Determination method, determination device, and computer program

Abstract

To provide a determination method or the like capable of determining the possibility of cancer using a receptor.SOLUTION: In the determination method, a computer executes a process of acquiring a response signal to a target sample derived from a determination target, the response signal being detected using a receptor exhibiting reactivity according to the possibility of cancer in the target, and determining the possibility of cancer in the determination target based on the acquired response signal to the target sample.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a determination method, a determination device, and a computer program. [Background technology]

[0002] In recent years, research and development into biosensors using biological elements has been progressing. Patent Document 1 discloses a transistor having a gate electrode containing aluminum or aluminum oxide. The sensor is a sensor that detects odors and insect cells that have olfactory receptors arranged on the gate electrode. and a detection device for detecting the current generated in the transistor when the transistor is activated. A new sensor is disclosed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-113957 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in Patent Document 1 uses receptors to determine the possibility of cancer. It's not that.

[0005] The purpose of the present disclosure is to provide a method for determining the possibility of cancer using a receptor. The purpose is to provide. [Means for solving the problem]

[0006] A method for determining whether a subject has cancer includes: A response signal to the target sample derived from the test subject detected using the detector is acquired, and the acquired A process for determining the possibility of cancer in a subject based on a response signal to the subject sample. The computer executes the process.

[0007] A determination device according to one aspect of the present disclosure includes a receptor that exhibits reactivity according to the possibility of cancer in a subject. A response signal to the target sample derived from the test subject detected using the detector is acquired, and the acquired A process for determining the possibility of cancer in a subject based on a response signal to the subject sample. The control unit executes the process.

[0008] A computer program according to one embodiment of the present disclosure is a program that calculates the probability of cancer in a subject. A response signal to the target sample from the test subject is obtained using a receptor that shows reactivity. and determining the possibility of cancer in the subject based on the response signal obtained from the subject sample. Determine gender. [Effects of the Invention]

[0009] According to the present disclosure, the receptor can be used to determine the likelihood of cancer. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram of a determination system. [Figure 2] FIG. 1 is a schematic diagram illustrating an example of the configuration of an olfactory sensor. [Figure 3] FIG. 2 is a block diagram showing the configuration of a determination device. [Figure 4] FIG. 10 is a diagram illustrating an example of information stored in a detection DB. [Figure 5] FIG. 2 is a block diagram showing the configuration of a terminal device. [Figure 6] FIG. 10 is a diagram showing an example of the change in luminescence intensity of a sensor cell over time. [Figure 7] FIG. 10 is a schematic diagram illustrating an example of a reception screen. [Figure 8]FIG. 10 is a diagram showing examples of a reference profile for cells selected for cancer diagnosis and a reference profile for cells not selected for cancer diagnosis. [Figure 9] FIG. 10 is a schematic diagram illustrating an example of a result screen showing a determination result. [Figure 10] FIG. 10 is a schematic diagram showing another example of a result screen showing a determination result. [Figure 11] 10 is a flowchart illustrating an example of a reference profile generation processing procedure. [Figure 12] 10 is a flowchart showing an example of a procedure for determining the possibility of cancer. [Figure 13] 10 is a flowchart illustrating an example of a processing procedure executed by a determination device according to a second embodiment. [Figure 14] 10A and 10B are diagrams illustrating examples of response profiles according to whether or not correction processing is performed. [Figure 15] FIG. 10 is a block diagram showing an example of the configuration of a determination device according to a third embodiment. [Figure 16] FIG. 1 is an explanatory diagram showing an overview of a learning model. [Figure 17] 11 is a flowchart showing an example of a procedure for a cancer possibility determination process executed by the determination system of the third embodiment. [Figure 18] 10 is a flowchart illustrating an example of a re-learning process of a learning model. [Figure 19] 10 is a flowchart illustrating an example of a processing procedure executed by a determination system according to a fourth embodiment. [Figure 20] FIG. 13 is a schematic diagram showing an example of a result screen showing a determination result in the fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] The present disclosure will be specifically described with reference to the drawings showing embodiments thereof.

[0012] (First embodiment) FIG. 1 is a schematic diagram of a determination system 100. The determination system 100 of this embodiment The system includes a measurement device 1, a terminal device 2, a detection device 3, and an olfactory sensor 4. The olfactory sensor 4 includes: The determination device 1 is an example of a biosensor. The terminal device 2 and the detection device 3 are communicably connected. Detection results of odor molecules in a test sample from a subject detected by the device 3 and the olfactory sensor 4 The possibility of cancer in the subject is determined based on the result of the determination device 1, and the determination result is transmitted via the terminal device 2. We provide services that present the following.

[0013] In the following embodiment, the odor molecules detected in urine of a subject as a test sample are used. Based on this, an example of determining the possibility of cancer in a subject will be explained. The types of cancer that can occur are not limited, but include lung cancer, esophageal cancer, breast cancer, stomach cancer, and liver cancer. Cancer, pancreatic cancer, gallbladder cancer, bile duct cancer, colon cancer, kidney cancer, bladder cancer, ovarian cancer, These include uterine cancer, prostate cancer, oral cancer, and pharyngeal cancer.

[0014] The determination device 1 is an information processing device capable of various information processing and transmitting and receiving information. The determination device 1 is a server computer, a personal computer, a quantum computer, etc. a signal indicating the subject's response to the odor of urine is acquired, and the subject is notified based on the acquired signal; A service that determines the possibility of cancer in a patient and provides the result of the determination to the user via the terminal device 2. The determination device 1 is a local computer installed in the facility where the detection device 3 is installed. The device may be a computer.

[0015] The terminal device 2 is an information processing terminal used by the subject, and may be, for example, a personal computer, The terminal device 2 is a smartphone, a tablet terminal, etc. The terminal device 2 receives the judgment from the judgment device 1. The test subject is an example of a user who receives the judgment result. Not limited to information provided to test subjects, but also to medical professionals, personnel at analytical institutions conducting analyses, etc. The number of terminal devices 2 connected to the determination device 1 may be one or three or more. stomach.

[0016] The olfactory sensor 4 and the detection device 3 are managed by, for example, an analytical institution. It is a facility that receives specimens collected from individuals and performs analyses of the specimens. The olfactory sensor 4 has cells 42 (see FIG. 2) that express olfactory receptors as detection elements, and detects olfactory The detection device 3 outputs a signal indicating the response of the olfactory receptor to the odor molecule. The detection device 3 is a detector that detects the response signal. In addition to all of these functions, it also functions as a computer that processes various data and communicates with external devices. and the detection data of the response signal obtained by the detection is transmitted to the determination device 1 through the network N. The detector and the computer are provided separately and are configured to be able to communicate with each other. The number of detection devices 3 connected to the determination device 1 may be one or three or more.

[0017] FIG. 2 is a schematic diagram showing an example of the configuration of the olfactory sensor 4. FIG. 2 shows the olfactory sensor 4 from above. The olfactory sensor 4 is disposed in a well 43 formed in a substrate 41. The substrate 41 has, for example, 384 wells 43 formed thereon. In FIG. 2, for the sake of simplicity, the substrate 41 and 24 wells 43 are formed on the plate. In this embodiment, cells 42 consisting of a plurality of cells of the same type are placed in each of a plurality of wells 43. That is, a large number of cells of the same type are seeded in each well 43 at high density. The cells 42 may be composed of one type of cell. Each cell has an olfactory receptor. The cell 42 has a sensor that outputs a signal indicating the response of the olfactory receptor to the odor molecule. Olfactory receptors function as sensor cells. Cell 42 is an example of a sensor element. Olfactory receptors detect specific odors. The response is based on the binding between the olfactory receptors provided in the olfactory sensor 4 and the odor molecules. By detecting the response signal, it is possible to selectively detect odor molecules contained in the subject's urine.

[0018] The substrate 41 is made of a material such as glass, silicon, ceramics, resin, or metal. The surface of the substrate 41 is subjected to, for example, plasma treatment, corona treatment, UV-Ozone treatment, etc. Surface treatment or coating with polypeptide or the like may be performed. The shape of the substrate 41 may be any shape as long as it can detect odors using the cells 42 arranged on the substrate 41. The size of the substrate 41 is not particularly limited, and the size of the cells 42 to be placed on the substrate 41 is It can be set appropriately depending on the number etc.

[0019] The olfactory receptors can be derived from animals. Examples include insects, vertebrates, and mammals, such as flies, mosquitoes, mice, rats, rabbits, and pigs. Olfactory receptors from animals such as rhesus monkeys, dogs, and humans can be used. Insect olfactory receptors form heterocomplexes with olfactory receptor co-receptors and are involved in the detection of odorants. It functions as an ion channel activated by ATP.

