Determination Method, Determination Device, and Computer Program

Abstract

Provided are a determination method and the like that can determine the possibility of cancer using a receptor. 【Solution means】The determination method acquires a response signal for a target sample derived from a determination target, which is detected using a receptor that exhibits reactivity according to the possibility of cancer in the target, and based on the acquired response signal for the target sample, a computer executes a process of determining the possibility of cancer in the determination target.

Description

Technical Field

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

Background Art

[0002] In recent years, research and development on biosensors using biodevices have been underway. For example, Patent Document 1 discloses an inexpensive odor sensor including a transistor having a gate electrode containing aluminum or aluminum oxide, insect cells having an olfactory receptor disposed on the gate electrode, and a detection device that detects a current generated in the transistor when the insect cells react to an odor.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the technique described in Patent Document 1 does not determine the possibility of cancer using a receptor.

[0005] An object of the present disclosure is to provide a determination method and the like that can determine the possibility of cancer using a receptor.

Means for Solving the Problems

[0006] A determination method according to an aspect of the present disclosure acquires a response signal for a target sample derived from a determination target, which is detected using a receptor that exhibits reactivity according to the possibility of cancer in the target, and based on the acquired response signal for the target sample, a computer executes a process of determining the possibility of cancer in the determination target.

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

[0008] A computer program according to one aspect of the present disclosure acquires a response signal for a target sample derived from a determination target, which is detected using a receptor that exhibits reactivity according to the possibility of cancer in the target, and determines the possibility of cancer in the determination target based on the acquired response signal for the target sample.

Advantages of the Invention

[0009] According to the present disclosure, the possibility of cancer can be determined using a receptor.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Mode for Carrying Out the Invention

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

[0012] (First Embodiment) FIG. 1 is a schematic diagram of a determination system 100. The determination system 100 of the present embodiment includes a determination device 1, a terminal device 2, a detection device 3, and an olfactory sensor 4. The olfactory sensor 4 is an example of a biosensor. The determination device 1 is communicably connected to the terminal device 2 and the detection device 3 through a network N such as the Internet. In the determination system 100, based on the detection result of odor molecules in a subject derived from a subject detected by the detection device 3 and the olfactory sensor 4, the possibility of cancer in the target is determined, and the determination device 1 provides a service for presenting the determination result via the terminal device 2.

[0013] In the following embodiments, a case will be described by way of example in which the possibility of cancer in a subject is determined based on odor molecules detected from the urine of the subject (sample). The types of cancer to be determined are not limited, and examples include lung cancer, esophageal cancer, breast cancer, gastric cancer, liver cancer, pancreatic cancer, gallbladder cancer, bile duct cancer, colorectal cancer, kidney cancer, bladder cancer, ovarian cancer, uterine cancer, prostate cancer, oral cancer, pharyngeal cancer, and the like.

[0014] The determination device 1 is an information processing device capable of various information processing and information transmission and reception, and is, for example, a server computer, a personal computer, a quantum computer, or the like. The determination device 1 acquires a signal indicating the response of the odor to the urine of the subject, determines the possibility of cancer in the subject based on the acquired signal, and realizes a service of providing the determination result to the user through the terminal device 2. The determination device 1 may be a local computer provided in the facility where the detection device 3 is installed.

[0015] The terminal device 2 is an information processing terminal used by the subject, and is, for example, a personal computer, a smartphone, a tablet terminal, or the like. The terminal device 2 displays the determination result received from the determination device 1. The subject is an example of a user who receives the provision of the determination result. The determination result is not limited to being provided to the subject, and may be provided to, for example, medical personnel, persons in charge of analysis institutions performing analysis, and the like. The number of terminal devices 2 connected to the determination device 1 may be 1 or 3 or more.

[0016] The olfactory sensor 4 and the detection device 3 are managed by, for example, an analysis institution. The analysis institution is a facility that receives a specimen collected from a subject and performs an analysis of the received specimen. The olfactory sensor 4 includes cells 42 (see FIG. 2) that express olfactory receptors as detection elements, and outputs a signal indicating a response of the olfactory receptor to odor molecules. The detection device 3 detects the response signal from the olfactory sensor 4. In addition to the function as a detector that performs the detection of the above-described response signal, the detection device 3 has the function as a computer that performs various data processes and communication with an external device, and transmits the detection data of the response signal obtained by the detection to the determination device 1 through the network N. Note that the detector and the computer may be provided separately and configured to be communicable with each other. The number of detection devices 3 connected to the determination device 1 may be 1 or 3 or more.

[0017] FIG. 2 is a schematic diagram showing a configuration example of the olfactory sensor 4. FIG. 2 is a view of the olfactory sensor 4 seen from above. The olfactory sensor 4 includes a substrate 41 and cells 42 disposed in wells 43 formed in the substrate 41. As the substrate 41, for example, a "384-well plate" in which 384 wells 43 are formed is used. In FIG. 2, for simplicity of illustration, a "24-well plate" in which 24 wells 43 are formed is shown as the substrate 41. In the present embodiment, cells 42 composed of a plurality of the same kind of cells are arranged in each of the plurality of wells 43. That is, a large number of the same kind of cells are seeded at high density in each well 43. Note that the cells 42 may be composed of one kind of cell. Each cell has an olfactory receptor. The cells 42 function as sensor cells that output a signal indicating a response of the olfactory receptor to odor molecules. The cells 42 are an example of a sensor element. The olfactory receptor responds to specific odor molecules. By detecting a response signal based on the binding between the olfactory receptor provided in the olfactory sensor 4 and the odor molecule, the odor molecule contained in the urine of the subject can be selectively detected.

[0018] The substrate 41 is made of a material such as glass, silicon, ceramics, resin, metal, etc. On the surface of the substrate 41, surface treatments such as plasma treatment, corona treatment, UV - Ozone treatment, etc., or coating using polypeptides, etc. may be performed. The shape of the substrate 41 may be any shape as long as the odor can be detected using the cells 42 arranged on the substrate 41, for example, it is a rectangular plate shape. The size of the substrate 41 is not particularly limited and can be appropriately set according to the number of cells 42 arranged on the substrate 41, etc.

[0019] As the olfactory receptor, those derived from animals can be used. Examples of animals include insects, vertebrates, mammals, etc., and for example, olfactory receptors of flies, mosquitoes, mice, rats, rabbits, cows, dogs, humans, etc. can be used. As the olfactory receptor, insect olfactory receptors are preferred. Insect olfactory receptors form a heterocomplex with olfactory receptor coreceptors and function as ion channels activated by odor molecules.

[0020] The amino acid sequences and coding sequences of the olfactory receptor and the olfactory receptor coreceptor are known or can be easily identified by sequence identity search based on known sequences. Furthermore, it can contain amino acid mutations with respect to known amino acid sequences. Amino acid mutations are, for example, substitution, insertion, addition, or deletion of amino acids.

[0021] As the cells 42, specific cells that naturally express olfactory receptors may be used, or genetically recombinant cells incorporated with the gene of the olfactory receptor may be used. Genetically recombinant cells can be prepared by transforming cells using a vector incorporated with the olfactory receptor gene. When the olfactory receptor is an insect olfactory receptor, it is preferably further incorporated with the gene of the olfactory receptor coreceptor.

[0022] Cell 42 may further have a fluorescent protein or a luminescent protein. In cell 42, when an odorant molecule binds to an ion channel-type olfactory receptor, cations such as calcium ions flow into the cell. By introducing into cell 42 a gene that expresses a fluorescent protein whose fluorescence intensity changes according to the ion concentration or a luminescent protein whose luminescence intensity changes, the response of the cell to the odorant molecule can be detected by the change in fluorescence intensity or luminescence intensity. That is, it is possible to detect the odorant molecule by the change in fluorescence intensity or luminescence intensity. Examples of such proteins include aequorin, Yellow Cameleon, GCaMP, and the like.

[0023] A calcium ion-dependent fluorescent dye may be introduced into cell 42. By introducing a calcium ion-dependent fluorescent dye into the cell, the influx of calcium ions into the cell due to the binding of an odorant molecule to the olfactory receptor can be detected by the change in fluorescence intensity. Examples of such calcium ion-dependent fluorescent dyes include Fura-2, Fluo-3, Fluo-4, and the like.

[0024] The detection device 3 detects a signal indicating the response of cell 42 based on the binding between the olfactory receptor and the odorant molecule. The detection device 3 performs detection, for example, for each well 43 in the olfactory sensor 4, with the luminescence intensity as the detection target. The detection device 3 includes, for example, a photomultiplier tube and detects the fluorescence or luminescence intensity based on the change in the ion concentration inside the cell. The response signal of cell 42 detected by the detection device 3 is not limited to the fluorescence or luminescence intensity, and may be an electrical signal (potential) based on the change in the ion concentration inside the cell. The response signal may be a moving image or a still image obtained by photographing the state of luminescence of cell 42 with an imaging device such as a CCD camera.

