Information processing system and information processing method

Abstract

[PROBLEM] To make it easy to numerically express changes in the color of a coloring reagent. [SOLUTION] An information processing system (1, 2) of an embodiment of the present invention comprises: an acquisition unit (101, 301) that acquires a captured image in which captured is the color of a coloring reagent, in a coloring reaction using a target biological sample; and a calculation unit (102, 302) that calculates, on the basis of the captured image, a feature amount obtained by numerically expressing the color.

Description

Information processing system and information processing method

[0001] The present invention relates to an information processing system and an information processing method.

[0002] One method for analyzing biological samples such as blood and urine is to use a color reagent (dye) that undergoes a color reaction when mixed with the sample. For example, various components contained in the biological sample can be analyzed by visually comparing the color of the reaction solution after the color reaction with a color legend or by measuring the spectral absorbance.

[0003] International Publication No. 2020 / 097043

[0004] However, although the more color reagents used, the more versatile the analysis becomes, the more time and effort is required to visually observe and measure color changes.

[0005] An object of the present invention is to provide an information processing system and an information processing method that can easily digitize the color change of a color reagent.

[0006] In order to solve the above-mentioned problems and achieve the object, the present invention provides an information processing system comprising an acquisition unit that acquires an image of the color of a color reagent in a color reaction using a target biological sample, and a calculation unit that calculates a feature that quantifies the color based on the image.

[0007] The present invention also provides an information processing method that includes acquiring an image of the color of a color reagent in a color reaction using a target biological sample, and calculating a feature that quantifies the color based on the image.

[0008] The present invention also provides an information processing method that includes acquiring an image capturing the color of a color reagent in a color reaction using at least one biological sample of a subject's saliva, urine, whole blood, plasma, and serum, and determining a health index related to the subject's health based on the image capturing the color.

[0009] The present invention also provides an information processing system that includes an acquisition unit that acquires an image of the color of a color reagent in a color reaction using at least one biological sample of a subject's saliva, urine, whole blood, plasma, or serum, and a determination unit that determines a health index related to the subject's health based on the image.

[0010] The present invention also provides an information processing system that includes a learning unit that performs machine learning for a plurality of subjects that provide training data using the features of the subjects and measurement values ​​of health indicators related to the subjects' health.

[0011] According to the present invention, it is possible to provide an information processing system and an information processing method that can easily digitize the color change of a color reagent.

[0012] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system. FIG. 2 is a diagram illustrating an example of the configuration of an imaging unit. FIG. 3 is a diagram illustrating an example of the hardware configuration of an information processing device. FIG. 4 is a flowchart illustrating a processing procedure of the information processing system. FIG. 5 is a diagram illustrating processing by a calculation unit. FIG. 6 is a diagram illustrating a trained model of the information processing system. FIG. 7 is a diagram illustrating an example of the configuration of the information processing system.

[0013] Hereinafter, an information processing system and an information processing method according to embodiments will be described with reference to the drawings. Note that the following embodiments are not limited to the following description. Furthermore, each embodiment can be combined with other embodiments or conventional techniques as long as there is no contradiction in the processing content.

[0014] In the following embodiments, a "subject" refers to a person who is the subject of analysis of a biological sample using a color reaction, and is typically a patient, but may also be a healthy person who is the subject of analysis for the purpose of understanding their health condition. Furthermore, the subject of analysis is not necessarily limited to humans, and may also be, for example, an animal such as a pet or livestock. When the subject of analysis also includes animals other than humans, it will be referred to as a "subject" or "specimen."

[0015] Furthermore, the term "user" refers to a person who uses the information processing system according to the embodiment, and is typically a medical professional, but does not necessarily have to be a medical professional. For example, the user may be the subject himself / herself, or a close relative, friend, or acquaintance of the subject.

[0016] Furthermore, the "biological sample" refers to at least one of a subject's saliva, feces, urine, whole blood, plasma, and serum.

[0017] (Embodiment) The configuration of an information processing system 1 according to the present invention will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1. As shown in Fig. 1, the information processing system 1 according to the embodiment includes an information processing device 10 and an image capturing unit 20. The information processing device 10 and the image capturing unit 20 are connected to each other by any communication means. As the communication means, any network such as a LAN (Local Area Network) or a WAN (Wide Area Network) can be applied.

[0018] The information processing device 10 is a server device that provides a service for analyzing biological samples using a color reaction. For example, the information processing device 10 includes an acquisition unit 101, a calculation unit 102, a determination unit 103, and an output control unit 104. The acquisition unit 101, the calculation unit 102, the determination unit 103, and the output control unit 104 will be described later.

[0019] The photographing unit 20 photographs the colors of the multiple color reagents in the color reaction and sends the photographed image to the information processing device 10. Here, the configuration of the photographing unit 20 provided in the information processing system 1 will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of the configuration of the photographing unit 20. As shown in FIG. 2, the photographing unit 20 has a photographing device 21, a color sensor array 22, a box 23, and a fixing fixture 24.

[0020] The image capturing device 21 is a device that captures an optical image (captured image) that is visible using visible light. For example, the image capturing device 21 corresponds to a smartphone equipped with a camera module capable of capturing optical images or a camera capable of capturing optical images. For example, the image capturing device 21 captures an image of a color sensor array that has undergone a color reaction with a biological sample of a subject.

[0021] The color sensor array 22 is a multi-well plate (e.g., a 96-well plate) in which multiple color reagents are arranged in individual wells (holes). The bottom of each well of the multi-well plate is transparent, and color changes in the color reagents in each well can be seen from the bottom.