[0020] The amino acid sequences and coding sequences of olfactory receptors and olfactory receptor co-receptors are either publicly known or publicly available. They can be easily identified by sequence identity searches based on known sequences. The amino acid sequence may include amino acid mutations. Acid substitutions, insertions, additions, or deletions.

[0021] As the cell 42, a specific cell that naturally expresses an olfactory receptor may be used. Alternatively, genetically modified cells incorporating the gene for the receptor may be used. They are produced by transforming cells with a vector incorporating an olfactory receptor gene. If the olfactory receptor is an insect olfactory receptor, the olfactory receptor co-receptor gene can be further identified. It is preferable to incorporate

[0022] The cells 42 may further comprise a fluorescent or luminescent protein. When odor molecules bind to ionotropic olfactory receptors in cells42, they are released into the cells. The fluorescent intensity changes depending on the ion concentration. A gene that expresses a protein or a photoprotein with variable luminescence intensity is introduced into cells 42. By placing the cells in a lab, the response of the cells to odor molecules can be detected by changes in fluorescence or luminescence intensity. In other words, odor molecules can be detected by changes in fluorescence intensity or luminescence intensity. Examples of such proteins include aequorin and Yellow Camel eon, GCaMP, etc.

[0023] A calcium ion-dependent fluorescent dye may be introduced into the cells 42. By introducing an odor-dependent fluorescent dye into cells, odor molecules are detected by binding to olfactory receptors. The influx of calcium ions into the cells can be detected by changes in fluorescence intensity. Examples of such calcium ion-dependent fluorescent dyes include Fura-2 and Fluo- 3, Fluo-4, etc.

[0024] The detection device 3 detects a signal indicating a response of the cell 42 based on the binding of the olfactory receptor with the odor molecule. The detection device 3 detects the luminescence intensity for each well 43 in the olfactory sensor 4, for example. The detection device 3 includes, for example, a photomultiplier tube, and detects the ion concentration in the cell. The fluorescence or luminescence intensity based on the change in the intensity is detected. The response signal is not limited to fluorescence or luminescence intensity, but is an electrical signal (electron) based on changes in intracellular ion concentration. The response signal may be transmitted to an imaging device such as a CCD camera, which captures the luminescence of the cell 42. The image may be a moving image or a still image taken by a camera.

[0025] As shown in FIG. 2, the olfactory sensor 4 of this embodiment includes a plurality of cells 4 arranged on a substrate 41. In the example shown in FIG. 2, a plurality of cells 42 are arranged at regular intervals on the upper surface of a substrate 41. are arranged in a vertical and horizontal alignment.

[0026] Generally, olfactory receptors have selectivity for odor molecules. Therefore, different olfactory receptors A plurality of cells 42 expressing the gene are placed on a substrate 41, and the responses of the cells 42 are measured. By emitting multiple odors, it is possible to detect multiple types of odors. It may have one or more types of olfactory receptors. The olfactory sensor 4 may include a plurality of identical cells 42. The sensor 4 is equipped with different types of cells 42, each of which has one type of olfactory receptor. do.

[0027] The number, type and arrangement of olfactory receptors used in the olfactory sensor 4 are determined based on the odor molecules to be detected. The olfactory receptors can be appropriately determined depending on the type of cancer to be detected. It may be a specific combination for a desired odor molecule, or a comprehensive combination for various odor molecules. For example, a number of olfactory receptors may be combined in one olfactory sensor 4. The number of cells 42 mounted on one olfactory sensor 4, i.e., the total number of sensor cells mounted on one olfactory sensor 4, is one or more. The number of types of cells 42 mounted on one olfactory sensor 4 can be set to 50,000 or less. can be between 1 and 2000 species.

[0028] The method of detecting the response signal is not limited to the above example. An appropriate method can be used depending on the type of odor molecule sensed by the receptor.

[0029] 3 is a block diagram showing the configuration of the determination device 1. The determination device 1 includes a control unit 11, a memory The determination device 1 may be a single computer or may be a multi-computer. It may be a computer system consisting of several computers and peripheral devices. The determination device 1 may be a virtual machine or a cloud. stomach.

[0030] The control unit 11 includes one or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), The control unit 11 includes a processor such as a built-in ROM (Read-Only Memory). Memory such as RAM (Random Access Memory), clock, counter, etc. The functional parts of the control unit 11 are implemented in software. It may be implemented in part or in whole as an ASIC (Application Specific Integrated Circuit). Even if it is realized by hardware such as FPGA (Field Programmable Gate Array), good.

[0031] The storage unit 12 may be, for example, a hard disk, a flash memory, or an SSD (Solid State Drive). The storage unit 12 is a separate unit from the determination device 1 and is connected to an external The storage unit 12 may be one or more external storage devices that are accessed by the control unit 11. The memory unit 12 stores various computer programs and data. A program 1P for making a computer execute the processing related to the detection DB (Data Base e) 121. The storage unit 12 further stores a reference profile, which will be described later. It may be done.

[0032] A computer program (program product) containing Program 1P is The data program may be provided by a non-transitory recording medium 1A that readably records the data program. The storage unit 12 stores computer program data read from the recording medium 1A by a reading device (not shown). The recording medium 1A stores a program. For example, the recording medium 1A may be a magnetic disk, an optical disk, a semiconductor memory, or the like. In addition, external servers connected to the communication network can access computer programs. The program 1P may be downloaded and stored in the storage unit 12. It may be a computer program, or may consist of multiple computer programs. The program 1P may also be executed on a single computer, or multiple computers. The present invention may be implemented by a number of computers working together.

[0033] The communication unit 13 includes a communication device that realizes communication via the network N. 11 transmits and receives data between the terminal device 2 and the detection device 3 via the communication unit 13.

[0034] The configuration of the determination device 1 is not limited to the above example. For example, The image forming apparatus may be provided with a display unit for displaying images, etc.

[0035] The determination device 1 and the detection device 3 are not limited to those that transmit and receive data via the network N. The determination device 1 is provided with, for example, an input interface for connecting the detection device 3. Alternatively, the data output from the detection device 3 may be received via a signal line or the like.

[0036] 4 is a diagram showing an example of the contents of information stored in the detection DB 121. The detection DB 121 includes , detection information for each of a plurality of subjects, subject information for the subject, and a reference profile It is a database that stores reference profile information about files.

[0037] In the detection information table, for example, the subject ID is used as a key to store the subject ID, the collection date, the detection device ID, and the like. D, the date of detection, the detection data, the judgment result, etc. are linked to the record. The specimen ID is identification information for uniquely identifying the specimen collected from the subject. The subject ID may be an ID attached to a container that contains a specific subject. is identification information for identifying the subject. The collection date indicates the date and time when the subject was collected. The detection device ID is a code for identifying the detection device 3 used to detect the response signal from the test subject. The detection date indicates the date and time when the response signal to the specimen was detected by the detection device 3. represent.

[0038] The detection data includes information indicating a response signal to the subject. In this embodiment, the response signal as detection data is a profile of the response signal. The response signal profile is the time-dependent data of the luminescence intensity. The result is generated for each cell 42 in the sample. The result represents the likelihood of cancer based on the detection data. The judgment result may be indicated by the presence or absence of a possibility, and the degree of possibility may be classified into multiple stages. The information in the detection information table is collected through the detection device 3, for example.

[0039] The subject information table contains, for example, the subject ID as a key, terminal device information, and subject attributes. The records linking information such as gender information are stored. The terminal device information is related to the terminal used by the subject. The information is used to identify the terminal device 2, and includes, for example, an address indicating the output destination of the determination result, a device ID, etc. The attribute information includes, for example, the subject's name, age, sex, health information, etc. The health information includes, for example, Information about the subject's health condition, such as current symptoms, medical history, test results, and health check results The information in the subject information table may include, for example, information collected through the terminal device 2. can be.

[0040] The reference profile information table contains, for example, cell information and the first base Records linking information such as primary profile information and secondary standard profile information are stored. Cancer information is information for identifying the cancer to be diagnosed, such as a cancer ID. The cell information includes the name of the cancer (cancer type), etc. This is information indicating the cell types selected for cancer diagnosis. The first reference profile information and the second reference profile information correspond to the cell information. The first and second reference profiles are information about the file and the second reference profile. The reference profile will be described in detail later. Note that FIG. 4 is an example, and the reference profile stored in the detection DB 121 The content of the information to be stored is not limited. The data holding method shown in FIG. 4 is an example. Other storage formats are also possible as long as the data contents and relationships between data are maintained.

[0041] 5 is a block diagram showing the configuration of the terminal device 2. The terminal device 2 includes a control unit 21, a memory The device includes a unit 22, a communication unit 23, a display unit 24, and an operation unit 25.

[0042] The control unit 21 includes one or more arithmetic processing units such as a CPU, an MPU, a GPU, etc. The unit 11 uses built-in memories such as ROM or RAM, clocks, counters, etc., to control each component. Controls the unit to execute processing.