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

[0026] Generally, olfactory receptors have selectivity for odor molecules. Therefore, it is possible to detect multiple types of odors by arranging a plurality of cells 42 expressing different olfactory receptors on a substrate 41 and detecting the responses of these cells 42 respectively. One cell 42 may have one type of olfactory receptor or may have multiple types of olfactory receptors. The olfactory sensor 4 may include a plurality of the same cells 42. The olfactory sensor 4 of the present embodiment includes different types of cells 42, and each cell 42 has one type of olfactory receptor.

[0027] The number, type, and arrangement position of the olfactory receptors used in the olfactory sensor 4 can be appropriately determined according to the odor molecules to be detected and the type of cancer to be judged. The olfactory receptors may be a specific combination for the odor molecules for which detection is desired, or a large number of olfactory receptors may be combined and used comprehensively for various odor molecules. For example, the number of cells 42 mounted on one olfactory sensor 4, that is, the total number of sensor cells mounted on one olfactory sensor 4, can be 1 or more and 50,000 or less, and the types of cells 42 mounted on one olfactory sensor 4 can be 1 or more and 2,000 or less.

[0028] The method for detecting the response signal is not limited to the above example, and an appropriate method can be used according to the olfactory receptors in the olfactory sensor 4 and the types of odor molecules sensed by the olfactory receptors.

[0029] Figure 3 is a block diagram showing the configuration of the determination device 1. The determination device 1 includes a control unit 11, a storage unit 12, and a communication unit 13. The determination device 1 may be a single computer, or may be a computer system composed of a plurality of computers, peripheral devices, etc. The determination device 1 may be a virtual machine with its entity virtualized, or may be a cloud.

[0030] The control unit 11 includes one or more arithmetic processing units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The control unit 11 controls each component and executes processing by using a memory such as a built-in ROM (Read Only Memory) or RAM (Random Access Memory), a clock, a counter, etc. The functional units of the control unit 11 may be realized software-wise, or a part or all of them may be realized by hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0031] The storage unit 12 includes a non-volatile memory such as a hard disk, a flash memory, or an SSD (Solid State Drive). The storage unit 12 is separate from the determination device 1 and may be one or more externally connected external storage devices. The storage unit 12 stores various computer programs and data referred to by the control unit 11. The storage unit 12 stores a program 1P for causing a computer to execute processing related to the determination of the possibility of cancer and a detection DB (Data Base) 121. The storage unit 12 may further store a reference profile described later.

[0032] A computer program (program product) including the program 1P may be provided by a non-temporary recording medium 1A that records the computer program in a readable manner. The storage unit 12 stores the computer program read from the recording medium 1A by a reading device (not shown). The recording medium 1A is, for example, a magnetic disk, an optical disk, a semiconductor memory, etc. Also, a computer program may be downloaded from an external server connected to a communication network and stored in the storage unit 12. The program 1P may be a single computer program or may be composed of a plurality of computer programs. The program 1P may also be executed on a single computer or may be executed in cooperation by a plurality of computers.

[0033] The communication unit 13 includes a communication device that realizes communication via the network N. The control unit 11 transmits and receives data to and from 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, it may include an operation unit for receiving user operations, a display unit for displaying images, and the like.

[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 may include, for example, an input interface for connecting the detection device 3, and receive data output from the detection device 3 through a signal line or the like.

[0036] FIG. 4 is a diagram showing an example of the content of the information stored in the detection DB 121. The detection DB 121 is a database that stores detection information regarding each of a plurality of subjects, subject information regarding a subject, and reference profile information regarding a reference profile.

[0037] In the detection information table, for example, records associating information such as subject ID, subject ID, collection date, detection device ID, detection date, detection data, and determination result are stored using the subject ID as a key. The subject ID is identification information for uniquely identifying a subject collected from a subject. The subject ID may be an ID attached to a storage container that houses a specific subject. The subject ID is identification information for identifying a subject. The collection date represents the date and time when the subject was collected. The detection device ID is identification information for identifying the detection device 3 used to detect the response signal for the subject. The detection date represents the date and time when the detection device 3 detected the response signal for the subject.

[0038] The detection data includes information indicating a response signal to the subject. The detection data is, for example, a profile of the response signal detected over time. In the present embodiment, the profile of the response signal as the detection data is the data of the emission intensity over time. The detection data is generated for each cell 42 in the olfactory sensor 4. The determination result represents the possibility of cancer based on the detection data. The determination result may be indicated, for example, by the presence or absence of possibility, or may be indicated by the degree of possibility classified into multiple stages. The information in the detection information table is collected, for example, through the detection device 3.

[0039] In the subject information table, records associating information such as terminal device information and subject attribute information are stored, for example, using the subject ID as a key. The detection information table and the subject information table are associated by the subject ID. The terminal device information is information for identifying the terminal device 2 used by the subject, and includes, for example, an address indicating the output destination of the determination result, a device ID, and the like. The attribute information includes, for example, the subject's name, age, gender, health information, and the like. The health information is information regarding the health status of the subject, and may include information such as current symptoms, medical history, examination results, and health diagnosis results. The information in the subject information table is collected, for example, through the terminal device 2.

[0040] In the reference profile information table, records associating cell information and information such as first reference profile information and second reference profile information are stored, for example, using the cancer ID as a key. The cancer information is information for identifying the cancer to be determined, and includes, for example, the cancer ID, the cancer name (cancer type), and the like. The cell information is information for identifying the cell 42 in the olfactory sensor 4, and is information representing the cell type selected for cancer determination. The first reference profile information and the second reference profile information are information regarding the first reference profile and the second reference profile corresponding to the above cell information. Details of the first reference profile and the second reference profile will be described later. Note that FIG. 4 is an example, and the content of the information stored in the detection DB121 is not limited. Also, the way of holding the data shown in FIG. 4 is an example, and other storage forms may be used as long as the data content and the relationship between the data are maintained.

[0041] FIG. 5 is a block diagram showing the configuration of the terminal device 2. The terminal device 2 includes a control unit 21, a storage 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 devices such as a CPU, MPU, and GPU. The control unit 11 uses a built-in memory such as a ROM or RAM, a clock, a counter, etc., to control each component and execute processing.

[0043] The storage unit 22 includes a non-volatile memory such as a hard disk, a flash memory, and an SSD. The storage unit 22 stores various computer programs and data referred to by the control unit 21. The storage unit 22 stores a program 2P for causing a computer to execute processing related to obtaining a determination result of the possibility of cancer.

[0044] A computer program (computer program product) including the program 2P may be provided by a non-temporary recording medium 2A that records the computer program in a readable manner. The storage unit 22 stores the computer program read from the recording medium 2A by a reading device (not shown). The recording medium 2A is, for example, a magnetic disk, an optical disk, a semiconductor memory, etc. Also, a computer program may be downloaded from an external server connected to the communication network and stored in the storage unit 22. The program 2P may be a single computer program or may be composed of a plurality of computer programs. The program 2P may also be executed on a single computer or may be executed in cooperation by a plurality of computers.

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

[0046] The display unit 24 includes a display device such as a liquid crystal display, an organic EL (Electro Luminescence) display, etc. The display unit 24 displays various information including the determination result according to an instruction from the control unit 21.

[0047] The operation unit 25 is an interface that receives a user's operation. The operation unit 25 includes, for example, a keyboard, a mouse, a touch panel device built into the display, a speaker, and a microphone, etc. The operation unit 25 receives an operation input from the user and sends a control signal corresponding to the operation content to the control unit 21.

[0048] FIG. 6 is a diagram showing an example of the change over time of the light emission intensity of the sensor cells. The vertical axis of the graph shown in FIG. 6 is the light emission intensity, and the horizontal axis is the time (s). In FIG. 6, the detection results of the light emission intensity when a solution containing a specific odor molecule is added to cells expressing an olfactory receptor that binds to the odor molecule are shown for each concentration of the odor molecule. In FIG. 6, from the highest concentration of the odor molecule in order, they are the first concentration, the second concentration, and the third concentration.

[0049] As shown in FIG. 6, the profile showing the change over time of the light emission intensity depends on the concentration. In the present embodiment, based on the response profile of the light emission intensity detected from the urine sample of the subject, by estimating the characteristics of a specific group of urinary odor molecules detectable by the sensor cells, the possibility of cancer in the subject is determined.

[0050] Hereinafter, a specific example will be given to explain the flow of the determination process in the determination system 100 of the present embodiment.

[0051] The determination device 1 receives an application for the determination service from the subject. A user (subject) who wishes to use the service applies, for example, using the terminal device 2 through the reception screen 50 provided by the determination device 1.