[0022] Here, examples of color reagents that can be used for any biological sample include picric acid, methyl violet, malachite green, o-cresol red, thymol blue, 2,4-dinitrophenol, Congo red, methyl orange, methyl yellow, bromophenol blue, bromocresol green, bromophenol red, methyl red, litmus (blue), litmus (red), methyl purple, bromocresol purple, chlorophenol red, bromothymol blue, p-nitrophenol, neutral red, and phenol red. Red, p-naphtholphthalein, cresol red, phenolphthalein, thymolphthalein, alizarin yellow, 1,3,5-trinitrobenzene, nitrazine yellow, rosolic acid, bromopyrogallol red, pyrocatechol violet, 4-(4-diethylaminostyryl)-1-methylpyridinium iodide, Brooker merocyanine dye, Nile red, 2-[2-cyano-4-[(N-succinimidyloxy)carbonyl]phenyl]-1,3a,6a-triazapentalene, Reichardt's reagent, 4-dimethylamino-4-nitro Rostilbene, phthalocyanine, 15-crown 4 [4-(2,4-dinitrophenylazo)phenol], 18-crown 5 [4-(2,4-dinitrophenylazo)phenol], Disperse Orange 25, flavone, 3-hydroxyflavone, chalcone, cyanidin chloride, cyanine, pelargonidin chloride, peonidin, delphinidin, petunidin, malvidin, α-carotene, β-carotene, γ-carotene, δ-carotene, ε-carotene, lycopene, 9-anthryldiazomethane, DMEQ-hydrazide, rhodamine B, Alcian blue , Fluorescein, Acridine Orange Base, Pigment Blue 15, Iron(II) Phthalocyanine, Magnesium(II) Phthalocyanine, Zinc Phthalocyanine, Cobalt(II) Phthalocyanine, Dilithium Phthalocyanine, Tin(II) Phthalocyanine, Sodium Phthalocyanine, Aluminum Phthalocyanine Chloride, Lead(II) Phthalocyanine, Titanyl Phthalocyanine, Manganese(III) Tetraphenylporphyrin Chloride, 5,10,15,20-Tetraphenylporphyrinatozinc, 5,10,15,20-Tetrakis(2,4,Examples of suitable color reagents include one or more of 5,10,15,20-tetrakis(pentafluorophenyl)porphyrinatozinc, 5,10,15,20-tetrakis(4-methoxyphenyl)porphyrinatocobalt, 5,10,15,20-tetrakis(pentafluorophenyl)porphyrinatozinc, and 5,10,15,20-tetrakis(4-methoxyphenyl)porphyrinatocobalt. Among the above color reagents, more preferred are one or more of thymol blue, bromocresol green, methyl red, bromocresol purple, chlorophenol red, bromothymol blue, phenol red, bromopyrogallol red, Nile red, Reichardt's reagent, rhodamine B, alcian blue, magnesium(II) phthalocyanine, zinc phthalocyanine, sodium phthalocyanine, and phthalocyanine chloroaluminum.

[0023] Furthermore, as a more preferred color reagent, one to five known color reagents can be appropriately selected depending on the biological sample. For example, when the biological sample is urine, the color reagent is preferably one to three of bromocresol green, bromocresol purple, Reichardt's reagent, and thymol blue. When the biological sample is saliva, the color reagent is preferably one to four of phenol red, Reichardt's reagent, bromothymol blue, bromocresol green, bromopyrogallol red, methyl red, and thymol blue. When the biological sample is plasma, the color reagent is preferably one to four of bromocresol green, Nile red, bromocresol purple, phenol red, methyl red, and chlorophenol red. Furthermore, when the biological sample is feces, the color reagent is preferably three to five of the following color reagents: bromocresol green, methyl red, Reichardt's reagent, bromocresol purple, bromopyrogallol red, bromothymol blue, phenol red, and chlorophenol red.

[0024] The box 23 is a housing that houses the color sensor array 22 and is equipped with a light source 23a. The box 23 may be open on one side as shown in FIG. 2, or may not be open on all sides. The light source 23a is installed above the housed color sensor array 22, but in a position that is not directly above the color sensor array 22, in order to obtain highly accurate captured images. The box 23 has white inner walls that reflect light from the light source 23a. In other words, the box 23 uses not only direct light from the light source 23a but also indirect light reflected by the inner walls to irradiate the color sensor array 22 with light as uniformly as possible (without significant bias).

[0025] The fixing fixture 24 fixes the relative positions of the image capture device 21 and the color sensor array 22. The fixing fixture 24 has an opening 24a through which light transmitted through the color sensor array 22 enters, and the color sensor array 22 is supported by four side walls that define the opening 24a. The fixing fixture 24 has a fixing position that fixes the image capture device 21 at a position where the light entering through the opening 24a can be focused. In the example shown in FIG. 2 , the image capture device 21 is inserted into the opening in the side wall of the fixing fixture 24 with its lens facing upward and fixed at the fixing position. If the bottom surface of the color sensor array 22 is substantially flat, fixing the image capture device 21 to the fixing fixture 24 as shown in FIG. 2 can obtain a more accurate captured image. Furthermore, the inner wall of the fixing fixture 24 is black, which reduces reflection of light transmitted through the color sensor array 22 on the inner wall.

[0026] In other words, in the imaging unit 20, light emitted from the light source 23a is directly or indirectly irradiated onto the upper surface of the color sensor array 22, is absorbed according to the color of the reflecting reagent in each well, and reaches the lens of the imaging device 21.

[0027] 1 and 2 are merely examples, and the present invention is not limited thereto. For example, the image capturing unit 20 does not necessarily have to be connected to the information processing device 10. Images captured by the image capturing unit 20 may be stored in the information processing device 10 via any portable recording medium, such as a DVD (Digital Versatile Disc).

[0028] 2 does not necessarily have to include the box 23 and the fixing device 24. For example, the imaging unit 20 may include the imaging device 21 and the color sensor array 22 after the color reaction.

[0029] Furthermore, the color sensor array 22 is not limited to a multi-hole plate, but may be a test strip on which a plurality of color reagents are arranged at individual positions. The test strip can be made of any material, such as paper or plastic (resin).

[0030] Next, the hardware configuration of the information processing device 10 included in the information processing system 1 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the hardware configuration of the information processing device 10.

[0031] As shown in FIG. 3, the information processing device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an auxiliary storage device 14, an input device 15, a display device 16, and an external I / F (Interface) 17.

[0032] The CPU 11 is a processor (processing circuit) that executes a program to comprehensively control the operation of the information processing device 10 and realize various functions of the information processing device 10. For example, the functions of the acquisition unit 101, the determination unit 102, and the output control unit 103 of the information processing device 10 are realized by the CPU 11.

[0033] The ROM 12 is a non-volatile memory that stores various data (information written during the manufacturing stage of the information processing device 10) including a program for starting up the information processing device 10. The RAM 13 is a volatile memory that has a work area for the CPU 11. The auxiliary storage device 14 stores various data such as the program executed by the CPU 11. The auxiliary storage device 14 is configured, for example, by a hard disk drive (HDD), a solid state drive (SSD), or the like.