[0043] The storage unit 22 is a non-volatile memory such as a hard disk, a flash memory, or an SSD. The storage unit 22 stores various computer programs and data referenced by the control unit 21. The storage unit 22 stores the process for obtaining the result of the cancer possibility determination. It stores the program 2P to be executed by the

[0044] A computer program (computer program product) containing Program 2P is The computer program is provided by a non-transitory recording medium 2A on which the program is readably recorded. The storage unit 22 may store the data read from the recording medium 2A by a reading device (not shown). The recording medium 2A stores a computer program. For example, the recording medium 2A may be a magnetic disk or an optical disk. and semiconductor memory. In addition, the data is transferred from an external server connected to a communication network to the computer. A computer program may be downloaded and stored in the storage unit 22. It may be a single computer program or may be a set of multiple computer programs. The program 2P may also be configured to run on a single computer. It may be executed by a single computer or by multiple computers working together.

[0045] The communication unit 23 includes a communication device that realizes communication via the network N. 21 transmits and receives data to and from the determination device 1 via the communication unit 23.

[0046] The display unit 24 is, for example, a liquid crystal display or an organic EL (Electro Luminescence) display. The display unit 24 is equipped with a display device such as a display panel. Displays various information including results.

[0047] The operation unit 25 is an interface that accepts user operations. For example, keyboard, mouse, touch panel device with built-in display, speaker and microphone The operation unit 25 receives operation input from the user and performs the following operations according to the operation content. The control signal is sent to the control unit 21 .

[0048] 6 is a graph showing an example of the change in luminescence intensity of the sensor cell over time. The axis represents the luminescence intensity, and the horizontal axis represents time (s). The results of detecting the luminescence intensity when added to cells expressing olfactory receptors that bind to odor molecules are shown below. The odor molecules are shown in order of concentration. The second concentration and the third concentration.

[0049] As shown in FIG. 6, the profile showing the change in luminescence intensity over time is concentration dependent. In this embodiment, the response profile of the luminescence intensity detected from the urine sample of the subject is used. By estimating the characteristics of specific odor molecules in urine that can be detected by the sensor cells, Determine the possibility of cancer in

[0050] A specific example of the flow of the determination process in the determination system 100 of this embodiment will be given below. I will explain.

[0051] The determination device 1 accepts an application for a determination service from a subject. A user (subject) who desires to receive the test data provided by the determination device 1 uses, for example, a terminal device 2. The application is made through the attached screen 50.

[0052] 7 is a schematic diagram showing an example of a reception screen 50. The determination device 1 receives a message via the terminal device 2. When a request for login using account information and reception screen is accepted by the subject, In this case, a reception screen 50 as shown in FIG.

[0053] The reception screen 50 displays a subject information input screen for receiving subject information about the subject to be evaluated. and a cancer information reception field 501 for receiving input of the target cancer for which the patient wishes to be diagnosed. The subject uses the operation unit 25 to enter the name and other information of the subject to be judged. If the subject has already registered as a user, the subject information is entered in the subject information reception field 501. The device 1 refers to the detection DB 121 and acquires subject information according to the logged-in account information. The subject information may be read out and displayed in the subject information reception field 501 .

[0054] The cancer information reception column 502 allows the selection of multiple cancers that can be diagnosed by the diagnosis system 100. The subject can select the check box corresponding to each cancer, for example. The user can input the desired cancer type or cancers for which they wish to be diagnosed. In this study, lung cancer was selected as the target cancer.

[0055] The determination device 1 determines the total number of target cancers selected as the desired determination. The fee for the assessment service is calculated so that the amount is large. The fee varies depending on the type of cancer. The determination device 1 may change the calculated usage fee in accordance with the cancer information reception column 502. Display it on.

[0056] The terminal device 2 receives various information input into a subject information reception field 501 and a cancer information reception field 502. When the application button 503 for specifying the application for judgment is selected in the state where the application is accepted, The subject information and the target cancer are transmitted to the determination device 1. The determination device 1 receives the subject information and the target cancer. The determination device 1 receives the subject information and the application for determination. The target cancer is stored in the storage unit 12, and, if necessary, the subject information and the target cancer are stored in the storage unit 12. The information is transmitted to a detection device 3 at the laboratory that performs the test.

[0057] The reception screen 50 may also include a payment method reception field 504 as shown in FIG. The user can select a specific payment method from the payment method acceptance field 504 to pay the desired amount. The terminal device 2 then selects the payment method. It processes online payments and credit card payments between the specified payment servers, etc. That's fine.

[0058] The information related to the application for the assessment service is received through the terminal device 2. The determination device 1 may receive input from a user, for example, to obtain subject information, etc. may be obtained.

[0059] Once the application is completed, a urine collection container will be sent to the subject. The urine collection container may be provided with a two-dimensional code that indicates the subject's ID, for example. The test subject will then collect urine and use it in a laboratory. The urine is collected in a urine collection container and submitted to an analysis facility. The urine collection container contains the subject's name and other attribute information. This information may be submitted together with the information, collection date, application number issued at the time of application for assessment, etc.

[0060] The urine collection container is received at the analysis facility. The detection device 3 receives input from, for example, a person in charge. By accepting the test, the subject ID, subject ID, collection date, etc. of the subject to be tested will be obtained. You will benefit.

[0061] Next, the response signal is detected by the olfactory sensor 4 at the analysis facility. In the olfactory receptor array, a predetermined number of cells 42 each expressing a different olfactory receptor are arranged. The olfactory sensor 4 may be, for example, a specific insect olfactory receptor placed under the control of a promoter sequence. coding sequences, specific insect olfactory receptor co-receptor coding sequences, and calcium-sensitive luminescence proteins It is created by integrating DNA containing the protein coding sequence into the chromosomal genomic DNA of each cell. are.

[0062] A predetermined amount of a test sample (for example, a urine sample from a test subject) is brought into contact with the olfactory sensor 4, and the detection device The luminescence intensity of each cell is detected over time by 3. This allows the time-dependent change in luminescence intensity to be displayed. The response profile is obtained by measuring the response of the cells 42 in the olfactory sensor 4. The detection device 3 generates the response profile for each test object. The subject ID, subject ID, collection date, detection device ID, detection date, etc. are associated with each other and sent to the determination device 1. Send.

[0063] The determination device 1 performs predetermined preprocessing on the detection data received from the detection device 3. The response profile may be generated by measuring the luminescence intensity of the olfactory sensor 4. It may be performed simultaneously on multiple arrayed sensor cells. The raw detection data output from the detection device 3 is a set of data for multiple sensor cells at various times ( It is assumed that the data includes the luminescence intensity at the time of detection. In this case, there is a possibility that detected values ​​relating to urine samples from multiple subjects are mixed together. Raw detection data including multiple detection values ​​is sorted by sensor cell or by subject-derived urine sample. The response profile can be created by changing the light source, arranging the light emission intensity over time, and converting it into a specified data format. When the time periods of the luminescence intensities in the raw detection data are different, the determination device 1 generates Each data point in the response profile is interpolated using a predetermined interpolation method. The time of the data may be unified.

[0064] The determination device 1 determines whether the subject is a urinary tract infection or not based on the response profile of the obtained urine sample derived from the subject. In this embodiment, the response profile of the urine sample derived from the subject to be analyzed is determined. The likelihood of cancer is determined by comparing the file with a pre-generated reference profile. Make a decision.

[0065] The reference profile was based on the luminescence intensity detected in urine samples from subjects in good health. A first reference profile based on the urinary tract infection detected in a urine specimen from a subject with poor health status was also prepared. and a second reference profile based on the detected luminescence intensity. In this case, subjects in good health refer to those without cancer, and A subject with poor health means a lung cancer patient. The baseline profile is For example, it is generated in advance and stored in the storage unit 12.

[0066] The first and second reference profiles were obtained from urine samples collected from non-cancer patients ( urine collected from lung cancer patients (hereinafter referred to as lung cancer urine) The odor molecules described above are detected by the olfactory sensor 4 using the sensor (described below), and a response profile is obtained. The first and second reference profiles are obtained by generating a profile of the cell. It is prepared every 42.

[0067] The first reference profile was a set of response profiles of multiple healthy urine samples obtained from multiple non-cancer patients. Preferably, the second reference profile is generated based on a file. It is generated based on the response profiles of multiple lung cancer urine samples obtained from 100 lung cancer patients. For example, it is preferable to calculate the statistical value of the luminescence intensity detected from each healthy urine sample for each time period, A first reference profile is generated based on the obtained statistical values. The statistical values ​​may be average values ​​or The median is preferred, and the weighted mean, geometric mean or median is more preferred, with the geometric mean being the most preferred. It is also preferable to measure the response of multiple lung cancer urine samples obtained from multiple lung cancer patients by a similar method. A second reference profile is generated based on the profile.

