diagnosis (for example, a periodic medical checkup) that the subject has requested from a medical institution.

[0104] When the score output unit 170 and the message output unit 180 output the score and message to the destination system 300, the destination system 300 can create a report displaying the score and message based on the acquired score and message. This allows the user of the destination system 300 (e.g., a medical institution) to create a report in the layout and format of their choice.

[0105] FIG. 10 is a flowchart showing an example of processing in the calculation system 100.

[0106] First, the correspondence data acquisition unit 120 acquires correspondence data, and the reference individual data group acquisition unit 130 acquires the reference individual data group (S1001). The metabolite data acquisition unit 140 acquires subject metabolite data of multiple metabolites in the subject (S1002). The metabolite data extraction unit 150 extracts subject metabolite data of at least one metabolite from the subject metabolite data of the multiple metabolites (S1003).

[0107] Then, the score calculation unit 160 calculates the disease score and the total score, and the score output unit 170 outputs the disease score and the total score (S1004). The message output unit 180 outputs a message according to the score, and the object output unit 190 outputs an object that displays the distribution of the reference subject data group and displays the part of the object that corresponds to the disease score in a different manner (S1005). The report output unit 195 generates and outputs a report that displays the disease score, the total score, the message, and the object (S1006).

[0108] Next, an example of a hardware configuration in which the calculation system 100 is realized by a computer 1100 will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the hardware configuration of the computer 1100.

[0109] As shown in FIG. 11, a computer 1100 includes, for example, a processor 1101, a memory 1102, a storage device 1103, an input I / F unit 1104, a data I / F unit 1105, a communication I / F unit 1106, and a display device 1107.

[0110] Computer 1100 may be, for example, a server computer, a personal computer (e.g., desktop, laptop, tablet, etc.), a media computing platform (e.g., cable, satellite set-top box, digital video recorder, etc.), a handheld computing device (e.g., PDA, email client, etc.), or any other type of computing or communications platform.

[0111] The processor 1101 is a control unit that controls various processes in the computer 1100 by executing programs stored in the memory 1102 .

[0112] The memory 1102 is a storage medium such as a RAM (Random Access Memory), etc. The memory 1102 temporarily stores the program code of the program executed by the processor 1101 and data required when the program is executed.

[0113] The storage device 1103 is a non-volatile storage medium such as a hard disk drive (HDD), flash memory, etc. The storage device 1103 stores an operating system and various programs for realizing the above-mentioned components.

[0114] The input I / F unit 1104 is a device for receiving input from a user. The input I / F unit 1104 is, for example, a keyboard, a mouse, a touch panel, various sensors, a wearable device, etc. The input I / F unit 1104 may be connected to the computer 1100 via an interface such as a USB.

[0115] The data I / F unit 1105 is a device for inputting data from outside the computer 1100. The data I / F unit 1105 is, for example, a drive device for reading data stored in various storage media. The data I / F unit 1105 may be provided outside the computer 1100. When the data I / F unit 1105 is provided outside the computer 1100, the data I / F unit 1105 is connected to the computer 1100 via an interface such as a USB.

[0116] The communication I / F unit 1106 is a device for performing data communication via a network such as the Internet, either wired or wirelessly, with devices external to the computer 1100. The communication I / F unit 1106 may be provided external to the computer 1100. When the communication I / F unit 1106 is provided external to the computer 1100, the communication I / F unit 1106 is connected to the computer 1100 via an interface such as a USB.

[0117] The display device 1107 is a device for displaying various types of information. The display device 1107 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, a display of a wearable device, or the like. The display device 1107 may be provided outside the computer 1100. When the display device 1107 is provided outside the computer 1100, the display device 1107 is connected to the computer 1100 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F unit 1104, the display device 1107 may be configured as an integral part of the input I / F unit 1104.

[0118] The above describes one embodiment of the present disclosure. The calculation system 100 acquires metabolite data for a subject, extracts metabolite data for at least one metabolite corresponding to a target disease based on the correspondence between metabolites and diseases, calculates a disease score for the subject based on the statistical correlation between the extracted metabolite data and a reference subject data group, and outputs the disease score. This allows the calculation system 100 to calculate the risk of developing a specific disease based on the metabolite data.

[0119] Furthermore, the calculation system 100 can extract metabolite data of at least one metabolite from a subject for each of a plurality of target diseases and calculate a disease score, thereby enabling the calculation system 100 to calculate the risk of contracting a specific disease for each of a plurality of target diseases.

[0120] Furthermore, the calculation system 100 can calculate and output a total score based on the disease scores for multiple target diseases, thereby enabling the calculation system 100 to evaluate the health condition of a subject based on the risk of contracting a specific disease.

[0121] Furthermore, the calculation system 100 can calculate a disease score based on the rank of the subject in the distribution of the reference subject data group. This allows the calculation system 100 to compare the distribution of the reference subject data group with the subject's metabolite data to calculate a disease score.

[0122] Furthermore, the calculation system 100 can output a message including content related to the subject's risk of the target disease corresponding to the disease score, thereby enabling, for example, the subject or a medical institution to understand the subject's risk of the target disease.