[0034] The input device 15 is a device for performing various operations by the operator of the information processing device 10. The input device 15 is configured by, for example, a mouse, a keyboard, a touch panel, or hardware keys.

[0035] The display device 16 displays various types of information. For example, the display device 16 displays image data, model data, a GUI (Graphical User Interface) for receiving various operations from an operator, medical images, etc. The display device 16 is configured as, for example, a liquid crystal display, an organic EL (Electro Luminescence) display, or a cathode ray tube display. Note that the input device 15 and the display device 16 may be integrated into one unit, for example, in the form of a touch panel.

[0036] The external I / F 17 is an interface for connecting (communicating) with any external device such as a server device 20 .

[0037] 3 is merely an example, and the present invention is not limited to this. For example, the hardware configuration of the information processing device 10 may be any configuration of a known computer or workstation.

[0038] The processing procedure of the information processing device 10 included in the information processing system 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the processing procedure of the information processing system 1. In the description of Fig. 4, Fig. 5 and Fig. 6 will be referred to as appropriate.

[0039] 4, the user performs a color reaction using a biological sample from a subject (step S101). For example, the user brings the biological sample obtained from the subject into contact with the color sensor array 22 to perform a color reaction.

[0040] Next, the user photographs the result of the color reaction of the subject (step S102). For example, the user photographs the color sensor array 22 after the color reaction using the photographing unit 20 shown in FIG.

[0041] Then, the photographing unit 20 transmits the photographed image to the information processing device 10 (step S103). As a result, the acquisition unit 101 of the information processing device 10 acquires the photographed image of the color sensor array 22 after the color reaction. Note that this process may be performed by any communication means or via any portable recording medium.

[0042] The calculation unit 102 of the information processing device 10 then calculates the color score of the subject based on the captured image (step S104). The color score is an example of a "feature amount" that quantifies the color of the color reagent. The color of the color reagent is represented by pixel values ​​in the RGB color space, Lab color space, CMYK color space, HSV color space, and Gray color space.

[0043] Here, the processing of the calculation unit 102 of the information processing device 10 will be described with reference to Fig. 5. Fig. 5 is a diagram for explaining the processing of the calculation unit 102.

[0044] The calculation unit 102 generates five captured images represented in the RGB color space, Lab color space, CMYK color space, HSV color space, and Gray color space from the captured image acquired by the acquisition unit 101. For example, if the captured image acquired by the acquisition unit 101 is an image represented in the RGB color space, the calculation unit 102 converts this image into each of the remaining four color spaces. For this conversion process, known image conversion techniques can be applied as appropriate.

[0045] The calculation unit 102 then identifies a region R1 in each image of each color space, in which the colors of the multiple color reagents are depicted. Specifically, the calculation unit 102 identifies the region of each well 22a of the color sensor array 22 from the captured image in which the color sensor array 22 is depicted, using pattern matching processing or the like. The calculation unit 102 then identifies a region R1 that includes a predetermined number of pixels (e.g., 50 pixels x 50 pixels) including the center of each well 22a.

[0046] The calculation unit 102 then detects pixels having outliers from within region R1. If any pixels in region R1 have outliers, the calculation unit 102 excludes the pixels having outliers. For example, the calculation unit 102 detects a region R2 of pixels including outliers from the pixels in region R1 using a known detection technique such as the 3-sigma method. The calculation unit 102 then identifies pixels included in region R3, which is obtained by excluding region R2 from region R1.

[0047] The calculation unit 102 then calculates, as the color score, a statistical value of the pixel values ​​of a predetermined number of pixels included in each of the identified regions R3. For example, the calculation unit 102 calculates, as the color score, a median value of the pixel values ​​of the predetermined number of pixels included in region R3.

[0048] Here, the color score is numerical data consisting of dimensional values ​​calculated from five images represented in five color spaces. For example, an image represented in the RGB color space has three-dimensional pixel values ​​of R, G, and B, so the median (statistical value) calculated from the image represented in the RGB color space is three-dimensional, such as (x1, x2, x3). Similarly, the median calculated from an image represented in the Lab color space is three-dimensional, such as (x4, x5, x6). The median calculated from an image represented in the CMYK color space is four-dimensional, such as (x7, x8, x9, x10). The median calculated from an image represented in the HSV color space is three-dimensional, such as (x11, x12, x13). The median calculated from an image represented in the Gray color space is one-dimensional, such as (x14). That is, the color score is 14-dimensional numerical data (x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14).

[0049] In this way, the calculation unit 102 calculates a color score, which is 14-dimensional numerical data, for each well (coloring reagent).

[0050] Note that the processing content of the calculation unit 102 described above is merely an example, and the present invention is not limited to this. For example, in the above example, the processing of excluding outliers is described, but the calculation unit 102 may convert the outliers to a predetermined value and calculate the feature amount. The predetermined value may be, for example, any statistical value such as the median, average, or mode of the pixel values ​​of the pixels included in region R3.

[0051] In the above example, the process of calculating the color score using all five images represented in five color spaces has been described, but the present invention is not limited to this. For example, the calculation unit 102 can calculate the color score using at least one of the five images represented in the five color spaces, or can calculate the color score using images represented in multiple color spaces, such as two or more, three or more, or four or more.

[0052] Furthermore, in the above example, the process of calculating the median as the color score has been described, but the present invention is not limited to this. For example, the calculation unit 102 can calculate any statistical value, such as the mean value or the mode value, in addition to the median value, as the color score. Furthermore, the calculation unit 102 may calculate the color score by combining any statistical value, such as the median value, the mean value, or the mode value. In this case, even when the mean value is used, 14-dimensional numerical data is obtained, so when the median value and the mean value are combined, the color score becomes 28-dimensional numerical data. In other words, the calculation unit 102 may calculate at least one of the median value, the mean value, and the mode value as the color score.

[0053] Returning to the description of FIG. 4 , the determination unit 103 of the information processing device 10 generates a determination result by inputting the subject's color score into a trained model (step S105). This trained model is trained using the color scores of multiple providers who provide training data and the measured values ​​of the providers' health indices. In other words, the determination result is information indicating the subject's health indices.