[0068] Furthermore, among the multiple types of cells 42 contained in the olfactory sensor 4, the cancer and One or more cells 42 suitable for determining lung cancer are selected. The cells that are suitable for lung cancer diagnosis are: Preferably, the reactivity significantly changes depending on whether or not the patient has lung cancer, and the response profile is affected. The cells suitable for lung cancer diagnosis are those found in urine samples from lung cancer cells rather than healthy urine samples. The cells may be those that respond to odor molecules that are relatively abundant in urine from lung cancer compared to healthy urine. In this embodiment, the cells may be cells that respond to odor molecules whose content is reduced compared to normal urine samples. The cells that react to odor molecules contained in urine samples containing lung cancer cells42 are considered to be cells suitable for detecting lung cancer. Cell 42.

[0069] In the production stage of the olfactory sensor 4, cells 42 suitable for determining the cancer to be determined are previously Therefore, in this embodiment, a plurality of types of cells 42 are mounted. An olfactory sensor 4 is prepared, and for each cancer to be determined, cancer cells are selected from multiple types of cells 42. A cell 42 suitable for the determination is identified.

[0070] The method for identifying cells 42 suitable for cancer diagnosis is not limited, but for example, The file can be identified based on the degree of dissimilarity between the file and the second reference profile. 1 calculates the dissimilarity between the first reference profile and the second reference profile, and The cells 42 whose similarity is equal to or greater than a first threshold value set in advance are identified as cells 42 for cancer determination. It may be determined.

[0071] The dissimilarity between the first and second reference profiles can be calculated by, for example, The maximum value of the emission intensity in the primary profile and the maximum value of the emission intensity in the second reference profile The difference between the first and second reference profiles is used as the dissimilarity. The area value enclosed by the file (integrated intensity difference between the first and second reference profiles) The difference between the maximum intensities or the intensity integral between the reference profiles may be used. The larger the difference integral value, the lower the similarity between the first reference profile and the second reference profile. This means that there is a large change in reactivity depending on whether or not there is a possibility of cancer. The response of cells42 differs greatly depending on whether or not they have the potential, and this is thought to be highly useful in determining cancer. In the above, the dissimilarity between the first and second reference profiles is used. However, similarity may also be used.

[0072] The selection of cells 42 for cancer diagnosis can be performed taking into account the accuracy of cancer diagnosis using cells 42. For example, a plurality of cells 42 selected for cancer diagnosis may be used for multiple examinations. A response profile for the sample is obtained, and the obtained response profile is used to The possibility of cancer is determined according to the determination method used. The determination results for each cell42 and known test materials are compared. Based on the characteristics of the sample (healthy urine or lung cancer urine), each cell was selected as the primary cell42. The accuracy of the judgment is calculated by, for example, the AUC of the ROC curve, the recall rate, and the specificity. Based on the obtained judgment accuracy value, each judgment accuracy is optimized. 42 types of cells to be selected for cancer diagnosis (for example, so that the accuracy of each diagnosis is maximized) The type and number of the identified cells 42 are identified. 42 will be second-selected.

[0073] FIG. 8 shows the reference profile of cells selected for cancer diagnosis and the FIG. 8A shows an example of a reference profile for cells that were not selected as cancer cells. FIG. 8B shows the reference profile of the cells selected for cancer assessment. In the case of cells for cancer assessment, the following is an example of a reference profile for cells that were not selected. The response profile was compared between healthy urine and simulated lung cancer urine (healthy urine to which odor molecules derived from lung cancer were added). On the other hand, in the case of cells not intended for cancer detection, the shape of the files is significantly different from that of normal urine and pseudo-lung cancer. There is no significant difference in the response profile between urine and sera.

[0074] In addition, if the type of cells42 suitable for determining a specific cancer is known, the cells for cancer determination can be used. The step of selecting the cells 42 may be omitted.

[0075] The determination device 1 determines a response profile of the urine sample of the subject corresponding to the selected cells 42 for cancer determination. a first reference profile and a second reference profile corresponding to the cells 42 for cancer determination; The likelihood of lung cancer is determined by determining the degree of similarity with each of the files. If the similarity to the file is higher than the similarity to the second reference profile, the possibility of lung cancer is It is determined that the similarity between the second reference profile and the first reference profile is not If the similarity is higher than , it is determined that there is a possibility of lung cancer. The possibility of lung cancer may be assessed in multiple stages or as a percentage.

[0076] The method for determining the degree of similarity is not limited, but for example, The absolute value of the difference between the emission intensity in the reference profile and the emission intensity in the reference profile is calculated for each elapsed time. The sum of the absolute values ​​of the calculated differences may be used as the index for determining the similarity. The smaller the sum of the absolute values ​​of the differences is, the higher the similarity is.

[0077] When a plurality of cells 42 for cancer determination are selected, the determination device 1 The possibility of lung cancer based on each of the 42 cells was individually assessed, and the individually assessed possibility of lung cancer was The determination device 1 performs a comprehensive determination of the possibility of lung cancer by integrating the above data. The overall judgment is the majority vote of the judgment results based on 2. In the overall judgment, The weighting may be performed so that the weight of the judgment result is increased. ,cells 42 with higher usefulness in cancer detection,cells 42 with higher similarity, and cells with higher response signal It may be a cell 42 or the like with little variation.

[0078] The determination of the possibility of lung cancer may be performed using a machine learning technique. When the similarity between the response profile of each cell 42 for cancer judgment and the reference profile is entered A judgment model that outputs the possibility of lung cancer is prepared in advance. The similarity between the response profile and the first reference profile, and the similarity between the response profile and the second reference profile and at least one similarity measure with a quasi-profile.

[0079] The determination device 1 adds to the determination model the response profile of each of the cells 42 for cancer determination. The similarity between the two is input into a judgment model, and the probability of lung cancer output from the judgment model is obtained. The type of cell 42 may be input to the judgment model together with the similarity. The lung cancer probability assessment result output from the test corresponds to the overall assessment result. The individual determination based on each cell 42 may be omitted.

[0080] In addition, if the type of cells 42 suitable for determining a specific cancer is known, For each type of cancer, an olfactory sensor 4 is individually generated using only cells 42 suitable for cancer detection. In this case, the olfactory sensor 4 may be individually adapted to the selected target cancer. The detection of each cell42 by the individual olfactory sensors4 is used to detect the possibility of cancer. The determination device 1 determines the sex of the sample based on a series of information obtained, such as the subject ID, the subject ID, the sample ID, the sample number, and the like. The detection database associates the collection date, detection device ID, detection date, response profile, and judgment result. The determination device 1 also outputs the determination result to the terminal device 2 of the subject.

[0081] 9 is a schematic diagram showing an example of a result screen 51 showing the determination result. A first display unit 511 displays information about the subject to be judged, and a second display unit 512 displays the judgment result. A second display unit 512 is included.

[0082] The determination device 1 determines the subject and the person to be determined based on the information stored in the detection DB 121. The first display unit 511 displays, for example, The subject's name, the date the specimen was collected, and the subject ID are displayed.

[0083] The determination device 1 also displays the determination result indicating the presence or absence of the possibility of cancer on the second display unit 512. When the judgment results for multiple types of cancer are obtained, the result screen 51 displays the results for each target cancer. The second display units 512 may each include a plurality of corresponding second display units 512. The target cancer and the assessment result for the target cancer are displayed.

[0084] FIG. 10 is a schematic diagram showing another example of the result screen 51 showing the determination result. In this example, the second display section 512 of the result screen 51 displays the results of the test subject detected by the olfactory sensor 4. The detection result display field 513 further includes a detection result display field 513 for displaying the detection result. , the response profile corresponding to the subject is displayed.

[0085] In the detection result display field 513, in addition to the response profile corresponding to the subject, the cancer determination The criteria used for processing, i.e., the first and second reference profiles, are displayed. For ease of explanation, only one type of response profile is shown in FIG. However, the detection result display field 513 displays multiple data showing the detection results for each cell 42 used for cancer determination. In the detection result display field 513, the response profile of the image captured by the imaging device may be displayed. An image showing the luminescence of the cells 42 in the olfactory sensor 4 may be displayed. .

[0086] When the response profile for a plurality of cells 42 is displayed in the detection result display field 513, The determination device 1 determines the usefulness in cancer diagnosis or the comparison of each response profile with a reference profile. The display order on the screen may be determined based on the similarity. The detection results of cells 42 with high affinity or similarity are preferentially displayed in the detection result display field 513. The determination device 1 displays the detection results for a predetermined number of cells 42 in the detection result display field 51 in descending order of priority. The determination device 1 may display the degree of contribution of the input information in the determination model. Based on this, the display order is set so that the higher the contribution of the similarity related to the cell 42, the higher the display priority. The contribution may be determined using, for example, the SHAP (SHapley Additive exPlanation) value, coefficient, LIME (Local Interpretable Model-Agnostic Explanation), PFI (Per It can be calculated based on mutation feature importance, etc.