[0052] FIG. 7 is a schematic diagram showing an example of the reception screen 50. When the determination device 1 receives a login request using the account information by the operation of the subject through the terminal device 2 and a request for the reception screen, the determination device 1 outputs the reception screen 50 to the terminal device 2 as shown in FIG. 7 and causes it to be displayed on the display unit 24.

[0053] The reception screen 50 includes a subject information reception field 501 for receiving input of subject information regarding the subject to be determined, and a cancer information reception field 502 for receiving input of the target cancer for which determination is desired. The subject uses the operation unit 25 to input the name etc. of the subject to be determined into the subject information reception field 501. In the case of a subject who has already been registered as a user in advance, the determination device 1 may read out the subject information corresponding to the logged-in account information with reference to the detection DB 121 and display the read subject information in the subject information reception field 501.

[0054] The cancer information reception field 502 displays a plurality of cancers that can be determined by the determination system 100 in a selectable manner. The subject can input the designation of one or more cancers for which determination is desired, for example, by selecting the check boxes associated with each cancer. In the example shown in FIG. 7, lung cancer is selected as the target cancer.

[0055] The determination device 1 calculates the usage fee for the determination service so that the amount increases as the total number of target cancers selected as the determination desire increases. The usage fee may be changed according to the type of target cancer. The determination device 1 displays the calculated usage fee at the lower part of the cancer information reception field 502.

[0056] When the application button 503 for specifying the application for determination is selected in a state where various pieces of information are input in the subject information reception column 501 and the cancer information reception column 502, the terminal device 2 transmits the received subject information and the target cancer to the determination device 1. The determination device 1 receives the subject information and the target cancer and accepts the application for determination. The determination device 1 stores the received subject information and the target cancer in the storage unit 12, and, if necessary, transmits information corresponding to the subject information and the target cancer to the detection device 3 of the analysis institution that conducts the examination.

[0057] The reception screen 50 may also include a payment method reception column 504 as shown in FIG. 7. The subject can specify a desired payment method by selecting a specific payment method from the payment method reception column 504. The terminal device 2 may execute processing for online payment or credit card payment with a predetermined payment server or the like according to the received payment method.

[0058] Note that information related to the application for the determination service is not limited to being received through the terminal device 2. The determination device 1 may acquire subject information and the like by receiving an input from the user, for example.

[0059] When the application is completed, a urine collection container is sent to the subject. The urine collection container may be distributed through a predetermined store, analysis institution, or the like. A label with a two-dimensional code or three-dimensional code representing the subject ID, for example, is attached to the urine collection container. The subject collects the urine in the urine collection container and submits it to the analysis institution. The urine collection container may be submitted together with the subject's attribute information such as the subject's name, the collection date, the application number issued at the time of the determination application, and the like.

[0060] At the analysis institution, the urine collection container is received. The detection device 3 acquires the specimen ID, subject ID, collection date, etc. of the specimen to be examined by receiving an input from the person in charge, for example.

[0061] Next, the analysis institution detects the response signal using the olfactory sensor 4. In the olfactory sensor 4, a predetermined number of cells 42 expressing different olfactory receptors are arranged in an array. The olfactory sensor 4 is produced, for example, by integrating DNA containing a specific insect olfactory receptor coding sequence, a specific insect olfactory receptor coreceptor coding sequence, and a calcium-sensitive luminescent protein coding sequence arranged under the control of a promoter sequence into the chromosomal genomic DNA of each cell.

[0062] A predetermined amount of the test substance (for example, a urine specimen derived from the subject) is brought into contact with the olfactory sensor 4, and the luminescence intensity of each cell is detected over time by the detection device 3. Thereby, a response profile representing the change in luminescence intensity over time is obtained. The response profile is generated for each cell 42 in the olfactory sensor 4. The detection device 3 associates the obtained response profile with the specimen ID, subject ID, collection date, detection device ID, detection date, etc. of the test substance to be inspected and transmits it to the determination device 1.

[0063] The determination device 1 may generate a response profile by performing a predetermined preprocessing on the detection data received from the detection device 3. The measurement of the luminescence intensity with respect to the olfactory sensor 4 may be performed collectively on a plurality of sensor cells arranged in an array. In such a case, it is assumed that the raw detection data output from the detection device 3 is data including the luminescence intensity at various times (detection times) for a plurality of sensor cells. Or, the detection data may contain detection values related to urine specimens from a plurality of subjects. The determination device 1 generates a response profile by sorting the raw detection data including a plurality of detection values for each sensor cell or for each urine specimen derived from the subject, arranging the luminescence intensity over time, and converting it into a predetermined data format. When the times of the luminescence intensity in the raw detection data are different, the determination device 1 may unify the times of each data in the response profile by interpolating the data using a predetermined interpolation method.

[0064] The determination device 1 determines the likelihood of cancer in the subject based on the response profile of the urine sample derived from the subject obtained. In the present embodiment, the likelihood of cancer is determined by comparing the response profile of the urine sample derived from the subject to be analyzed with a reference profile generated in advance.

[0065] The reference profile includes a first reference profile based on the luminescence intensity detected from urine samples derived from subjects in good health and a second reference profile based on the luminescence intensity detected from urine samples derived from subjects in poor health. As an example, when the target cancer is lung cancer, a subject in good health means a cancer-free non-sufferer who does not have cancer, and a subject in poor health means a lung cancer patient who has lung cancer. The reference profile is, for example, generated in advance and stored in the storage unit 12.

[0066] The first reference profile and the second reference profile are obtained by detecting the above-mentioned odor molecules with the olfactory sensor 4 using urine collected from cancer-free subjects (hereinafter also referred to as healthy urine) and urine collected from lung cancer patients (hereinafter also referred to as lung cancer urine), and generating a response profile. The first reference profile and the second reference profile are prepared for each cell 42.

[0067] The first reference profile is preferably generated based on the response profiles of a plurality of healthy urine samples obtained from a plurality of cancer-free subjects. Similarly, the second reference profile is preferably generated based on the response profiles of a plurality of lung cancer urine samples obtained from a plurality of lung cancer patients. For example, the statistical value of the luminescence intensity detected from each healthy urine is calculated for each time, and the first reference profile is generated based on the obtained statistical value. As the statistical value, the average value or the median is preferable, the weighted average, the geometric average or the median is more preferable, and the geometric average is most preferable. In the same manner, the second reference profile is generated based on the response profiles of a plurality of lung cancer urine samples obtained from a plurality of lung cancer patients.

[0068] Furthermore, one or more cells 42 suitable for the determination of lung cancer as the cancer to be determined are selected from among the plurality of types of cells 42 included in the olfactory sensor 4. The cells suitable for the determination of lung cancer are cells that exhibit reactivity in response to lung cancer urine. As the cells suitable for the determination of lung cancer, preferably, the reactivity significantly changes according to the presence or absence of lung cancer, and there are significant differences in the response profiles. The cells suitable for the determination of lung cancer may be cells that react to odor molecules contained relatively more in lung cancer urine than in healthy urine, or may be cells that react to odor molecules whose content decreases in lung cancer urine compared to healthy urine. In the present embodiment, the cells 42 that react to odor molecules contained more in lung cancer urine than in healthy urine are defined as the cells 42 suitable for the determination of lung cancer.

[0069] In the production stage of the olfactory sensor 4, it is not easy to specify in advance the cells 42 suitable for the determination of the cancer to be determined. For this reason, in the present embodiment, an olfactory sensor 4 equipped with a plurality of types of cells 42 is prepared, and for each cancer to be determined, the cells 42 suitable for the determination of the cancer are specified from among the plurality of types of cells 42.

[0070] The method for specifying the cells 42 suitable for the determination of cancer is not limited. For example, it can be specified based on the dissimilarity between the first reference profile and the second reference profile. The determination device 1 may calculate the dissimilarity between the first reference profile and the second reference profile, and specify the cells 42 whose calculated dissimilarity is equal to or greater than a first threshold value set in advance as the cells 42 for cancer determination.

[0071] As the dissimilarity between the first reference profile and the second reference profile, for example, a difference value between the maximum value of the emission intensity in the first reference profile and the maximum value of the emission intensity in the second reference profile is used. As the dissimilarity, an area value surrounded by the first reference profile and the second reference profile (an intensity difference integral value obtained by integrating the intensity difference between the first reference profile and the second reference profile) may be used. The greater the difference between the maximum values of the intensities between the reference profiles or the intensity difference integral value, the lower the similarity between the first reference profile and the second reference profile, which means that the change in reactivity according to the presence or absence of the possibility of cancer is large. That is, the response difference of the cell 42 according to the presence or absence of the possibility of cancer is large, and it is considered to be highly useful in cancer determination. Note that although the dissimilarity between the first reference profile and the second reference profile is used above, the similarity may be used.