[0054] Here, the trained model of the information processing system 1 will be described with reference to FIG. 6. FIG. 6 is a diagram for explaining the trained model of the information processing system 1. The upper part of FIG. 6 shows the processing during training of the trained model, and the lower part of FIG. 6 shows the processing during operation of the trained model. Here, the trained model is constructed in advance and stored in a predetermined storage area (e.g., ROM 12) available to the determination unit 103. The processing of the "learning unit" for constructing the trained model will be described later.

[0055] As shown in the upper part of Figure 6, during learning, machine learning is performed using, for example, color scores based on biological samples from multiple donors 1 to N and health index measurement values. Here, the donor's color score is calculated based on a color reaction using the donor's biological sample. The method for calculating the donor's color score is similar to the method for calculating the subject's color score by the calculation unit 102, and therefore will not be described here. The donor's health index measurement value is a measurement value of the component to be analyzed in the biological sample, such as the creatinine concentration in urine or the concentration or abundance of short-chain fatty acids in feces. Among these health index measurement values, the present invention provides useful results when the concentration or abundance of short-chain fatty acids in feces is used. Examples of short-chain fatty acids in feces include at least one selected from acetic acid, succinic acid, lactic acid, propionic acid, formic acid, butyric acid, isobutyric acid, isovaleric acid, and valeric acid. Particularly useful results are obtained when at least one selected from lactic acid, acetic acid, butyric acid, and propionic acid is used. Health index measurement values ​​can be measured using known measurement techniques. Furthermore, as the machine learning model, a known classification model or a known regression model can be applied as appropriate.

[0056] As shown in the lower part of Figure 6, during operation, the determination unit 103 inputs the subject's color score into a trained model constructed by machine learning, causing the trained model to output a determination result indicating the subject's health index. For example, a machine learning model trained using the creatinine concentration in the donor's urine outputs an estimated value of the creatinine concentration in the subject's urine as a determination result. In this way, the determination unit 103 determines a health index related to the subject's health based on the color score. Note that the health index is an in-vivo substance useful for managing the subject's health, and is therefore also called a health management index.

[0057] The processing content of the determination unit 103 described above is merely an example, and the present invention is not limited thereto. For example, in the above description, a case where the creatinine concentration in urine is estimated as a health index is described, but the present invention is not limited thereto. Any index can be applied as training data for machine learning, as long as it is a component or bacterial amount in a biological sample that can be measured by a known measurement technique.

[0058] Furthermore, the judgment result is not limited to an estimated value of the health index, and may be, for example, a rank (or score) according to the estimated value. For example, if a health index is considered to be more suitable the higher (or lower) the measured value, the estimated value may be classified into any number of ranks such as "A," "B," "C," etc., in ascending order, and the classified rank may be output as the judgment result. Furthermore, if a health index is considered to have a suitable range for its measured value, values ​​within that range may be classified as "A," and values ​​outside the range may be classified into any number of ranks such as "B," "C," etc., depending on the magnitude of the value, and the classified rank may be output as the judgment result.

[0059] 6 can be executed at any time before the operation process is executed. The learning process can also be executed to update (additionally learn) an already generated trained model.

[0060] Returning to the description of Fig. 4, the output control unit 104 outputs the determination result (step S106). For example, the output control unit 104 may display the determination result on the display device 16 or store it in the ROM 12. The output control unit 104 may also transmit the determination result to an information processing terminal that can be viewed by the user. The information processing terminal may display the determination result transmitted from the output control unit 104 on a predetermined display device or store it in a predetermined storage device.

[0061] As described above, in the information processing system 1 according to the present invention, the acquisition unit 101 of the information processing device 10 acquires a captured image of the color of a color reagent in a color reaction using a biological sample from a subject. The calculation unit 102 calculates a feature amount that quantifies the color based on the captured image. This allows the information processing system 1 according to the present invention to easily quantify the color change of the color reagent.

[0062] Furthermore, in the information processing system 1, the determination unit 103 determines a health index related to the subject's health based on the feature amount. This makes it easy for the information processing system 1 to construct a machine learning model using the feature amount, thereby simplifying the analysis of biological samples using color reactions. Specifically, the information processing system 1 can easily perform multifaceted analysis of biological samples using many color reagents.

[0063] Furthermore, the information processing system 1 can analyze not only human biological samples but also biological samples obtained from animals such as pets and livestock, which is considered to be particularly useful for understanding the health status of animals that cannot be interviewed.

[0064] Note that the content described in the above embodiment is merely an example, and the present invention is not limited thereto. For example, in the above embodiment, the process of calculating the color score using the captured image of the color sensor array 22 after the color reaction was described, but the captured image of the color sensor array 22 before the color reaction can also be used. For example, it is also possible to generate a difference image between the captured images before and after the color reaction, and calculate the color score from this difference image.

[0065] (Learning Unit) The information processing system according to the present invention may also include a learning function for constructing the trained model described in the above embodiment.

[0066] The configuration of an information processing system 2 according to the present invention will be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of the configuration of the information processing system 2. As shown in Fig. 7, the information processing system 2 includes an information processing device 30 and an imaging unit 40. The hardware configuration of the information processing device 30 is basically the same as the hardware configuration of the information processing device 10 shown in Fig. 3, and therefore a description thereof will be omitted. Furthermore, the configuration of the imaging unit 40 is basically the same as the configuration of the imaging unit 20 shown in Fig. 2, and therefore a description thereof will be omitted.

[0067] The information processing device 30 is a server device that constructs a trained model for determining a subject's health index. For example, the information processing device 30 includes an acquisition unit 301, a calculation unit 302, a learning unit 303, and an output control unit 304. The configurations of the acquisition unit 301, calculation unit 302, and output control unit 304 shown in Fig. 7 are basically the same as the configurations of the acquisition unit 101, calculation unit 102, and output control unit 104 shown in Fig. 1, and therefore description thereof will be omitted.

[0068] Here, the learning unit 303 performs machine learning using color scores based on biological samples from multiple donors 1 to N and health index measurement values ​​to construct a trained model for determining the health index of the subject. For example, the learning unit 303 performs the machine learning described in the upper part of Figure 6 to generate a trained model that receives the subject's color score as input and outputs a determination result indicating the subject's health index. The learning unit 303 stores the generated trained model in any storage area available to the determination unit 103.