[0087] The determination device 1 displays the time series change of the determination result on the result screen 51 shown in FIGS. 9 and 10. The determination device 1 may determine the display target based on the information stored in the detection DB 121. Among the detected information associated with the subject ID of the subject, the collection date within the specified period is The determination device 1 reads out the determination results and response profiles related to the plurality of collection dates. A table or graph showing the judgment results and response profile corresponding to the results is generated and displayed on the result screen 51. Display it.

[0088] The detection result is not limited to being presented to the subject through the terminal device 2. The detection results may be output to, for example, another computer or a predetermined printing device.

[0089] FIG. 11 is a flowchart illustrating an example of a reference profile generation process. The process in the flowchart is performed by a program 1P stored in the storage unit 12 of the determination device 1. Therefore, it is executed by the control unit 11.

[0090] The control unit 11 of the determination device 1 detects, through the detection device 3, the detected amount of the normal urine of a plurality of cancer-free patients. The response profile was compared with that detected in urine samples from lung cancer patients. The response profile is, for example, a time-dependent data of the emission intensity. The response profile is generated for each cell 42 in the olfactory sensor 4. , information indicating the corresponding cell 42 may be linked.

[0091] The control unit 11 generates a first reference profile based on each response profile for a plurality of normal urine samples. The control unit 11 generates a file (step S12). Generate a first reference profile by calculating the geometric mean of the luminescence intensity over time. .

[0092] The control unit 11 generates a second reference profile based on each response profile for a plurality of lung cancer urine samples. The control unit 11 generates a file (step S13). A second reference profile is generated by calculating the geometric mean of the measured luminescence intensities over time. do.

[0093] The control unit 11 selects cells 42 from the plurality of types of cells 42 contained in the olfactory sensor 4 that are used for lung cancer detection. The control unit 11 selects one or more cells 42 that are present in the olfactory sense (step S14). For each cell 42 included in the sensor 4, a first reference profile and a second reference profile are generated. The control unit 11 calculates the maximum value of the luminescence intensity or the integral value of the intensity difference for each of the channels. a cell in which the difference between the maximum values ​​of the luminescence intensities or the integral value of the intensity difference is equal to or greater than a first threshold value set in advance; In step S14, the control unit 11 selects each cell 42 as a cell 42 for lung cancer determination. The accuracy of each determination was optimized based on the accuracy of determining the possibility of cancer when using cell 42. In order to do so, the type and number of cells 42 to be selected for cancer diagnosis are identified, and the results of the identification are used to Cells 42 for lung cancer diagnosis may be selected.

[0094] The control unit 11 receives cancer information, cell information of the selected cells 42 for lung cancer determination, and The first and second reference profiles corresponding to the respective (step S15), and the series of processes ends.

[0095] The control unit 11 performs the above-mentioned Processing is performed to generate first and second reference profiles for various cancer determinations. The above process is performed before the operational stage where the judgment service is performed. That's fine.

[0096] FIG. 12 is a flowchart showing an example of a procedure for determining the possibility of cancer. The process is carried out by the control unit 11 in accordance with a program 1P stored in the storage unit 12 of the determination device 1. The terminal device 2 is controlled in accordance with a program 2P that is executed and stored in the storage unit 22 of the terminal device 2. This is performed by unit 21.

[0097] The control unit 21 of the terminal device 2 determines whether the subject wishes to be examined based on the subject's operation using the reception screen. The subject information of the subject and the target cancer (cancer type) are received (step S20). The control unit 21 transmits the received subject information and target cancer to the determination device 1 (step S twenty one).

[0098] The control unit 11 of the determination device 1 receives the subject information and the target cancer (step S22).

[0099] The control unit 11 detects a response profile generated from a urine sample derived from a subject through the detection device 3. The response profile is obtained by measuring the response of the cells 4 in the olfactory sensor 4 (step S23). The response profile includes the subject ID, subject ID, collection date, and The control unit 11 controls the raw sample obtained by the detection. The raw detection data is acquired from the detection device 3, and various preprocessing steps are performed on the acquired raw detection data. The control unit 11 may generate a response profile by , collection date, detection device ID, detection date, and response profile by cell type are associated and detected D B121 (step S24).

[0100] The control unit 11 performs a test on a urine sample derived from a subject for each cell 42 for cancer determination according to the target cancer. Similarity of the response profile to the first and second reference profiles, respectively The degree is calculated (step S25).

[0101] The control unit 11 compares the calculated similarities and selects a profile corresponding to a reference profile with a high similarity. By identifying the health status of the subject, whether or not the subject has a risk of cancer In step S26, the possibility of cancer is determined for each cell 42. The control unit 11 determines whether or not the cell 42 has a specific function by, for example, a majority vote of the individual determinations of each cell 42. The control unit 11 makes a comprehensive determination as to whether or not there is a possibility of cancer (step S27). The results are stored in the detection DB 121 in association with the subject ID (step S28).

[0102] The control unit 11 generates a result screen showing the obtained cancer possibility assessment result (step S29). The control unit 11 displays the generated result screen based on the subject information acquired in step S23. The result is transmitted to the terminal device 2 corresponding to the subject identified by the above (step S30).

[0103] The control unit 21 of the terminal device 2 receives the result screen from the determination device 1 (step S31). The control unit 21 displays the received result screen on the display unit 24 (step S32), and executes a series of processes. Exit.

[0104] In the above process, the subject requests the display of the result screen using the terminal device 2, and By accepting the result screen accordingly, you can check the judgment results at any time. The determination result may be provided through a web service provided by the determination device 1. may be provided.

[0105] In the above process, the control unit 11 of the determination device 1 detects D Based on the newly stored response profile and judgment results in B121, the reference profile is The control unit 11 may update the rule, for example, at appropriate intervals, by updating one or more newly added rules. The control unit 11 extracts a number of response profiles from the detection DB 121. Among the files, several new response profiles were added that were determined to be cancer-free. The first reference profile is regenerated based on the response profile. is the response profile that was determined to be possibly cancerous among the extracted response profiles. Regenerate the second criteria profile based on the newly added multiple response profiles. .

[0106] In the above, an olfactory sensor 4 having olfactory receptors is used to detect a urine sample based on the detection data. The possibility of cancer was judged based on the olfactory receptors. The specimens to be analyzed are not limited to urine, but also include blood, sweat, saliva, tears, breath, The fluid may be skin gas, tissue fluid, synovial fluid, follicular fluid, cerebrospinal fluid, semen, milk, vaginal fluid, etc. The subject for determining the possibility of cancer is not limited to humans, but may also be an animal.

[0107] According to this embodiment, cancer is detected based on detection data from a biosensor having a receptor. It is possible to determine the feasibility of using biosensors and improve the practicality of biosensors. It is possible to provide healthcare services tailored to the needs of each individual. By using the pre-generated bases, it is possible to accurately determine the possibility of cancer. The possibility of cancer is determined by comparing with the quasi-profile. This makes it easier.

[0108] Subjects can obtain results by submitting their test samples and registering the necessary information. This reduces the burden of inspection and increases the utilization rate of the service. You can check the results of the test at any time, so you can be sure to understand the results. By displaying the detection result in a visually recognizable manner in addition to the judgment result, The results can be confirmed more reliably and in detail. In addition to the subject's own detection results, By displaying a reference profile that serves as a reference, the interpretability of the judgment results is improved.

[0109] (Second embodiment) In the second embodiment, correction is performed to eliminate individual differences in response profiles. In this embodiment, differences from the first embodiment will be mainly described, and the configurations common to the first embodiment will be described. The same reference numerals are used and detailed explanations thereof will be omitted.

[0110] The response signal detected from the subject may vary from person to person due to various factors. For example, due to the influence of impurities contained in the urine sample, urine samples containing the same concentration of odor compounds may differ in quality. However, the luminescence intensity detected from urine samples containing many impurities is higher than that detected from urine samples with few impurities. In other words, the influence of impurities on the concentration of odor molecules and the luminescence intensity The response signal also varies from individual to individual due to the influence of the balance of odor molecules. Individual differences may occur not only in luminescence intensity but also in various response signals. obtain.

[0111] When making judgments based on response profiles, the occurrence of individual differences as described above is This leads to a decrease in the accuracy of the determination. Comparison of the urine profile with the reference profile determines whether the urine sample is a healthy urine or a lung cancer urine. When determining whether profiles are similar, there is a possibility of misjudgment due to individual differences. In this embodiment, a correction process is performed to eliminate individual differences in the response profile. By carrying out this process, we aim to improve the accuracy of judgment.