[0072] The selection of the cell 42 for cancer determination may be performed in consideration of the cancer determination accuracy using the cell 42. For example, for a plurality of cells 42 preliminarily selected for cancer determination, response profiles for a plurality of samples for examination are acquired, and the possibility of cancer is determined according to a determination method described later using the acquired response profiles. Based on the determination result related to each cell 42 and the characteristics of the known samples for examination (healthy urine or lung cancer urine), the determination accuracy when each cell 42 preliminarily selected is used is obtained. The determination accuracy includes, for example, the AUC of the ROC curve, recall rate, specificity, accuracy, precision, and the like. Based on the obtained determination accuracy values, the type and number of the cells 42 selected for cancer determination are specified so as to optimize each determination accuracy (for example, so that each determination accuracy becomes maximum). The cell 42 for cancer determination is secondarily selected so as to conform to the specified type and number of the cells 42.

[0073] FIG. 8 is a diagram showing an example of a reference profile related to cells selected for cancer determination and a reference profile related to cells not selected for cancer determination. FIG. 8A shows a reference profile related to cells selected for cancer determination, and FIG. 8B shows an example of a reference profile related to cells not selected for cancer determination. In the case of cells for cancer determination, the shape of the response profile is significantly different between healthy urine and pseudo-lung cancer urine (urine obtained by adding odor molecules derived from lung cancer to healthy urine). On the other hand, in the case of cells not for cancer determination, no significant difference is observed in the response profile between healthy urine and pseudo-lung cancer urine.

[0074] Note that when the type of the cell 42 suitable for the determination of a specific cancer is known, the step of selecting the cell 42 for cancer determination may be omitted.

[0075] The determination device 1 determines the possibility of lung cancer by determining the similarity between the response profile of the urine sample of the subject corresponding to the selected cell 42 for cancer determination and each of the first reference profile and the second reference profile corresponding to the cell 42 for cancer determination. When the similarity with the first reference profile is higher than the similarity with the second reference profile, it is determined that there is no possibility of lung cancer. When the similarity with the second reference profile is higher than the similarity with the first reference profile, it is determined that there is a possibility of lung cancer. The determination device 1 may determine the possibility of lung cancer in multiple stages, as a percentage, etc., according to the value of the similarity.

[0076] The method for determining the above similarity is not limited. For example, the absolute value of the difference between the luminescence intensity in the response profile of the urine sample of the subject and the luminescence intensity in the reference profile may be calculated for each elapsed time, and the sum of the calculated absolute values of the differences may be used as an index for determining the similarity. The smaller the sum of the absolute values of the differences in luminescence intensity, the higher the similarity.

[0077] When a plurality of cancer-determining cells 42 are selected, the determination device 1 individually determines the possibility of lung cancer based on each of the cancer-determining cells 42, and comprehensively determines the possibility of lung cancer by integrating the individually determined possibilities of lung cancer. The determination device 1, for example, makes a majority decision of the determination results based on each cell 42 as the comprehensive determination. At the time of comprehensive determination, weighting may be performed so as to increase the weight of the determination result based on a specific cell 42. The cell 42 for which weighting is performed may be a cell 42 having higher usefulness in cancer determination, a cell 42 having higher similarity, a cell 42 having less variation in response signals, or the like.

[0078] The determination of the possibility of lung cancer may be performed using a machine learning method. The determination device 1 prepares in advance a determination model that outputs the possibility of lung cancer when the similarity between the response profile of each cancer-determining cell 42 and the reference profile is input. The similarity includes at least one of the similarity between the response profile of the subject's urine sample and the first reference profile, and the similarity between the response profile and the second reference profile.

[0079] The determination device 1 inputs the similarity regarding the response profile of each cancer-determining cell 42 into the determination model, and obtains the possibility of lung cancer output from the determination model. The type of the cell 42 may be input into the determination model together with the similarity. The determination result of the possibility of lung cancer output from the determination model corresponds to the comprehensive determination result. In this case, the individual determination based on each cell 42 may be omitted.

[0080] In addition, when the types of cells 42 suitable for the determination of a specific cancer are known, for each type of cancer to be determined, individual olfactory sensors 4 may be generated using only the cells 42 suitable for the determination of cancer. In this case, the detection of the luminescence intensity is performed using the individual olfactory sensors 4 corresponding to the selected target cancer, and the possibility of cancer is determined based on the detection results of the respective cells 42 in the individual olfactory sensors 4. The determination device 1 stores, in the detection DB 121, by associating them, a series of obtained information, such as the subject ID, the subject ID, the collection date, the detection device ID, the detection date, the response profile, and the determination result. The determination device 1 also outputs the determination result to the terminal device 2 of the subject.

[0081] FIG. 9 is a schematic diagram showing an example of a result screen 51 indicating the determination result. The result screen 51 includes a first display unit 511 that displays information about the subject to be determined and a second display unit 512 that displays the determination result.

[0082] Based on the information stored in the detection DB 121, the determination device 1 causes the first display unit 511 to display information about the subject and the subject to be determined. For example, the name of the subject, the collection date of the subject, and the subject ID are displayed on the first display unit 511.

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

[0084] FIG. 10 is a schematic diagram showing another example of the result screen 51 indicating the determination result. In the example shown in FIG. 10, the second display unit 512 of the result screen 51 further includes a detection result display column 513 that displays the detection result for the subject detected by the olfactory sensor 4. The response profile corresponding to the subject is displayed in the detection result display column 513.

[0085] In the detection result display column 513, in addition to the response profile corresponding to the subject, the determination criteria used in the cancer determination process, that is, the first reference profile and the second reference profile, may be displayed. In FIG. 10, for ease of explanation, only one type of response profile is shown, but in the detection result display column 513, a plurality of response profiles indicating the detection results for each cell 42 used for cancer determination may be displayed. In the detection result display column 513, an image showing the light emission state of the cells 42 in the olfactory sensor 4 captured by the imaging device may be displayed.

[0086] When displaying the response profiles related to a plurality of cells 42 in the detection result display column 513, the determination device 1 may determine the display order on the screen based on the usefulness in cancer determination or the similarity between each response profile and the reference profile. For example, the determination device 1 preferentially displays the detection results of the cells 42 with high usefulness or similarity in the detection result display column 513. The determination device 1 may display the detection results related to a predetermined number of cells 42 in the detection result display column 513 in descending order of priority. The determination device 1 may also determine the display order based on the contribution degree of the input information in the above-described determination model, such that the higher the contribution degree of the similarity related to the cell 42, the more preferentially it is displayed. The contribution degree can be calculated based on, for example, SHAP (SHapley Additive exPlanation) value, Gini coefficient, LIME (Local Interpretable Model-Agnostic Explanations), PFI (Permutation Feature Importance), etc.

[0087] The determination device 1 may display the time-series change of the determination result on the result screen 51 shown in FIGS. 9 and 10. Based on the information stored in the detection DB 121, the determination device 1 reads out the determination result and the response profile related to the collection date within the most recent predetermined period from the detection information associated with the subject ID of the subject to be displayed. The determination device 1 generates a list or graph showing the determination results and response profiles corresponding to the read plurality of collection dates and displays them on the result screen 51.

[0088] Note that the detection result is not limited to the configuration presented to the subject through the terminal device 2. The determination device 1 may output the detection result to, for example, another computer, a predetermined printing device, or the like.

[0089] FIG. 11 is a flowchart showing an example of the generation process procedure of the reference profile. The processes in the following flowchart are executed by the control unit 11 according to the program 1P stored in the storage unit 12 of the determination device 1.

[0090] The control unit 11 of the determination device 1 acquires, through the detection device 3, the response profiles detected from the healthy urine of a plurality of cancer-free patients and the response profiles detected from the lung cancer urine of a plurality of lung cancer patients (step S11). The response profile is, for example, time-series data of luminescence intensity and is generated for each cell 42 in the olfactory sensor 4. Information indicating the corresponding cell 42 may be associated with each response profile.

[0091] The control unit 11 generates a first reference profile based on each response profile for a plurality of healthy urines (step S12). The control unit 11 generates the first reference profile, for example, by calculating the geometric mean of the luminescence intensities detected from each healthy urine for each time.

[0092] The control unit 11 generates a second reference profile based on each response profile for a plurality of lung cancer urines (step S13). The control unit 11 generates the second reference profile, for example, by calculating the geometric mean of the luminescence intensities detected from each lung cancer urine for each time.