[0069] That is, the learning method according to the present invention performs machine learning for a plurality of providers who provide training data, using the features of the providers and the measured values ​​of the health indices of the providers.

[0070] Although the case where the information processing device 30 includes the learning unit 303 has been described here, the present invention is not limited to this. For example, the learning unit 303 may be included in the information processing device 10.

[0071] Furthermore, when generating a trained model that outputs a judgment result indicating the health index of animals such as pets and livestock, it is preferable that the living organisms that provide the biological samples for training are animals rather than humans. When the living organisms that provide the biological samples for training include animals other than humans, they are referred to as "subjects (experimental subjects)."

[0072] According to the embodiment and modified examples described above, the color change of the color reagent can be easily quantified.

[0073] The programs executed by the information processing systems 1 and 2 according to the above-described embodiments and modifications may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD, or a USB (Universal Serial Bus), or may be provided or distributed via a network such as the Internet. Also, various programs may be provided by being pre-installed in a non-volatile storage medium such as a ROM.

[0074] The above-described embodiment can be arbitrarily combined with the above-described modified examples, and the above-described modified examples may be arbitrarily combined with each other.

[0075] [Examples] The present invention will be described in more detail below based on examples, but the present invention is not limited thereto. In these examples, imaging units (measurement devices) and machine learning models corresponding to Examples 1 to 33 shown in Tables 1 to 7 were constructed, and the accuracy rate or coefficient of determination was evaluated as an index of the estimation accuracy of health indices. Note that Comparative Example 1 is the result of a human judge visually classifying 20 images without using a machine learning model, using one actual positive example and one actual negative example image as reference.

[0076] The biological samples used in this example are described below. Human plasma and urine samples from 20 individuals were obtained from ProteoGenex (USA). Human saliva samples from 20 individuals were obtained from BiomedicaCRO (Ukraine). Human feces samples from 100 individuals were collected from infants within the first year of life.

[0077] The color reagents used in this example are as follows: CR: Chlorophenol Red (Tokyo Chemical Industry Co., Ltd. (TCI)) dissolved in ethanol at a concentration of 1 mM. BB: Bromothymol Blue (Fujifilm Wako) dissolved in ethanol at a concentration of 1 mM. BG: Bromocresol Green (Fujifilm Wako) dissolved in ethanol at a concentration of 1 mM. TB: Thymol Blue (Fujifilm Wako) dissolved in ethanol at a concentration of 1 mM. BP: Bromocresol Purple (Fujifilm Wako) dissolved in ethanol at a concentration of 1 mM. MR: Methyl Red (Fujifilm Wako) dissolved in ethanol at a concentration of 1 mM. PR: Phenol Red (Fujifilm Wako) dissolved in ethanol at a concentration of 0.8 mM. BR: Bromopyrogall Red (Tokyo Chemical Industry Co., Ltd. (TCI)) dissolved in ethanol at a concentration of 0.6 mM. NR: Nile Red (Tokyo Chemical Industry Co., Ltd. (TCI)) dissolved in ethanol at a concentration of 0.5 mM. RDE: Reichardt's reagent (Sigma) dissolved in ethanol at a concentration of 2 mM. RDM: Reichardt's reagent (Sigma) dissolved in methanol (Fujifilm Wako) at a concentration of 2 mM. RDI: Reichardt's reagent (Sigma) dissolved in isopropyl alcohol (Fujifilm Wako) at a concentration of 2 mM.

[0078] In this example, each component was measured using the following kits. Urine x Creatinine: QuantiChrom Protein Creatinine Ratio Assay kit from Bioassay Systems. Urine x Glucose: Cholesterol Assay Kit from Cayman Chemical. Urine x Protein: QuantiChrom Protein Creatinine Ratio Assay kit from Bioassay Systems. Saliva x DHEA: DHEA (Saliva) kit from Yanaihara Laboratories, Inc. Saliva x Cortisol: DetectX Cortisol ELISA Kit from Arbor Assays. Saliva x Secretory IgA: s-IgA (Saliva) ELISA kit from Yanaihara Laboratories, Inc. Saliva x Protein: Takara Bradford Protein Assay Kit from Takara Bio Inc. Saliva x Chromogranin A: Human Chromogranin A EIA kit from Yanaihara Laboratories, Inc. Plasma x Total Cholesterol: Cholesterol Assay Kit from Cayman Chemical. Plasma x Uric Acid: Uric Acid Assay Kit from Cayman Chemical. Plasma x AST: Cayman Chemical's Aspartate Aminotransferase Activity Assay Kit. Plasma x ALT: Bioassay Systems' EnzyChrom Alanine Transaminase Assay Kit. Plasma x ALP: Fujifilm Wako Pure Chemical's Lab Assay ALP. Plasma x Protein: Takara Bio's TaKaRa Bradford Protein Assay Kit. Serum x Protein: Takara Bio's TaKaRa Bradford Protein Assay Kit.

[0079] Fecal short-chain fatty acids were measured using the following method, rather than a kit. Lyophilized fecal samples were disrupted using a bead mill (Shake Master, Biomedical Science) by vigorous shaking (1,500 G, 10 min) with 3.0 mm zirconia beads. 10 mg of the disrupted fecal sample was suspended in 1,000 μL of crotonic acid (an internal standard), followed by the addition of 500 μL of hydrochloric acid and 2,000 μL of ether. The tube was then vigorous shaking (1,500 G, 10 min) in the bead mill, followed by centrifugation at 10,000 G for 10 min. After centrifugation, 80 μL of the upper ether layer was collected and added to an Agilent crimp-cap vial containing 16 μL of N-tert-butyldimethylsilyl N-methyltrifluoroacetamide. The vial was sealed and heated in an 80°C water bath for 20 min. After heating, the mixture was left overnight at room temperature to t-butyldimethylsilylate the hydroxyl groups. Calibration was performed using standard solutions (formic acid, acetic acid, propionic acid, isobutyric acid, butyric acid, isovaleric acid, valeric acid, lactic acid, and succinic acid) derivatized in the same manner as the test samples. The derivatized samples were analyzed using an Agilent Technologies 7890 Series GC-MS system equipped with a DB-5ms column (0.25 mm x 30 m x 0.25 μm; Agilent Technologies). Measurements were performed using Agilent MassHunter Workstation Data Acquisition software (version 10.0, Agilent Technologies), and the acquired data were analyzed using Agilent MassHunter Quantitative Analysis software (version 10.1, Agilent Technologies).