[0112] FIG. 13 is a flowchart showing an example of a processing procedure executed by the determination device 1 of the second embodiment. The process of FIG. 13 is, for example, a process between step S24 and step S25 in the first embodiment. It is executed in

[0113] The control unit 11 of the determination device 1 selects individual cells 42 from among the multiple types of cells 42 contained in the olfactory sensor 4. One or more cells 42 to be used for correcting individual differences are selected (step S41). The cells used for this purpose have a higher reactivity to the target cancer (e.g., lung cancer) than the cells used for cancer assessment. As cells for correcting individual differences, cells with low lung cancer incidence are more preferable. In cells where the reactivity does not change significantly depending on whether or not the antibody is present, and no significant difference in the response profile is observed The cells used for individual difference correction have almost the same concentration in both healthy urine and lung cancer urine. These may be cells that respond to certain odor molecules, or odor molecules artificially added to urine. In other words, the cells may be cells that react to odor molecules that are not contained in the urine before addition.

[0114] The control unit 11 may, for example, select a first reference profile based on non-cancer urine (healthy urine) and a second reference profile based on lung cancer urine. Cell 42 was selected for individual variability correction based on dissimilarity to a second urine-based reference profile. Specifically, the control unit 11 performs the following for each cell 42 included in the olfactory sensor 4: The control unit 11 calculates the degree of dissimilarity between the first reference profile and the second reference profile. The cells 42 whose calculated dissimilarity is less than a second threshold value set in advance are classified as cells for correcting individual differences. The dissimilarity between the first and second reference profiles is selected as cell 42. For example, in the case of identifying cells 42 for cancer determination, the difference between the maximum value of the luminescence intensity in the first reference profile and the maximum value of the luminescence intensity in the second reference profile, or may be an integral value of the difference in intensity between the first reference profile and the second reference profile. In the above, the dissimilarity between the first and second reference profiles is used. , similarity may also be used.

[0115] The first and second reference profiles are each obtained from a plurality of individuals. Preferably, the second threshold is generated based on the response profiles of multiple urine samples. It may be the same as or smaller than the first threshold value used to select the cells 42 for measurement. The cells 42 for correcting individual differences are selected from the cells 42 in the olfactory sensor 4 for cancer detection. The cells 42 for correcting individual differences may be selected from cells 42 other than the cells 42. If is known, the above selection step may be omitted.

[0116] The control unit 11 acquires a correction profile corresponding to the selected correction cell 42 ( Step S42). The correction profile is a first reference profile and a second reference profile. The response profile may be generated based on the statistical values ​​of the first reference profile. When the maximum value of the emission intensity or the integral value of the intensity difference between the first reference profile and the second reference profile is approximately zero, uses either the first reference profile or the second reference profile as the correction profile. The correction profile is obtained for each correction cell 42.

[0117] The control unit 11 compares the acquired correction profile with the response profile of the subject's urine sample. Based on this, a correction coefficient (correction value) for correcting the response profile is calculated (step (P S43).

[0118] The correction factor can be calculated, for example, by the following method. The area enclosed by the x-axis (time axis) and the x-axis (time profile) is For each section, the area of ​​the first region enclosed by the response profile and The ratio of the area of ​​the second region surrounded by the correction profile is calculated. The geometric mean value of the ratios is used as the correction coefficient. Note that the calculation method of the correction coefficient is not limited to the above example. The correction coefficient is not limited to the above, but may be set to correct for individual differences in response profiles. may be adjusted depending on the type of the determination cell 42. For example, The above correction coefficient calculated based on the response profile is used to predict the response of each test cell 42. By multiplying the predetermined coefficient set for the purpose of the correction, a correction coefficient for each cell 42 for determination can be obtained. good.

[0119] When a plurality of cells 42 are selected as correction cells 42, the control unit 11 The above correction coefficients are calculated for the cells 42, and the statistical values ​​(e.g., geometric mean) of the calculated correction coefficients are calculated. The final correction factor may be determined by calculating the mean, median, etc.

[0120] The control unit 11 uses the calculated correction coefficient to determine the number of cells 42 selected for cancer diagnosis. The response profile is corrected (step S44). Specifically, the response profile for cancer diagnosis is Each emission intensity in the file is multiplied by a correction factor to generate a corrected response profile. The control unit 11 executes the processes from step S25 onward using the corrected response profile. The likelihood of cancer is determined based on the adjusted response profile.

[0121] According to the above process, the correction cells selected from the cells 42 in the olfactory sensor 4 The correction coefficient was calculated based on the 42 response profiles and the reference profile. The number can be used to correct the response profile of the cells 42 for cancer determination. The cells 42 do not show different response signal properties depending on whether or not there is a possibility of cancer, and the response The profile is largely independent of whether or not there is a possibility of cancer. Cells for cancer determination42 shows the characteristics of different response signals depending on whether or not there is a possibility of cancer, and the response profile is highly dependent on whether or not cancer is possible.

[0122] FIG. 14A shows an example of a response profile according to whether or not correction processing is performed. In the example shown, the response profile before correction is generally low due to the influence of contaminants that weaken the activity. The emission intensity is decreasing. The response profile after correction is corrected so that the emission intensity is increased. The correction shown in Figure 14A reduces the number of subjects with possible cancer to those without possible cancer. This reduces the possibility of misjudging the image to be too small.

[0123] In the example shown in Figure 14B, the response profile before correction shows a significant increase in activity due to the influence of contaminants. The response profile after correction shows that the emission intensity is small. The correction shown in Figure 14B is used to reduce the number of subjects with no possibility of cancer. This reduces the possibility of incorrectly identifying a possible cancer.

[0124] According to this embodiment, it is possible to correct the individual differences between subjects, and the accuracy of determination due to the individual differences can be improved. The decrease in the concentration of the receptor can be suppressed by using a biosensor to measure biological samples. When this is done, it is thought that differences in the response signals may occur due to various factors. If so, such individual differences can be appropriately eliminated.

[0125] According to this embodiment, cells for individual correction can be efficiently selected based on the characteristics of the response profile. A biosensor with multiple sensor cells is prepared, and the response of each cell is measured. By acquiring a response profile, appropriate individual corrections can be made according to the various properties that are the object of judgment. Cells for use can be selected.

[0126] (Third embodiment) In the third embodiment, a learning model is used to determine the possibility of cancer.

[0127] 15 is a block diagram showing an example of the configuration of a determination device 1 according to the third embodiment. The determination device 1 stores a learning model 122 in the storage unit 12. The learning model 122 includes: The learning model 122 is a machine learning model that has learned predetermined training data. It is expected to be used as a program module that constitutes part of software.

[0128] FIG. 16 is an explanatory diagram showing an overview of the learning model 122. The learning model 122 is The response profile of the luminescence intensity detected from the urine sample is used as input. The output is information indicating whether or not the corresponding subject has a possibility of the target cancer. The learning model 122 is composed of a plurality of individual learning models 123. The individual learning model 123 is divided into a first learning model 123A, a second learning model 123B, and a third learning model 123C. It is also written as the Learning Model 123C.

[0129] The first learning model 123A is a model for determining the possibility of lung cancer as the first cancer. The response profile of a plurality of cells 42 is input, and the presence or absence of the possibility of lung cancer is output. The second learning model 123B is a model for determining the possibility of prostate cancer as a second cancer. The response profiles of multiple cells42 are used as input to predict the likelihood of prostate cancer. The third learning model 123C determines the possibility of colon cancer as the third cancer. It is a model for colon cancer, which uses response profiles of multiple cells42 as input. In this way, the individual learning model 123 outputs the presence or absence of cancer for each cancer to be judged. The individual learning model 123 included in the learning model 122 is constructed to correspond to this. The number may be four or more. Since the individual learning models 123 all have the same configuration, The configuration of the first learning model 123A is described below.

[0130] The first learning model 123A is, for example, a CNN (Conv The first learning model 123A is a holistic neural network (NN). The input layer receives input, the output layer outputs whether there is a possibility of lung cancer, and the intermediate layer (hidden layer) The intermediate layer may include a convolution layer, a pooling layer, a fully connected layer, etc. It has multiple nodes that extract the feature quantities of the response profile, and extracts them using various parameters. The output feature is passed to the output layer. When a response profile is input to the input layer, the learning The intermediate layer performs calculations based on the calculated parameters, and the output layer indicates whether or not there is a possibility of lung cancer. Output information indicating the classification results is output.

[0131] The input data input to the first learning model 123A is the data of all cells in the olfactory sensor 4. 42, the response profile of cell 42 selected for lung cancer assessment. The input data for the learning model 123A contains 42 types of cells corresponding to the response profiles. It may be included.