[0093] The control unit 11 selects one or more cells 42 to be used for lung cancer determination from among the plurality of types of cells 42 included in the olfactory sensor 4 (step S14). For example, for each cell 42 included in the olfactory sensor 4, the control unit 11 calculates the maximum value of the emission intensity or the integrated intensity difference value in each of the first reference profile and the second reference profile. The control unit 11 selects, as the cells 42 for lung cancer determination, the cells 42 for which the difference in the calculated maximum value of the emission intensity or the integrated intensity difference value is equal to or greater than a preset first threshold value. In step S14, the control unit 11 may specify the type and number of cells 42 selected for cancer determination so as to optimize each determination accuracy based on the determination accuracy of the possibility of cancer when each cell 42 is used, and select the cells 42 for lung cancer determination according to the specified result.

[0094] The control unit 11 associates the cancer information, the cell information of the selected cells 42 for lung cancer determination, the first reference profile and the second reference profile corresponding to the cells 42, and stores them in the detection DB 121 (step S15), and ends a series of processes.

[0095] The control unit 11 executes the above-described processes for all cancers that can be the determination target in the determination service, and generates and stores the first reference profile and the second reference profile for various cancer determinations. The above-described processes may be executed in a stage prior to the operation stage of providing the determination service.

[0096] FIG. 12 is a flowchart showing an example of a determination process procedure for the possibility of cancer. The following processes are executed by the control unit 11 according to a program 1P stored in the storage unit 12 of the determination device 1, and are also executed by the control unit 21 according to a program 2P stored in the storage unit 22 of the terminal device 2.

[0097] Based on an operation of a subject using the reception screen, the control unit 21 of the terminal device 2 receives the subject information and the target cancer (cancer type) of the subject who wishes to be determined (step S20). The control unit 21 transmits the received subject information and target cancer to the determination device 1 (step S21).

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

[0099] The control unit 11 acquires a response profile generated from a urine sample derived from the subject through the detection device 3 (step S23). The response profile is generated for each cell 42 in the olfactory sensor 4. The response profile is associated with a subject ID, a subject ID, a collection date, a detection device ID, a detection date, etc. The control unit 11 may acquire the raw detection data obtained by the detection from the detection device 3 and generate a response profile by performing various pre-processings on the acquired raw detection data. The control unit 11 associates the response profile of the subject ID, the subject ID, the collection date, the detection device ID, the detection date, and the cell type and stores it in the detection DB121 (step S24).

[0100] The control unit 11 calculates the similarity between the response profile of the urine sample derived from the subject and each of the first reference profile and the second reference profile for each cell 42 for cancer determination corresponding to the target cancer (step S25).

[0101] The control unit 11 compares the calculated similarities and individually determines the presence or absence of the possibility of cancer in the subject by specifying the health state corresponding to the reference profile with the highest similarity as the health state of the subject (step S26). In step S26, the presence or absence of the possibility of cancer is determined for each cell 42. The control unit 11 comprehensively determines the presence or absence of the possibility of cancer, for example, by a majority vote of individual determinations for each cell 42 (step S27). The control unit 11 stores the obtained determination result in association with the subject ID in the detection DB121 (step S28).

[0102] The control unit 11 generates a result screen showing the obtained determination result of the possibility of cancer (step S29). The control unit 11 transmits the generated result screen to the terminal device 2 corresponding to the subject identified by the subject information acquired in step S23 (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 ends the series of processes.

[0104] In the above-described process, the subject may be configured to be able to confirm the determination result at an arbitrary timing by requesting the display of the result screen using the terminal device 2 and receiving the result screen in response to the request. The determination result may be provided through the web service provided by the determination device 1.

[0105] In the above-described process, the control unit 11 of the determination device 1 may update the reference profile based on the response profile newly stored in the detection DB 121 and the determination result by the process of step S28. The control unit 11 extracts, for example, one or a plurality of newly added response profiles from the detection DB 121 at an appropriate interval. The control unit 11 regenerates the first reference profile based on the plurality of response profiles obtained by newly adding the response profiles determined to have no possibility of cancer among the extracted response profiles. Alternatively, the control unit 11 regenerates the second reference profile based on the plurality of response profiles obtained by newly adding the response profiles determined to have a possibility of cancer among the extracted response profiles.

[0106] In the above, it was assumed that the possibility of cancer was determined based on the detection data for the urine sample using the olfactory sensor 4 having olfactory receptors, but the receptor used for detecting the response signal is not limited to the olfactory receptor. The subject to be analyzed is not limited to urine, and may be, for example, blood, sweat, saliva, tears, exhaled breath, skin gas, tissue fluid, synovial fluid, follicular fluid, cerebrospinal fluid, semen, milk, vaginal fluid, etc. Further, the subject for which the possibility of cancer is determined is not limited to humans, and may be an animal.

[0107] According to this embodiment, based on the detection data by the biosensor including a receptor, the possibility of cancer can be determined. The practicality of the biosensor can be improved, and a health management service using the biosensor can be provided. By using the response profile indicating the response of the olfactory receptor, the possibility of cancer can be accurately determined. By determining the possibility of cancer by comparing with a pre-generated reference profile, the determination process of the possibility of cancer becomes easy.

[0108] Since the subject can obtain the determination result by submitting the test sample and registering the necessary information, the burden required for the examination is reduced, and the utilization rate of the service is increased. Since the determination result can be confirmed using the terminal device 2, the determination result can be surely grasped at an arbitrary timing. By displaying the detection result in a visually recognizable manner in addition to the determination result, the result can be confirmed more surely and in detail. By displaying the reference profile serving as the determination criterion in addition to the detection result of the subject himself / herself, the explanatory power for the determination result is improved.

[0109] (Second Embodiment) In the second embodiment, correction for eliminating individual differences in the response profile is performed. In the following embodiments, mainly the differences from the first embodiment will be described, and the same reference numerals will be given to the configurations common to the first embodiment, and the detailed description thereof will be omitted.

[0110] The response signal detected from the test sample may have individual differences due to various factors. For example, due to the influence of contaminants contained in the urine sample, even for urine samples containing the same concentration of odor compounds, the value of the luminescence intensity detected from a urine sample containing more contaminants is larger or smaller than that from a urine sample containing fewer contaminants. That is, due to the influence of contaminants, individual differences occur in the correlation between the concentration of odor molecules and the luminescence intensity. The response signal may also have individual differences due to the influence of the balance of odor molecules. The occurrence of individual differences can occur not only in the luminescence intensity but also for various response signals.

[0111] When performing the determination based on the response profile, the occurrence of individual differences as described above leads to a decrease in the determination accuracy. In particular, as described in the first embodiment, when determining whether the urine sample is similar to the profile of healthy urine or lung cancer urine by comparing the target response profile with the reference profile, the possibility of misjudgment due to the influence of individual differences increases. In this embodiment, the determination accuracy is improved by performing correction processing for eliminating individual differences in the response profile.

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

[0113] The control unit 11 of the determination device 1 selects one or a plurality of cells 42 to be used for correcting individual differences from among the plurality of types of cells 42 included in the olfactory sensor 4 (step S41). As the cells for individual difference correction, cells 42 having a lower reactivity corresponding to the target cancer (for example, lung cancer) than the cells for cancer determination are preferable. As the cells for individual difference correction, more preferably, the reactivity does not significantly change depending on the presence or absence of lung cancer, and there is no significant difference in the response profile. The cells for individual difference correction may be cells that react to odor molecules having substantially the same concentration in both healthy urine and lung cancer urine, or may be cells that react to odor molecules artificially added to urine and not contained in the urine before addition.

[0114] The control unit 11 selects the cell 42 for individual difference correction based on, for example, the dissimilarity between the first reference profile based on non-cancer urine (healthy urine) and the second reference profile based on lung cancer urine. Specifically, for each cell 42 included in the olfactory sensor 4, the control unit 11 calculates the dissimilarity between the first reference profile and the second reference profile. The control unit 11 selects, as the cell 42 for individual difference correction, the cell 42 for which the calculated dissimilarity is less than a preset second threshold value. As the dissimilarity between the first reference profile and the second reference profile, for example, similar to the specific case of the cell 42 for cancer determination, it may be 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 the intensity difference integral value between the first reference profile and the second reference profile. Note that although the dissimilarity between the first reference profile and the second reference profile is used above, the similarity may also be used.

[0115] It is preferable that each of the first reference profile and the second reference profile is generated based on response profiles of a plurality of urine samples obtained from a plurality of people. The second threshold value may be the same as or smaller than the first threshold value used for the selection of the cell 42 for cancer determination. The cell 42 for individual difference correction may be selected from among the cells 42 other than the cell 42 for cancer determination among the cells 42 in the olfactory sensor 4. Note that when the type of the cell 42 for individual difference correction is known, the above selection process may be omitted.

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

[0117] Based on the acquired correction profile and the response profile of the urine sample of the subject, the control unit 11 calculates a correction coefficient (correction value) for correcting the response profile (step S43).