[0080] The physiological significance of each component as a health indicator is as follows: Creatinine in urine: Indicates kidney dysfunction. Glucose in urine: Indicates diabetes or glomerular damage. Protein in urine: Indicates kidney dysfunction such as nephritis, high blood pressure, or kidney disease. DHEA (dehydroepiandrosterone) in saliva: Related to stress, adrenal function, and hormone balance. Cortisol in saliva: Indicates stress level, adrenal dysfunction, Cushing's syndrome, etc. Secretory IgA (immunoglobulin A) in saliva: Indicates immune system function and risk of infection. Protein in saliva: Indicates salivary gland function and oral health. Chromogranin A in saliva: Related to stress level and nervous system function. Total cholesterol in plasma: Indicates cardiovascular disease, hyperlipidemia, arteriosclerosis, etc. Uric acid in plasma: Indicates gout, kidney dysfunction, and hyperuricemia. AST (aspartate aminotransferase) in plasma: Indicates liver damage, myocardial infarction, muscle disease, etc. ALT (alanine aminotransferase) in plasma: Suggests liver disease, especially hepatitis. ALP (alkaline phosphatase) in plasma: Suggests liver disease, bone disease, biliary tract disorders, etc. Protein in plasma: Suggests nutritional status, dehydration, kidney disease, liver disease, etc. Protein in serum: Suggests nutritional status, dehydration, kidney disease, liver disease, etc. Short-chain fatty acids in feces: An energy source for the large intestine and an indicator of intestinal health.

[0081] The procedure for the color reaction in this example is described below. For urine and saliva samples, samples frozen at -80°C were thawed in a 37°C water bath, and 1.5 mL was then weighed into a 2 mL Eppendorf tube and centrifuged at 10,000 G for 10 minutes to collect the supernatant. 30 μL of the resulting supernatant was mixed with 30 μL of each color reagent on a 96-well plate, stirred on a shaker for 1 minute, and then photographed with a digital camera to obtain images.

[0082] For plasma samples, samples frozen at -80°C were thawed in a 37°C water bath, 1.5 mL was measured into a 2 mL Eppendorf tube, and centrifuged at 10,000 g for 10 minutes to collect the supernatant. The supernatant was diluted 20-fold with ultrapure water, and 40 μL of the resulting supernatant was mixed with 20 μL of each color reagent on a 96-well plate. The mixture was shaken for 1 minute and then photographed with a camera to capture images.

[0083] For fecal samples, samples frozen at -80°C were thawed in a 37°C water bath. 20–25 mg of fecal material was weighed into a 2 mL Eppendorf tube, 24 μL of PBS was added per mg of sample, and the sample was suspended by vortexing for 30 seconds. The sample was then centrifuged at 9000 G for 10 minutes, and the supernatant was collected. For samples other than RDE, RDM, and RDI, 30 μL of the supernatant was mixed with 30 μL of color reagent on a 96-well plate, shaken for 1 minute, and then photographed with a digital camera. For RDE, RDM, and RDI, 54 μL of the supernatant was mixed with 6 μL of color reagent, shaken for 1 minute, and then photographed with a digital camera.

[0084] To obtain color scores, the wells of the 96-well plate were cropped to a 50 × 50 pixel area from the images obtained above, and the resulting images were processed using Python's Pillow 9.0.1 to obtain the median values ​​of 2500 pixels for the RGB, HSV, Lab, CMYK, and gray color spaces. The following results were used for further machine learning model testing: BB, BG, BP, BR, CR, MR, NR, PR for plasma and serum; BB, BG, BP, BR, CR, MR, PR, RDE, RDI, RDM, TB for saliva; BB, BG, BP, BR, CR, MR, PR, RDE, RDI, RDM, TB for urine; and CR, BB, BG, BP, MR, PR, BR, RDE, RDM, RDI for feces.

[0085] The machine learning evaluation (classification model) will be described below. First, for each biomarker in each sample, samples with values ​​less than the median of all samples were labeled 0, and samples with values ​​greater than the median were labeled 1. All combinations of color reagents for each health indicator were evaluated using double cross-validation. For double cross-validation, one test data set was selected from all samples, and the remaining 19 were used as training data. The training data was divided into five sets, and training was performed using four sets. Testing was performed using the remaining set to calculate the accuracy rate. This was performed for all five combinations while changing the hyperparameters, and the hyperparameters were determined. Using the determined hyperparameters, training was performed using the training data, and testing was performed using one test data sample. This was repeated for all combinations, and the accuracy rate was calculated.

[0086] This section describes machine learning evaluation (regression model). All combinations of color reagents were evaluated using double cross-validation. For double cross-validation, one test data set was selected from the total 20 samples, and the remaining data were selected as training data 19 and test data 1. Training data 19 was divided into five parts (4, 4, 4, 4, 3). Four of the parts were used for training, and the remaining part was used for testing to calculate the accuracy rate. This was done for all five combinations while changing the hyperparameters, and the hyperparameters were determined. Using the determined hyperparameters, training was performed using training data 19 and testing was performed using one test data sample. This was done for all 20 combinations, and the coefficient of determination (R^2) was calculated.

[0087] Table 1 shows the verification results regarding the configuration of the imaging unit (measuring device).

[0088]

[0089] "Light source position" is an item related to the position of the light source 23a. "Top board edge" refers to a structure in which the light source 23a is placed at the position shown in FIG. 2 (the edge on the opening side of the top board of the box 23). "Top board center (directly above)" refers to a structure in which the light source 23a is placed near the center of the inner wall of the top board of the box 23, that is, directly above the color sensor array 22. The light source 23a used was the one mounted on the box 23 described below.

[0090] "Camera position" is an item related to the position of the image capture device 21. "Below plate" indicates a structure in which the image capture device 21 is placed in the position shown in FIG. 2 (below the color sensor array 22). "Above plate" indicates a structure in which the image capture device 21 is placed above the color sensor array 22. The image capture device 21 used was a Sony Cyber-shot (DSC-WX500, WW220188).