[0132] The first learning model 123A generates a label indicating the possibility of lung cancer for the response profile. The training data is used to train untrained neural networks. The correct labels can be generated by machine learning the network. For example, the results of a diagnosis by an experienced doctor are used. The training data includes multiple possible lung cancers. Response profiles detected in specimens from multiple subjects and multiple subjects without suspected lung cancer The learning model 122 includes a response profile detected from the examiner's subject. Learn the relationship between these response profiles and the likelihood of lung cancer.

[0133] The determination device 1 uses a plurality of response profiles included in the training data as neural networks before learning. It is input to the input layer of the network model, processed in the middle layer, and output from the output layer. The determination device 1 obtains the possibility of lung cancer output from the output layer. The presence or absence of lung cancer is compared with the presence or absence of lung cancer in the training data, and the output layer outputs For example, we use backpropagation to train neural networks so that the probability of lung cancer approaches the correct value. The learning model 122 is constructed by an external device. The information may be stored in the determination device 1 .

[0134] The determination device 1 uses an individual learning model corresponding to one or more cancers selected as the determination target. Each of the 123 cells was assigned a response profile for cancer assessment corresponding to the target cancer. , and obtain the probability of the target cancer output from each individual learning model 123 .

[0135] The input data to the individual learning model 123 is limited to images that represent the response profile of the luminescence intensity. The input to the individual learning model 123 may be the value of the luminous intensity over time. Of course, a response signal other than intensity may also be used.

[0136] The input data input to the individual learning model 123 further includes, as shown in FIG. The subject information that is an input element to the personalized learning model 123 may also be included. The subject information includes, for example, the subject's attributes such as age and sex, current symptoms, medical history, Includes health information such as test results and health check results.

[0137] The individualized learning model123 is not limited to predicting the possibility of cancer as either present or absent, but may also be used to predict the possibility of cancer as If desired, the possibility level may be classified into several levels according to the degree of possibility, and the possibility may be expressed as a percentage. A numerical value indicating a rate may be output.

[0138] The individualized learning model 123 analyzes responses to samples collected from subjects on multiple collection dates. It takes a profile, i.e., a time series response profile, as input and outputs the probability of cancer. In this case, the individual learning model 123 may be configured to use the latest response profile and The current probability of cancer in a subject is calculated using the response profile of the past few times as input. The device may output a prediction of the risk of cancer in the future.

[0139] The configuration of the learning model 122 is not limited to the above example. The learning model 122 may be, for example, a Recurrent Neural Network (RNN). al Network), GNN (Graph Neural Network), Transformer, SVM (Su Support Vector Machine), Logistics Regression, XGBoost (eXtreme Gradient Boost The model may be constructed using other learning algorithms such as sting.

[0140] As individual learning models123, one model was constructed for each type of cell42. In this case, the determination device 1 may determine whether the individual learning model 123 corresponding to the cell type is a It is advisable to derive an overall assessment result for one cancer based on the individual assessment results. The determination device 1 performs a comprehensive determination of the possibility of cancer using a determination model in the same manner as in the first embodiment. In this case, the determination model may be the type of cell 42 output from the learning model 122. The system may be configured to receive the probability of cancer for each individual as an input and output the probability of cancer. The learning model 122 is configured to output the probability of various types of cancer using one learning model 122. It may be configured.

[0141] FIG. 17 shows the procedure of the cancer possibility determination process executed by the determination system 100 of the third embodiment. 10 is a flowchart illustrating an example of the process.

[0142] The control unit 21 of the terminal device 2 executes the same processes as steps S20 to S21. Receive subject information and target cancer (step S50) and transmit (step S51). .

[0143] The control unit 11 of the determination device 1 executes the same processes as steps S22 to S24. The subject information and the target cancer are received (step S52), and a response profile is acquired (step S53). The acquired information is stored in the detection DB 121 (step S54).

[0144] The control unit 11 selects a plurality of individual learning models included in the learning model 122 stored in the storage unit 12. From the 123 messages, the target cancer and the corresponding cancer diagnosis cells 42 were selected. The individual learning model 123 that matches the learning model is selected (step S55).

[0145] The control unit 11 assigns the corresponding cancer determination cell 42 to each selected individual learning model 123. The control unit 11 inputs the response profile (step S56). Based on the information, the subject of the subject identified by the subject ID corresponding to the response profile The examiner information is read out, and the attributes and health information of the examinee corresponding to the read response profile are The control unit 11 may input the output from the individual learning model 123. The individualized learning model 123 obtains the probability of cancer (step S57). The control unit 11 outputs whether or not there is a possibility of cancer for each type of cancer. The same process as in step S32 is executed.

[0146] The determination device 1 may re-learn the learning model 122. 10 is a flowchart showing an example of a re-learning process of the delta 122.

[0147] The control unit 11 of the determination device 1 acquires the doctor's diagnosis of cancer in the subject ( Step S61). The diagnosis result is input by the subject through the terminal device 2 of the subject, for example. It may be acquired by accepting the application or by communicating with the medical institution's computer. Good too.

[0148] The control unit 11 uses the possibility of cancer indicated by the acquired doctor's diagnosis result to generate a learning model. The learning model 122 is re-learned and updated (step S62). The control unit 11 inputs the results of the diagnosis into the individual learning model 123 corresponding to the cancer type. Retraining response profiles and the probability of cancer indicated by diagnostic results as training data The control unit 11 updates the individual learning model 123. The parameters are optimized so that the predicted probability of cancer approximates the diagnosis result, and an individual learning model is created. Regenerate 123.

[0149] According to this embodiment, the possibility of cancer can be easily and accurately determined using the learning model 122. By constructing an individual learning model123 according to the type of cancer, The accuracy of determining the possibility can be improved. By using this as an input element, it is possible to determine the possibility of cancer by taking into account a wider range of information. This is expected to improve accuracy.

[0150] The operation of this system is improved by re-learning the learning model 122 based on the doctor's diagnosis results. The learning model 122 can be optimized through use.

[0151] (Fourth embodiment) In the fourth embodiment, a plurality of determination methods are used to determine the possibility of cancer. The determination device 1 determines the possibility of cancer based on the sensor data obtained by the olfactory sensor 4, and also: The result of the cancer possibility assessment made by another assessment method is obtained.

[0152] Other methods of assessment are not particularly limited as long as they can determine the possibility of cancer. For example, image data obtained by an image inspection device, detection data obtained by a physical sensor, or chemical sensor The detection data obtained by the sensor, the bio-devices using biological elements other than cells with olfactory receptors, One example is a method that uses detection data obtained by a sensor.

[0153] Methods that use image data include, for example, X-ray inspection equipment, CT inspection equipment, and MRI inspection equipment. Examples of such judgments include those based on image data obtained from devices such as PET scanners and ultrasound scanners. Examples of methods using detected data of physical quantities include body temperature, pulse, heart rate, intravascular pressure, intraocular pressure, etc. These include judgments based on detection data of physical quantities of enzymes, antibodies, nucleic acids, microorganisms, sugar chains, lipids, etc. As a method using the detection data of a biosensor equipped with a biological element such as a membrane, for example, urea , glucose, monoamines, sucrose, phospholipids, total cholesterol, triglycerides, amino acids Judgments are based on the detection data of chemical substances such as IgI, IgA, IgM, and albumin. Other methods of detection include genetic testing, chromosome testing, cell surface marker testing, and biomarker testing. Test data based on marker (e.g., amino acids, microRNA, nucleic acids, proteins, etc.) tests The determination process by each method may be performed by the determination device 1. The determination of the possibility of cancer by other determination methods may be performed by the olfactory sensor 4. The determination may be a primary determination, and a secondary determination may be made based on the results of the primary determination.

[0154] FIG. 19 is a flowchart showing an example of a processing procedure executed by the determination system 100 of the fourth embodiment. The determination system 100 performs the process up to step S27 in the first embodiment, for example. After making a comprehensive assessment of the possibility of cancer using the above method, the following process is carried out.

[0155] The control unit 11 of the determination device 1 determines whether or not the olfactory sensor 4 is used by a determination method different from the determination method using the olfactory sensor 4. The result of the cancer possibility assessment is obtained (step S71). The determination results may be obtained, for example, by communication with a computer at another testing institution. The results may be associated with the subject's identity.

[0156] The control unit 11 compares the acquired determination results by the different determination methods with the previously acquired olfactory sensor results. Based on the result of the determination by the determination method using 4, the final determination result is derived (step S 72) The control unit 11 determines the final judgment result as a majority vote of the judgment results obtained by the judgment method, for example. In the final judgment, weighting is applied to give greater weight to judgment results based on specific judgment methods. The control unit 11 may then execute the same processes as steps S28 to S32. do.