[0118] The correction coefficient can be calculated, for example, by the following method. The areas enclosed by the response profile of the urine sample of the subject and the correction profile respectively and the x-axis (time axis) are divided at a predetermined time interval. For each division, the ratio of the area of the first region enclosed by the response profile to the area of the second region enclosed by the correction profile is obtained. The geometric mean value of the ratios in all divisions is used as the correction coefficient. Note that the calculation method of the correction coefficient is not limited to the above example, and any method can be used as long as it can correct the individual differences of the response profile. The correction coefficient may be adjusted according to the type of the cells 42 for determination. For example, for the above-mentioned correction coefficient calculated based on the correction profile and the response profile, a predetermined coefficient preset for each of the cells 42 for determination may be multiplied to obtain the correction coefficient for each of the cells 42 for determination.

[0119] When a plurality of cells 42 are selected as the correction cells 42, the control unit 11 may calculate the above-mentioned correction coefficient for each correction cell 42 and determine the final correction coefficient by obtaining the statistical value (such as geometric mean, median, etc.) of the calculated correction coefficients.

[0120] The control unit 11 corrects the response profile of each cell 42 selected for cancer determination using the calculated correction coefficient (step S44). Specifically, a corrected response profile is generated by multiplying each emission intensity in the response profile for cancer determination by the correction coefficient. The control unit 11 uses the corrected response profile to execute the processing after step S25, and determines the possibility of cancer based on the corrected response profile.

[0121] According to the above processing, a correction coefficient can be obtained based on the response profiles and reference profiles of the correction cells 42 selected from among the cells 42 in the olfactory sensor 4, and the response profile of the cancer determination cells 42 can be corrected using the obtained correction coefficient. The correction cells 42 do not exhibit the properties of different response signals depending on the presence or absence of cancer, and the response profile hardly depends on the presence or absence of cancer. The cancer determination cells 42 exhibit the properties of different response signals depending on the presence or absence of cancer, and the response profile strongly depends on the presence or absence of cancer.

[0122] Figure 14 is a diagram showing an example of a response profile according to the presence or absence of correction processing. In the example shown in Figure 14A, in the response profile before correction, the overall luminescence intensity has decreased due to the influence of impurities that weaken the activity. The response profile after correction has been corrected so that the luminescence intensity increases. By the correction shown in Figure 14A, the possibility of misjudging a subject with a potential for cancer as having no potential for cancer can be suppressed.

[0123] In the example shown in Figure 14B, in the response profile before correction, the overall luminescence intensity has increased due to the influence of impurities that enhance the activity. The response profile after correction has been corrected so that the luminescence intensity decreases. By the correction shown in Figure 14B, the possibility of misjudging a subject with no potential for cancer as having a potential for cancer can be suppressed.

[0124] According to the present embodiment, individual differences in the subject can be corrected, and a decrease in determination accuracy due to individual differences can be suppressed. When measuring a biological sample using a biosensor using a receptor, it is considered that differences may occur in the response signal due to various factors. According to the present embodiment, such individual differences can be appropriately eliminated.

[0125] According to the present embodiment, based on the characteristics of the response profile, cells for individual correction can be efficiently determined. By preparing a biosensor equipped with a plurality of sensor cells and obtaining the response profile of each cell, appropriate cells for individual correction can be selected according to various properties for determination purposes.

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

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

[0128] FIG. 16 is an explanatory diagram showing an overview of the learning model 122. The learning model 122 takes, as input, the response profile of the luminescence intensity detected from a urine specimen of a subject, and outputs information indicating the presence or absence of the possibility of the target cancer in the subject corresponding to the response profile. The learning model 122 of the present embodiment is composed of a plurality of individual learning models 123. In the following description, the individual learning model 123 will also be referred to as the first learning model 123A, the second learning model 123B, and the third learning model 123C.

[0129] The first learning model 123A is a model for determining the possibility of lung cancer as the first type of cancer. It takes the response profiles related to a plurality of cells 42 as input and outputs whether there is a possibility of lung cancer. The second learning model 123B is a model for determining the possibility of prostate cancer as the second type of cancer. It takes the response profiles related to a plurality of cells 42 as input and outputs whether there is a possibility of prostate cancer. The third learning model 123C is a model for determining the possibility of colorectal cancer as the third type of cancer. It takes the response profiles related to a plurality of cells 42 as input and outputs whether there is a possibility of colorectal cancer. Thus, the individual learning model 123 is constructed to correspond to each cancer to be determined. Note that the number of individual learning models 123 included in the learning model 122 may be 4 or more. Since all the individual learning models 123 have a similar configuration, the configuration of the first learning model 123A will be described below.

[0130] The first learning model 123A is, for example, a CNN (Convolutional Neural Network), which is a type of neural network. The first learning model 123A includes an input layer to which each response profile is input, an output layer that outputs whether there is a possibility of lung cancer, and an intermediate layer (hidden layer). The intermediate layer may include a convolutional layer, a pooling layer, a fully connected layer, and the like. The intermediate layer has a plurality of nodes that extract feature amounts of the response profile and passes the feature amounts extracted using various parameters to the output layer. When a response profile is input to the input layer, calculations are performed in the intermediate layer by the learned parameters, and output information indicating the classification result of whether there is a possibility of lung cancer is output from the output layer.

[0131] The input data input to the first learning model 123A is the response profile related to the cells 42 selected for lung cancer determination among all the cells 42 in the olfactory sensor 4. The input data of the first learning model 123A may include the types of cells 42 corresponding to the response profile.

[0132] The first learning model 123A can be generated by preparing training data in which labels indicating the presence or absence of the possibility of lung cancer are associated with response profiles, and performing machine learning on an unlearned neural network using the training data. As the correct label, for example, the diagnosis result by an experienced doctor is used. The training data includes response profiles detected from the specimens of a plurality of subjects with the possibility of lung cancer, and response profiles detected from the specimens of a plurality of subjects without the possibility of lung cancer. The learning model 122 learns the relationship between those response profiles and the possibility of lung cancer.

[0133] The determination device 1 inputs a plurality of response profiles included in the training data into the input layer of the neural network model before learning, obtains the presence or absence of the possibility of lung cancer output from the output layer through arithmetic processing in the intermediate layer. The determination device 1 compares the presence or absence of the possibility of lung cancer output from the output layer with the presence or absence of the possibility of lung cancer included in the training data, and optimizes parameters such as the weights between neurons using, for example, the error backpropagation method so that the presence or absence of the possibility of lung cancer output from the output layer approaches the correct value. Note that the learning model 122 may be constructed by an external device and deployed to the determination device 1.

[0134] The determination device 1 gives the response profile of the cancer determination cell 42 corresponding to the target cancer to each of the individual learning models 123 corresponding to one or more cancers selected as the determination target, and obtains the possibility of the target cancer output from each individual learning model 123.

[0135] The input data to the individual learning model 123 is not limited to an image representing the response profile of the emission intensity, and may be the value of the emission intensity over time. Of course, the input to the individual learning model 123 may be a response signal other than the emission intensity.

[0136] The input data input to the individual learning model 123 may further include subject information regarding the subject, as shown in FIG. 16. The subject information that is an input element to the individual learning model 123 includes, for example, attributes such as the age and gender of the subject corresponding to the specimen, current symptoms, medical history, examination results, health examination results, and other health information.

[0137] The individual learning model 123 is not limited to estimating the presence or absence of cancer. For example, it may output a probability level that is classified into multiple levels according to the degree of probability, or may output a numerical value indicating the probability as a percentage.

[0138] The individual learning model 123 may be configured to output the probability of cancer, taking as input a response profile for specimens collected from the subject on multiple collection dates, that is, a time-series response profile. In this case, the individual learning model 123 may take as input the latest response profile and the response profiles for the past several times, and output the current probability of cancer in the subject, or may output the future probability of cancer.

[0139] The configuration of the learning model 122 is not limited to the above example, and it is sufficient that the probability of the target cancer can be identified from the time-series data of the response signal. The learning model 122 may be a model constructed by other learning algorithms such as RNN (Recurrent Neural Network), GNN (Graph Neural Network), Transformer, SVM (Support Vector Machine), logistic regression, XGBoost (eXtreme Gradient Boosting), etc.

[0140] As the individual learning models 123, one model may be constructed for each type of cell 42. In this case, the determination device 1 may derive a comprehensive determination result for one cancer based on the individual determination results output from the respective individual learning models 123 corresponding to the cell types. The determination device 1 may perform a comprehensive determination of the cancer possibility using a determination model in the same manner as in the first embodiment. In this case, the determination model may be configured to output the cancer possibility by taking as input the cancer possibility for each type of cell 42 output from the learning model 122. Note that the learning model 122 may be configured to output the cancer possibilities for various cancers by one learning model 122.