[0091] "Fixing fixture" is an item related to the structure of the fixing fixture 24. "Present" indicates a structure in which the fixing fixture 24 shown in FIG. 2 is placed. "Absent" indicates that the fixing fixture 24 is not placed and the color sensor array 22 is supported by hand. The fixing fixture 24 was created using a three-dimensional printer.

[0092] "Outer box" is an item related to the presence or absence of the box 23. "Present" indicates a structure in which the box 23 shown in Figure 2 is placed. "Absent" indicates a structure in which the box 23 is not placed. The box 23 used was a 40cm type folding photography box (W40 x H40 x D40cm, light source: 35 white LEDs) equipped with an LED light manufactured by Nakabayashi Co., Ltd.

[0093] "Color space" is an item related to the number of types of color spaces used in calculating the color score. "Five types" indicates that the color score is calculated using five types of color spaces: RGB color space, Lab color space, CMYK color space, HSV color space, and Gray color space. "One type" indicates that the color score is calculated using only the RGB color space. Note that in Comparative Example 1, the color score was not calculated, so "-" is displayed.

[0094] "Learning sample" indicates the type of biological sample used as a sample for machine learning. Note that in Comparative Example 1, a machine learning model was not used, so the type of biological sample used in visual classification is indicated.

[0095] "Color reagent used" indicates the type of color reagent used in the color reaction with the biological sample.

[0096] "Learning data" indicates the components in the biological sample that were the subject of analysis. Note that in Comparative Example 1, a machine learning model was not used, so the components in the biological sample that were the subject of analysis in visual classification are shown.

[0097] "Classification or regression" indicates whether the machine learning model used is a classification model or a regression model. Note that in Comparative Example 1, no machine learning model was used, so "-" is used.

[0098] "Algorithm" indicates whether or not outlier correction was performed. "Outlier correction performed" indicates that the process of removing outliers described in the calculation unit 102 was performed. "Outlier correction not performed" indicates that the process of removing outliers was not performed. Note that in Comparative Example 1, a machine learning model was not used, so "-" is used.

[0099] "Accuracy rate" is the evaluation result of the classification model or visual classification. Note that "-" indicates that there is no evaluation result.

[0100] "R^2 (coefficient of determination)" is the evaluation result of the regression model. Note that "-" indicates that there is no evaluation result.

[0101] As shown in Table 1, Example 1 reproduced the configuration of the imaging unit 20 according to the embodiment described above. The training sample was urine, the color reagents were BG and BP, and the training data was creatinine. A machine learning model was constructed using Support Vector Classification (SVC) to predict the amount of creatinine in a biological sample using a two-class classification. Evaluation was performed based on the accuracy rate. The accuracy rate was a favorable 0.85. In contrast, the accuracy rates of Example 2, in which the light source 23 was positioned directly above the tabletop; Example 3, in which the camera was positioned on the plate; Example 4, in which the color sensor array was manually supported without the fixture 24; Example 5, in which the box 23 was not used; Example 6, in which only the RGB color space was used; and Example 7, in which outlier correction was not performed, were all lower than those of Example 1. Furthermore, Comparative Example 1, in which a judge visually classified the samples, showed a particularly poor accuracy rate. The results of Table 1 suggest that the configuration of the imaging unit 20 is suitable.

[0102] Table 2 shows the results of verification of color reagents suitable for estimating various components in urine. The items in Table 2 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 2, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 1, 8, and 9 shown in Table 2 show combinations of color reagents that achieved good accuracy rates.

[0103]

[0104] The results of Table 2 show that the combination of BG and BP color reagents is suitable for estimating the amount of creatinine in urine. The combination of RDE and TB color reagents is suitable for estimating the amount of glucose in urine. The combination of RDE and TB color reagents is suitable for estimating the amount of protein in urine.

[0105] Table 3 shows the results of verification of color reagents suitable for estimating various components in saliva. The items in Table 3 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 3, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 10 to 14 shown in Table 3 show combinations of color reagents that achieved a good accuracy rate.

[0106]

[0107] The results of Table 3 indicate that the combination of PR and RDE color reagents is suitable for estimating the amount of DHEA in saliva. Furthermore, the combination of PR and RDE color reagents is suitable for estimating the amount of cortisol in saliva. Furthermore, the combination of BB color reagents is suitable for estimating the amount of secretory IgA in saliva. Furthermore, the combination of BG, BR, MR, and TB color reagents is suitable for estimating the amount of protein in saliva. Furthermore, the combination of BP and PR color reagents is suitable for estimating the amount of chromogranin A in saliva.

[0108] Table 4 shows the results of verification of color reagents suitable for estimating various components in plasma. The items in Table 4 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 4, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 15 to 20 shown in Table 4 show combinations of color reagents that achieved good accuracy rates.

[0109]

[0110] From the results of Table 4, it can be said that the combination of BG and NR color reagents is suitable for estimating the amount of total cholesterol in plasma. Also, it can be said that the combination of BG, BP, BR, and PR color reagents is suitable for estimating the amount of uric acid in plasma. Also, it can be said that MR color reagents are suitable for estimating the amount of AST in plasma. Also, it can be said that MR color reagents are suitable for estimating the amount of ALT in plasma. Also, it can be said that CR color reagents are suitable for estimating the amount of ALP in plasma. Also, it can be said that the combination of BG, MR, and CR color reagents is suitable for estimating the amount of protein in plasma.

[0111] Table 5 shows the results of verification of color reagents suitable for estimating various components in feces. The items in Table 5 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 5, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 21 to 29 shown in Table 5 show combinations of color reagents that achieved good accuracy rates.

[0112]

[0113] The results of Table 5 show that a combination of BG, MR, RDE, and RDM is suitable for estimating the amount of acetic acid in feces. A combination of BG, BP, and RDM is suitable for estimating the amount of succinic acid in feces. A combination of BG, MR, and RDM is suitable for estimating the amount of lactic acid in feces. A combination of BG, MR, and RDM is suitable for estimating the amount of propionic acid in feces. A combination of BG, BR, and RDE is suitable for estimating the amount of formic acid in feces. A combination of BB, BG, BP, PR, and RDM is suitable for estimating the amount of butyric acid in feces. A combination of CR, BR, and RDM is suitable for estimating the amount of isobutyric acid in feces. Furthermore, it can be said that a combination of BP, RDE, and RDI is suitable for estimating the amount of isovaleric acid in feces, and a combination of BG, PR, and RDM is suitable for estimating the amount of valeric acid in feces.