[0157] FIG. 20 is a schematic diagram showing an example of a result screen 51 showing the determination result of the fourth embodiment. In the example shown in 20, the result screen 51 displays information about the subject to be evaluated. a display unit 511 and a plurality of target cancers selected by the subject, 2 and a display unit 512.

[0158] Each second display unit 512 displays the type of target cancer and the assessment result for the target cancer. The determination device 1 performs a determination process for each type of determination method based on the determination results of each determination method. The result of the cancer possibility determination by the determination method is displayed on the second display unit 512. In addition, the final judgment result based on each judgment result is displayed on the second display unit 512.

[0159] According to this embodiment, by combining a plurality of determination methods, the accuracy of determining the possibility of cancer can be improved. By providing the subject with the results of each assessment method, It becomes possible to grasp the judgment results in detail.

[0160] The following additional notes are provided regarding the above-described embodiments. (Appendix 1) The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. obtaining a response signal to a target sample derived from the Based on the acquired response signal to the target sample, the possibility of cancer in the target is determined. judge A method for determining whether a process is executed by a computer. (Appendix 2) The receptor exhibits a responsiveness according to the likelihood of a particular cancer, Multiple receptors detected using multiple receptors corresponding to multiple types of cancer, Acquire a response signal to the target sample; Based on the response signals of the plurality of receptors obtained, the possibility of cancer in the subject to be determined is determined. and to determine the type of cancer The determination method described in Appendix 1. (Appendix 3) Detecting the response signal using a biosensor having a plurality of the receptors. The determination method described in Appendix 1 or Appendix 2. (Appendix 4) The receptor exhibits reactivity in response to a likelihood of a first cancer among a plurality of cancers, and 2. Receptors that do not show reactivity according to the possibility of cancer A determination method according to any one of appendices 1 to 3. (Appendix 5) The method is detected using a receptor that does not show reactivity according to the possibility of cancer in a subject. A response signal to the target sample is further acquired. A determination method according to any one of appendices 1 to 4. (Appendix 6) A response signal to samples derived from cancer patients and non-cancer patients related to the receptor; Based on a comparison with the response signal for the target sample, the possibility of cancer in the target is determined. Determine A determination method according to any one of appendices 1 to 5. (Appendix 7) Samples derived from cancer patients and non-cancer patients for each of the above receptors for each type of cancer and the response signal for the target sample, Determine the possibility and type of cancer in The determination method described in Appendix 6. (Appendix 8) Response signals to the samples derived from the cancer patient and the non-cancer patient are stored in advance. The determination method described in Appendix 6 or Appendix 7. (Appendix 9) Response signals to the samples derived from the cancer patient and the non-cancer patient, and and outputting information that distinguishes between the signal and the response signal. A determination method according to any one of appendices 6 to 8. (Appendix 10) The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. When a response signal for the target sample is input, the probability of cancer in the target is output. The acquired response signal for the target sample is input to a learning model for Determine the likelihood of cancer in a given subject 10. The method of determining whether or not a substance is present in a sample. (Appendix 11) Acquire target information including the attributes or health status of the target to be determined; When the target information related to the target and the response signal for the target sample are input, The subject information and the subject sample are input to the learning model, which outputs the possibility of cancer in the subject. A response signal to the test is input to determine the possibility of cancer in the test subject. The determination method described in Appendix 10. (Appendix 12) Response signals for each of multiple receptors to samples from cancer patients and non-cancer patients Obtain the number, Based on each response signal obtained, the possibility of cancer among the plurality of receptors is determined. Identifying the type or number of receptors 12. A determination method according to any one of claims 1 to 11. (Appendix 13) Responses of samples derived from cancer patients and non-cancer patients to each of the multiple receptors and obtaining a determination accuracy of the possibility of cancer based on the response signal; Based on the obtained determination accuracy, the receptors are used to determine the possibility of cancer. Identify the type and number of receptors 13. The method of any one of claims 1 to 12. (Appendix 14) acquiring response signals to the subject sample derived from the subject on a plurality of collection dates; A response signal for the target sample relating to each collection date obtained, and Output the result in association with the cancer possibility assessment result 14. The method of any one of claims 1 to 13.

[0161] The embodiments disclosed herein are illustrative in all respects and are not to be considered as limiting. The technical features described in each embodiment can be combined with each other. The scope of the present invention includes all modifications within the scope of the claims and the scope equivalent to the claims. is intended to include. The sequences shown in each embodiment are not limited to those shown in the above, and each processing step may be performed as long as there is no contradiction. The order of the steps may be changed, and multiple steps may be performed in parallel. The processing entity of each process is not limited, and the processing of each device may be controlled by other devices within the scope of no contradiction. The device may execute the process.

[0162] The features described in each embodiment can be combined with each other. The scope of the invention includes all combinations of independent and dependent claims, regardless of their form of reference. Furthermore, the claims may include other The claim citing two or more claims (multiple claim format) is used. Multi-claims that cite at least one other claim may be used, but are not limited to this. It is also possible to write it in the format used to write a system (multiple multiple claim). [Explanation of symbols]

[0163] 100 Judgment System 1 Judgment device 11 Control section 12 Storage section 13 Communications Department 1A Recording Media 1P Program 121 Detection DB 122 Learning Model 2. Terminal Device 21 Control Unit 22 Memory section 23 Communications Department 24 Display section 25 Control section 2A Recording Media 2P Program 3. Detection equipment 4. Olfactory sensor 42 cells

Claims

1. The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. obtaining a response signal to a target sample derived from the Based on the acquired response signal to the target sample, the possibility of cancer in the target is determined. judge A method for determining whether a process is executed by a computer.

2. The receptor exhibits a responsiveness according to the likelihood of a particular cancer, Multiple receptors detected using multiple receptors corresponding to multiple types of cancer, Acquire a response signal to the target sample; Based on the response signals of the plurality of receptors obtained, the possibility of cancer in the subject to be determined is determined. and to determine the type of cancer The determination method according to claim 1 .

3. Detecting the response signal using a biosensor having a plurality of the receptors. The determination method according to claim 1 or 2.

4. The receptor exhibits reactivity according to the likelihood of a first cancer among a plurality of cancers, and It is a receptor that does not show reactivity according to the possibility of cancer 2. The determination method according to claim 1 or 2.

5. The method is detected using a receptor that does not show reactivity according to the possibility of cancer in a subject. A response signal to the target sample is further acquired. The determination method according to claim 1 or 2.

6. A response signal to samples derived from cancer patients and non-cancer patients related to the receptor; Based on a comparison with the response signal for the target sample, the possibility of cancer in the target is determined. Determine The determination method according to claim 1 or 2.

7. Samples derived from cancer patients and non-cancer patients for each of the above receptors for each type of cancer and the response signal for the target sample, Determine the possibility and type of cancer in The determination method according to claim 6.

8. Response signals to the samples derived from the cancer patient and the non-cancer patient are stored in advance. The determination method according to claim 6.

9. Response signals to the samples derived from the cancer patient and the non-cancer patient, and and outputting information that distinguishes between the signal and the response signal. The determination method according to claim 6.

10. The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. When a response signal for the target sample is input, the probability of cancer in the target is output. The acquired response signal for the target sample is input to a learning model for Determine the likelihood of cancer in a given subject The determination method according to claim 1 or 2.

11. Acquire target information including the attributes or health status of the target to be determined; When the target information related to the target and the response signal for the target sample are input, The subject information and the subject sample are input to the learning model, which outputs the possibility of cancer in the subject. A response signal to the test is input to determine the possibility of cancer in the test subject. The determination method according to claim 10.

12. Response signals for each of multiple receptors to samples from cancer patients and non-cancer patients Obtain the number, Based on each response signal obtained, the possibility of cancer among the plurality of receptors is determined. Identifying the type or number of receptors The determination method according to claim 1 or 2.

13. Responses of samples derived from cancer patients and non-cancer patients to each of the multiple receptors and obtaining a determination accuracy of the possibility of cancer based on the response signal; Based on the obtained determination accuracy, the receptors are used to determine the possibility of cancer. Identify the type and number of receptors The determination method according to claim 1 or 2.

14. acquiring response signals to the subject sample derived from the subject on a plurality of collection dates; A response signal for the target sample relating to each collection date obtained, and Output the result in association with the cancer possibility assessment result The determination method according to claim 1 or 2.

15. The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. obtaining a response signal to a target sample derived from the Based on the acquired response signal to the target sample, the possibility of cancer in the target is determined. judge Equipped with a control unit that executes processing Judgment device.

16. The subject to be evaluated is detected using a receptor that shows reactivity according to the possibility of cancer in the subject. obtaining a response signal to a target sample derived from the Based on the acquired response signal to the target sample, the possibility of cancer in the target is determined. judge A computer program that causes a computer to perform a process.

Images