[0141] FIG. 17 is a flowchart showing an example of the determination processing procedure for the cancer possibility executed by the determination system 100 of the third embodiment.

[0142] The control unit 21 of the terminal device 2 executes the same processing as in steps S20 to S21, receives (step S50) and transmits (step S51) the subject information and the target cancer.

[0143] The control unit 11 of the determination device 1 executes the same processing as in steps S22 to S24, receives (step S52) the subject information and the target cancer, acquires (step S53) the response profile, and stores (step S54) the acquired information in the detection DB 121.

[0144] The control unit 11 selects (step S55) an individual learning model 123 corresponding to the received target cancer and the cancer-determining cell 42 corresponding to the target cancer from among the plurality of individual learning models 123 included in the learning model 122 stored in the storage unit 12.

[0145] The control unit 11 inputs the response profile of the corresponding cancer-diagnosis cell 42 into each selected individual learning model 123 (step S56). Based on the information stored in the detection DB 121, the control unit 11 may read out the subject information of the subject identified by the subject ID corresponding to the response profile, and input the attributes and health information of the subject corresponding to the read response profile into the individual learning model 123. The control unit 11 obtains the cancer probability output from the individual learning model 123 (step S57). The individual learning model 123 outputs the presence or absence of cancer probability, for example, for each type of cancer. Subsequently, the control unit 11 executes the same processing as in steps S28 to S32.

[0146] The determination device 1 may perform retraining of the above-described learning model 122. FIG. 18 is a flowchart showing an example of the retraining process of the learning model 122.

[0147] The control unit 11 of the determination device 1 obtains the doctor's diagnosis result regarding cancer in the subject (step S61). The diagnosis result may be obtained, for example, by receiving an input from the subject through the terminal device 2 of the subject, or by communicating with the computer of the medical institution.

[0148] The control unit 11 performs retraining of the learning model 122 using the cancer probability indicated by the obtained doctor's diagnosis result, and updates the learning model 122 (step S62). Specifically, the control unit 11 performs retraining using the response profile input to the individual learning model 123 corresponding to the cancer type for which the diagnosis result was obtained and the cancer probability indicated by the diagnosis result as training data, and updates the individual learning model 123. The control unit 11 optimizes the parameters so that the cancer probability output from the individual learning model 123 approximates the diagnosis result, and regenerates the individual learning model 123.

[0149] According to this embodiment, the learning model 122 can be used to easily and accurately determine the possibility of cancer. By constructing an individual learning model 123 according to the cancer type, the determination accuracy of the possibility of cancer can be improved. By using the attributes and health information of the subject as input elements to the learning model 122, the possibility of cancer can be determined considering more diverse information, and an improvement in accuracy is expected.

[0150] By executing the relearning of the learning model 122 based on the diagnosis result of the doctor, the learning model 122 can be optimized through the operation of this system.

[0151] (Fourth Embodiment) In the fourth embodiment, the possibility of cancer is determined using a plurality of determination methods. The determination device 1 of the fourth embodiment acquires the determination result of the possibility of cancer determined by other determination methods in addition to the determination of the possibility of cancer based on the sensor data by the olfactory sensor 4.

[0152] The other determination methods are not particularly limited as long as they can determine the possibility of cancer. For example, methods using image data obtained by an imaging device, detection data obtained from a physical sensor, detection data obtained by a chemical sensor, detection data obtained by a biosensor using a biodevice other than cells having olfactory receptors, etc. can be mentioned.

[0153] Examples of methods using image data include determination based on image data obtained by, for example, an X-ray inspection apparatus, a CT inspection apparatus, an MRI inspection apparatus, a PET inspection apparatus, an ultrasonic inspection apparatus, etc. Examples of methods using detection data of physical quantities include determination based on detection data of physical quantities such as body temperature, pulse, heartbeat, intravascular pressure, intraocular pressure, etc. Examples of methods using detection data of biosensors equipped with biological elements such as enzymes, antibodies, nucleic acids, microorganisms, sugar chains, lipid membranes, etc. include determination based on detection data of chemical substance amounts such as urea, glucose, monoamine, sucrose, phospholipid, total cholesterol, neutral fat, amino acid, IgI, IgA, IgM, albumin, etc. Other determination methods may be determination based on inspection data by gene inspection, chromosome inspection, cell surface marker inspection, biomarker (for example, amino acid, microRNA, nucleic acid, protein, etc.) inspection, etc. The determination process by each method may be executed by the determination device 1 or may be performed externally. The determination of the possibility of cancer by other determination methods may be a secondary determination performed after receiving the result of the primary determination, with the determination by the olfactory sensor 4 as the primary determination.

[0154] FIG. 19 is a flowchart showing an example of the processing procedure executed by the determination system 100 of the fourth embodiment. After the determination system 100 performs a comprehensive determination of the possibility of cancer by the processing up to step S27 of the first embodiment, for example, the following processing is executed.

[0155] The control unit 11 of the determination device 1 acquires the determination result of the possibility of cancer determined by a determination method different from the determination method using the olfactory sensor 4 (step S71). The determination result by a different determination method may be acquired, for example, by communication with a computer of another inspection institution. The determination result may be associated with the identification information of the subject.

[0156] The control unit 11 derives a final determination result based on the determination results obtained by different determination methods and the determination result obtained by the determination method using the olfactory sensor 4 that has been acquired in advance (step S72). For example, the control unit 11 may use a majority vote of the determination results by the determination methods as the final determination result. When making the final determination, weighting may be performed so as to increase the weight of the determination result based on a specific determination method. The control unit 11 then executes the same processing as in steps S28 to S32.

[0157] FIG. 20 is a schematic diagram showing an example of a result screen 51 indicating the determination result of the fourth embodiment. In the example shown in FIG. 20, the result screen 51 includes a first display unit 511 that displays information about the subject to be determined, and a plurality of second display units 512 corresponding to each of the plurality of target cancers selected by the subject.

[0158] Each second display unit 512 displays the cancer type of the target cancer and the determination result related to the target cancer. The determination device 1 causes the second display unit 512 to display the determination result of the possibility of cancer by each determination method for each type of determination method based on the determination results by each determination method. The determination device 1 also causes the second display unit 512 to display the final determination result based on each determination result.

[0159] According to the present embodiment, by combining a plurality of determination methods, the determination accuracy of the possibility of cancer can be further improved. By providing the determination result for each determination method to the subject, it becomes possible to grasp the determination result in detail.

[0160] Regarding the above embodiments, the following additional remarks are further disclosed. (Additional Remark 1) A response signal for a target sample derived from a determination target, which is detected using a receptor showing reactivity according to the possibility of cancer in the target, is acquired, Based on the acquired response signal for the target sample, the possibility of cancer in the determination target is determined A determination method executed by a computer. (Additional Remark 2) The receptor exhibits reactivity according to the possibility of a specific cancer, obtain response signals for the plurality of target samples detected using a plurality of the receptors corresponding to each of the plurality of types of cancer, determine the possibility of cancer and the type of cancer in the object to be determined based on the response signals of the plurality of receptors obtained; The determination method according to Appendix 1. (Appendix 3) detect the response signal using a biosensor comprising a plurality of the receptors; The determination method according to Appendix 1 or Appendix 2. (Appendix 4) The receptor is a receptor that exhibits reactivity according to the possibility of a first cancer among a plurality of cancers and does not exhibit reactivity according to the possibility of a second cancer. The determination method according to any one of Appendices 1 to 3. (Appendix 5) further obtain a response signal for the target sample detected using a receptor that does not exhibit reactivity according to the possibility of cancer in the object; The determination method according to any one of Appendices 1 to 4. (Appendix 6) determine the possibility of cancer in the object to be determined based on a comparison between the response signals for samples derived from cancer patients and samples derived from non-cancer patients related to the receptor and the response signal for the target sample; The determination method according to any one of Appendices 1 to 5. (Appendix 7) determine the possibility of cancer and the type of cancer in the object to be determined based on a comparison between the response signals for samples derived from cancer patients and samples derived from non-cancer patients related to each of the receptors for each type of cancer and the response signal for the target sample; The determination method according to Appendix 6. (Appendix 8) pre-store the response signals for samples derived from cancer patients and samples derived from non-cancer patients; The determination method according to Appendix 6 or Appendix 7. (Appendix 9) Output information that can distinguish the response signals for samples from the cancer patient and samples from non-cancer patients from the response signal for the target sample The determination method according to any one of Appendices 6 to 8. (Appendix 10) Input the response signal for the target sample from the determination target, which is detected using a receptor that exhibits reactivity according to the possibility of cancer in the subject, into the learning model that outputs the possibility of cancer in the determination target, and determine the possibility of cancer in the determination target by inputting the response signal for the target sample The determination method according to any one of Appendices 1 to 9. (Appendix 11) Obtain target information including the attributes or health status of the determination target, Input the target information and the response signal for the target sample obtained for the determination target into the learning model that outputs the possibility of cancer in the determination target when the target information related to the determination target and the response signal for the target sample are input, and determine the possibility of cancer in the determination target The determination method according to Appendix 10. (Appendix 12) Obtain response signals for samples from cancer patients and samples from non-cancer patients related to each of the plurality of receptors, Based on each of the obtained response signals, specify the type or number of receptors among the plurality of receptors to be used for determining the possibility of cancer The determination method according to any one of Appendices 1 to 11. (Appendix 13) Obtain the determination accuracy of the possibility of cancer based on the response signals for samples from cancer patients and samples from non-cancer patients related to each of the plurality of receptors, Based on the obtained determination accuracy, specify the type or number of receptors among the plurality of receptors to be used for determining the possibility of cancer The determination method according to any one of Appendices 1 to 12. (Appendix 14) Obtain response signals for the target sample from the determination target on a plurality of collection dates, Output by associating the response signal for the target sample corresponding to each collection date obtained with the determination result of the possibility of the cancer based on the response signal The determination method according to any one of Appendices 1 to 13.