[0114] Table 6 shows the results of verification of color reagents suitable for estimating proteins in urine, saliva, plasma, and serum. The items in Table 6 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 6, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 9, 13, 20, and 30 shown in Table 6 show combinations of color reagents that achieved good accuracy rates.

[0115]

[0116] The results of Table 6 show that the combination of RDE and TB color reagents is suitable for estimating the amount of protein in urine. Furthermore, the combination of BG, BR, MR, and TB color reagents is suitable for estimating the amount of protein in saliva. Furthermore, the combination of BG, MR, and CR color reagents is suitable for estimating the amount of protein in plasma. Furthermore, the combination of BG and MR color reagents is suitable for estimating the amount of protein in serum.

[0117] Table 7 shows the results of verification of color reagents suitable for estimating various components in various biological samples when a regression model is used. The items in Table 7 are the same as those in Table 1, so explanations will be omitted. Although not shown in Table 7, the inventors performed similar verification for all combinations of color reagents and evaluated the accuracy rate. Examples 31 to 33 shown in Table 7 show combinations of color reagents that achieved good accuracy rates.

[0118]

[0119] The results in Table 7 suggest that the combination of BG and BP is suitable for estimating the amount of creatinine in urine using a regression model. The combination of BP and PR is suitable for estimating the amount of chromogranin A in saliva using a regression model. The combination of BG, MR, and RDM is suitable for estimating the amount of lactic acid in feces using a regression model.

[0120] REFERENCE SIGNS LIST 1, 2 Information processing system 10, 30 Information processing device 11 CPU 12 ROM 13 RAM 14 Auxiliary storage device 15 Input device 16 Display device 17 External I / F 20, 40 Imaging unit 101, 301 Acquisition unit 102, 302 Calculation unit 103 Determination unit 104, 304 Output control unit 303 Learning unit

Claims

1. An information processing system comprising: an acquisition unit that acquires a captured image of the color of a color reagent in a color reaction using a target biological sample; and a calculation unit that calculates a feature that quantifies the color based on the captured image.

2. The information processing system of claim 1, wherein the calculation unit identifies areas in the captured image in which the colors of each of a plurality of coloring reagents are depicted, and calculates the statistical value of the pixel values ​​of a predetermined number of pixels contained in each of the identified areas as the feature.

3. The information processing system according to claim 2, wherein, when a pixel having an outlier is included in the predetermined number of pixels, the calculation unit calculates the feature amount by excluding the pixel having the outlier.

4. The information processing system according to claim 2, wherein, when a pixel having an outlier is included in the predetermined number of pixels, the calculation unit converts the outlier into a predetermined value and calculates the feature amount.

5. The information processing system according to claim 2, wherein the calculation unit calculates at least one of a median, a mean, and a mode as the statistical value.

6. The information processing system according to claim 1, wherein the colors are represented by pixel values ​​in each of an RGB color space, a Lab color space, a CMYK color space, an HSV color space, and a Gray color space.

7. The information processing system according to claim 1, further comprising a determination unit that determines a health index related to the subject's health based on the feature amount.

8. The information processing system of claim 7, wherein the judgment unit judges the health index of a subject by inputting the features of the subject into a trained model trained using the features of the subject and measurement values ​​of health indexes related to the health of the subject for multiple subjects providing training data.

9. The information processing system according to claim 1, further comprising an imaging unit that captures images of the colors of the plurality of color reagents in the color reaction.

10. The information processing system of claim 9, wherein the photographing unit comprises: a photographing device that photographs the photographed image; a color sensor array in which each of the plurality of color reagents is arranged at an individual position; and a box that houses the color sensor array and is equipped with a light source.

11. The information processing system according to claim 10, wherein the box includes the light source above the color sensor array housed therein.

12. The information processing system according to claim 10, wherein the box includes the light source at a position above the color sensor array housed therein, but not directly above the color sensor array.

13. The information processing system according to claim 10, wherein the box has white interior walls.

14. The information processing system according to claim 10, wherein the photographing section further comprises a fixing device for fixing the positional relationship between the photographing device and the color sensor array.

15. The information processing system according to claim 14, wherein the fixing device is a structure having an opening through which light that has passed through the color sensor array enters, and a fixing position for fixing the imaging device in a position where the light that has entered through the opening can be focused.

16. The information processing system according to claim 14, wherein the fixing fixture has a black inner wall.

17. The information processing system of claim 1, wherein the biological sample is at least one of saliva, feces, urine, whole blood, plasma, and serum of the subject.

18. The information processing system according to claim 1, wherein the color reagents are one to five types of color reagents.

19. The information processing system according to claim 1, wherein the biological sample is urine, and the color reagent is one to three of bromocresol green, bromocresol purple, Reichardt's reagent, and thymol blue.

20. The information processing system of claim 1, wherein the biological sample is saliva, and the color reagent is one to four of the following color reagents: phenol red, Reichardt's reagent, bromothymol blue, bromocresol green, bromopyrogallol red, methyl red, and thymol blue.

21. The information processing system according to claim 1, wherein the biological sample is plasma, and the color reagent is one to four of the following color reagents: bromocresol green, Nile red, bromocresol purple, phenol red, methyl red, and chlorophenol red.

22. The information processing system of claim 1, wherein the biological sample is feces, and the color reagents are three to five of the following color reagents: bromocresol green, methyl red, Reichardt's reagent, bromocresol purple, bromopyrogallol red, bromothymol blue, phenol red, and chlorophenol red.

23. An information processing method comprising: acquiring an image of the color of a color reagent in a color reaction using a target biological sample; and calculating a feature value that quantifies the color based on the image.

24. An information processing method comprising: acquiring an image capturing the color of a color reagent in a color reaction using at least one biological sample selected from the group consisting of saliva, urine, whole blood, plasma, and serum of a subject; and determining a health index related to the subject's health based on the image capturing the color.

25. An information processing system comprising: an acquisition unit that acquires an image of the color of a color reagent in a color reaction using at least one biological sample of a subject's saliva, urine, whole blood, plasma, or serum; and a determination unit that determines a health index related to the subject's health based on the image.

Images