[0123] Furthermore, the calculation system 100 can output a message including information about at least one metabolite corresponding to the statistical correlation between the extracted metabolite data and the data group of the reference subjects, thereby enabling, for example, the subject or a medical institution to understand information about metabolites with lower scores than the reference subjects.

[0124] Furthermore, the calculation system 100 can output a message according to the statistical correlation between the extracted metabolite data and the data group of reference individuals, and the disease score, thereby enabling, for example, the subject or a medical institution to understand the subject's risk of the target disease.

[0125] Furthermore, the calculation system 100 can output an object that displays the distribution of the reference subject data group, and that displays the portion of the object that corresponds to the disease score in a different manner, thereby enabling, for example, the subject or a medical institution to intuitively grasp the position of the subject's disease score in the distribution of the reference subject data group.

[0126] It should be noted that the present embodiment is provided to facilitate understanding of the present disclosure and is not intended to limit the present disclosure. The present disclosure may be modified or improved without departing from the spirit thereof, and equivalents thereof are also included in the present disclosure.

[0127] In addition, in this disclosure, a "unit" does not simply mean a physical means, but also includes cases where the functions of the "unit" are realized by software. Furthermore, the functions of one "unit" or device may be realized by two or more physical means, devices, or software, and the functions of two or more "units" or devices may be realized by one physical means, device, or software.

[0128] 100 Calculation system, 110 Storage unit, 120 Correspondence data acquisition unit, 130 Reference subject data group acquisition unit, 140 Metabolite data acquisition unit, 150 Metabolite data extraction unit, 160 Score calculation unit, 170 Score output unit, 180 Message output unit, 190 Object output unit, 195 Report output unit, 200 Measurement system, 300 Output destination system

Claims

1. A metabolite data acquisition unit that acquires subject metabolite data regarding the amounts or concentrations of a plurality of metabolites in a subject; a metabolite data extraction unit that extracts, from the acquired subject metabolite data, subject metabolite data of at least one metabolite corresponding to a target disease for which a score is calculated based on the correspondence between the metabolite and the disease; a score calculation unit that calculates a disease score regarding the risk of the target disease in the subject based on the statistical relevance between the extracted subject metabolite data and a reference data group including reference metabolite data regarding the amounts or concentrations of the at least one metabolite in a plurality of reference subjects acquired in advance; and a score output unit that outputs the disease score. A calculation system comprising these components.

2. The target disease includes a plurality of target diseases. The metabolite data extraction unit extracts subject metabolite data of at least one metabolite for each of the plurality of target diseases. The score calculation unit calculates the disease score for each of the plurality of target diseases. The calculation system according to claim 1.

3. The score calculation unit further calculates an overall score regarding the health status of the subject based on the disease scores for each of the plurality of target diseases. The score output unit outputs the overall score. The calculation system according to claim 2.

4. The statistical relevance includes the rank in the distribution of the data group. The score calculation unit calculates the disease score based on the rank of the subject in the distribution of the reference data group. The calculation system according to any one of claims 1 to 3.

5. Further comprising a message output unit that outputs a message addressed to the subject, the message including content regarding the risk of the target disease in the subject corresponding to the calculated disease score, based on a plurality of message templates set in advance according to the disease score. The calculation system according to claim 1 or 2.

6. The message output unit generates the message further including content regarding the at least one metabolite corresponding to the magnitude relationship between the extracted subject metabolite data and the predetermined threshold, based on a plurality of message templates set in advance according to the magnitude relationship between the metabolite data and the predetermined threshold. The calculation system according to claim 5.

7. The calculation system according to claim 6, wherein the message output unit outputs the message according to the magnitude relationship between the extracted subject metabolite data and the predetermined threshold value, and the disease score.

8. The calculation system according to claim 7, further comprising an object output unit that is an object for displaying the distribution of the reference person data group and outputs an object that displays, in different manners, a location corresponding to the disease score in the object.

9. A calculation method, wherein a computer: obtains subject metabolite data regarding a plurality of metabolites in a subject; extracts, from the obtained subject metabolite data, subject metabolite data of at least one metabolite corresponding to a target disease for which a score is to be calculated, based on the correspondence between the metabolite and the disease; calculates a disease score regarding the risk of the target disease in the subject, based on the statistical relevance between the extracted subject metabolite data and a reference person data group including reference person metabolite data of the at least one metabolite in a plurality of pre-acquired reference persons; and outputs the disease score.

10. A calculation program for causing a computer to realize: a metabolite data acquisition unit that obtains subject metabolite data regarding a plurality of metabolites in a subject; a metabolite data extraction unit that extracts, from the obtained subject metabolite data, subject metabolite data of at least one metabolite corresponding to a target disease for which a score is to be calculated, based on the correspondence between the metabolite and the disease; a score calculation unit that calculates a disease score regarding the risk of the target disease in the subject, based on the statistical relevance between the extracted subject metabolite data and a reference person data group including reference person metabolite data of the at least one metabolite in a plurality of pre-acquired reference persons; and a score output unit that outputs the disease score.

Images