[0161] The embodiments disclosed this time should be considered as illustrative in all respects and not restrictive. The technical features described in each embodiment can be combined with each other, and the scope of the present invention is intended to include all modifications within the scope of the claims and the scope equivalent to the claims. The sequences shown in each embodiment are not limited, and within a non - contradictory range, each processing procedure may be executed with its order changed, or a plurality of processes may be executed in parallel. The processing entity of each process is not limited, and within a non - contradictory range, the processing of each device may be executed by another device.

[0162] The matters described in each embodiment can be combined with each other. Also, the independent claims and dependent claims described in the claims can be combined with each other in all possible combinations regardless of the citation form. Furthermore, the claims use a form (multi - claim form) of describing claims that cite two or more other claims, but are not limited to this. A form of describing a multi - claim (multi - multi - claim) that cites at least one multi - claim may be used.

Explanation of Signs

[0163] 100 Determination system 1 Determination device 11 Control unit 12 Storage unit 13 Communication unit 1A Recording medium 1P Program 121 Detection DB 122 Learning model 2 Terminal device 21 Control unit 22 Storage unit 23 Communication unit 24 Display unit 25 Operation unit 2A Recording medium 2P Program 3 Detection device 4 Olfactory sensor 42 Cell

Claims

1. Obtain at least one or more types of cancer selected by the user, Using a biosensor comprising a plurality of types of first receptors that exhibit reactivity according to the possibility of cancer in a subject corresponding to the plurality of types of cancer obtained, and a second receptor that does not exhibit reactivity according to the possibility of cancer in the subject, obtain the response signals of each receptor to a subject sample derived from the determination target, Based on the response signal of the second receptor to the obtained subject sample, perform a predetermined correction process on the response signal of each first receptor, Based on the response signals of each first receptor after the correction process, determine the possibility of one or more types of cancer in the determination target, Output information representing the determined cancer possibility A determination method in which a computer executes the process.

2. The first receptor exhibits reactivity according to the possibility of a specific cancer, Obtain response signals for a plurality of the subject samples detected using a plurality of the first receptors corresponding to each of the plurality of types of cancer, Based on the response signals of the plurality of the first receptors obtained, determine the possibility of cancer and the cancer type in the determination target The determination method according to Claim 1.

3. The first receptor includes a receptor that exhibits reactivity according to the possibility of a first cancer among a plurality of cancers and does not exhibit reactivity according to the possibility of a second cancer The determination method according to Claim 1 or Claim 2.

4. Based on a comparison between the response signal of the first receptor to samples from cancer patients and non-cancer patients and the response signal to the subject sample, determine the possibility of cancer in the determination target The determination method according to Claim 1 or Claim 2.

5. Based on a comparison between the response signals of each first receptor for each type of cancer to samples from cancer patients and non-cancer patients and the response signal to the subject sample, determine the possibility of cancer and the cancer type in the determination target The determination method according to Claim 4.

6. Pre-store in advance the response signals of samples from cancer patients and non-cancer patients The determination method according to Claim 4.

7. Output information that discriminatively represents the response signals of samples from cancer patients and non-cancer patients and the response signal to the subject sample The determination method according to Claim 4.

8. When a response signal for a target sample derived from a determination target, which is detected using a first receptor that exhibits reactivity according to the possibility of cancer in the target, is input, the possibility of cancer in the determination target is output by inputting the response signal of the first receptor for the target sample to the learning model obtained. Determine the possibility of cancer in the determination target by inputting the response signal of the first receptor for the target sample obtained by the learning model that outputs the possibility of cancer in the determination target when inputting the target information including the attribute or health state of the determination target and the response signal for the target sample related to the determination target. The determination method according to claim 1 or claim 2.

9. Obtain target information including the attribute or health state of the determination target, When the target information related to the determination target and the response signal for the target sample are input, the possibility of cancer in the determination target is output by inputting the obtained target information and the response signal of the first receptor for the target sample to the learning model that outputs the possibility of cancer in the determination target. Determine the possibility of cancer in the determination target by inputting the response signal of the first receptor for the target sample obtained by the learning model that outputs the possibility of cancer in the determination target when inputting the target information including the attribute or health state of the determination target and the response signal for the target sample related to the determination target. The determination method according to claim 8.

10. Obtain response signals for samples derived from cancer patients and non-cancer patients respectively related to a plurality of receptors, Based on each obtained response signal, identify the type or number of receptors to be used for determining the possibility of cancer among the plurality of receptors. The determination method according to claim 1 or claim 2.

11. Obtain the determination accuracy of the possibility of cancer based on the response signals for samples derived from cancer patients and non-cancer patients respectively related to the plurality of receptors, Based on the obtained determination accuracy, identify the type or number of receptors to be used for determining the possibility of cancer among the plurality of receptors. The determination method according to claim 1 or claim 2.

12. Obtain response signals for the target sample derived from the determination target at a plurality of collection dates, Output by associating the response signal for the target sample related to each obtained collection date with the determination result of the possibility of cancer based on the response signal. The determination method according to claim 1 or claim 2.

13. Obtain at least one or a plurality of types of cancer selected by the user, Using a biosensor comprising a plurality of types of first receptors that exhibit reactivity according to the possibility of cancer in a target corresponding to the plurality of types of cancer obtained, and a second receptor that does not exhibit reactivity according to the possibility of cancer in the target, obtain the response signal of each receptor for a target sample derived from the determination target, Based on the response signal of the second receptor for the obtained target sample, perform a predetermined correction process on the response signal of each first receptor. Based on the response signals of each first receptor after the correction process, determine the possibility of one or more cancers in the object to be determined, Output information representing the determined cancer possibility Comprising a control unit that executes the process Determination device.

14. Obtain at least one or more types of cancers selected by the user, Obtain the response signals of each receptor for the target sample derived from the object to be determined, detected using a biosensor comprising a plurality of types of first receptors that exhibit reactivity according to the possibility of cancer in the target and a second receptor that does not exhibit reactivity according to the possibility of cancer in the target, Based on the response signal of the second receptor for the obtained target sample, perform a predetermined correction process on the response signal of each first receptor, Based on the response signals of each first receptor after the correction process, determine the possibility of one or more cancers in the object to be determined, Output information representing the determined cancer possibility A computer program that causes a computer to execute the process.

15. Obtain the response signals of each receptor for the target sample derived from the object to be determined, detected using a biosensor comprising a plurality of types of first receptors that exhibit reactivity according to the possibility of cancer in the target and a second receptor that does not exhibit reactivity according to the possibility of cancer in the target, Based on the response signal of the second receptor for the obtained target sample, perform a predetermined correction process on the response signal of each first receptor, Based on the response signals of each first receptor after the correction process, determine the possibility and type of cancer in the object to be determined, Output information representing the determined cancer possibility and type of cancer A determination method executed by a computer.

16. Obtain the response signals for the target sample derived from the object to be determined on a plurality of collection dates detected using a plurality of types of receptors that exhibit reactivity according to the possibility of cancer in the target, Determine the possibility of cancer in the object to be determined by inputting the response signals for the target sample on the plurality of collection dates obtained using a plurality of types of receptors that exhibit reactivity according to the possibility of cancer in the target into a learning model that has been machine-learned to output the possibility of cancer in the object to be determined when the response signals of each receptor for the target sample derived from the object to be determined on the plurality of collection dates are input, The learning model is trained using training data including response signals of each receptor for a target sample detected using a plurality of types of receptors that exhibit reactivity according to the likelihood of cancer in the target, and the correct label of the diagnosis result. A determination method for a computer to execute processing.

Images