Information processing method, information processing device, information processing program, method for generating a trained model, and trained model

Abstract

To provide an information processing method, an information processing apparatus, and an information processing program that are capable of highly accurately determining the presence or absence of respiratory disease symptoms, a trained model used in them, a method for generating the trained model, and a measurement device.SOLUTION: A processor 11 performs processing for: acquiring data based on measurement data measured from a subject and indicating the subject's respiratory condition; acquiring medication history information regarding a subject's medication history and exercise history information regarding the subject's exercise history in a past period before measurement timing of the measurement data; and inputting the data, the medication history information, and the exercise history information to a trained model and obtaining a determination result on the presence or absence of respiratory disease symptoms in the subject from the trained model.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The technology of the present disclosure relates to an information processing method, an information processing apparatus, an information processing program, a method for generating a learned model, a learned model, and a measuring instrument.

Background Art

[0002] Patent Document 1 describes a treatment support apparatus including a processor that acquires measurement sound data of a lung sound measurement device that measures lung sounds worn on the body of a subject, acquires behavior data of the subject during the measurement period of the measurement sound data, and causes an image based on the measurement sound data and the behavior data to be displayed on a display device of an external device.

[0003] Patent Document 2 describes a treatment support apparatus including a processor that acquires determination result data of a device that determines a respiratory tract state of a subject during a measurement period of the lung sound based on the lung sound measured from the subject, and state information indicating the state of the subject during a period different from the measurement period among days including the measurement period, and associates and records the determination result data and the state information.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] The presence or absence of symptoms of respiratory diseases such as asthma, pulmonary fibrosis, upper airway obstruction, or chronic obstructive pulmonary disease is determined with a high degree of accuracy by a doctor directly examining a patient using a stethoscope or the like. On the other hand, devices such as sensors capable of detecting wheezing and peak flow meters are also known, and by using such devices, it is possible to determine the presence or absence of symptoms without seeing a doctor. The determination of the presence or absence of symptoms by a device is performed using respiratory sounds or vital capacity measured from the patient. However, since the physical condition of the patient varies, it is desirable to determine the presence or absence of symptoms in consideration of that condition.

[0006] The technology of the present disclosure aims to provide an information processing method, an information processing apparatus, and an information processing program capable of accurately determining the presence or absence of symptoms of respiratory diseases, a learned model used therein and a method for generating the same, and a measuring device.

Means for Solving the Problems

[0007] The technology of the present disclosure is as follows. In the parentheses, corresponding components and the like in the following embodiments are shown, but the present disclosure is not limited thereto.

[0008] (1) A processor (processor 11) acquires data (measurement processed data) based on measurement data indicating the respiratory state of the subject measured from the subject (user), acquires action history information regarding the action history of the subject in a period past the measurement timing of the measurement data, and performs a process of inputting the data and the action history information into a learned model (learned model 13) to obtain a determination result of the presence or absence of symptoms of a respiratory disease of the subject from the learned model.

[0009] (2) The information processing method according to (1), wherein the action history information includes at least one of medication history information regarding a medication history and exercise history information regarding an exercise history.

[0010] (3) The information processing method according to (2), wherein the medication history information is an information processing method including the number of medication times during the above period.

[0011] (4) The information processing method according to (2) or (3), wherein the exercise history information is an information processing method including exercise amount information.

[0012] (5) The information processing method according to (2) or (3), wherein the exercise history information is an information processing method including information on the frequency of exercise performed under specific circumstances.

[0013] (6) Obtain data (measurement processed data) based on measurement data indicating the respiratory state of the subject measured from the subject (user), Obtain action history information regarding the action history of the subject in a period prior to the measurement timing of the measurement data, An information processing apparatus (information processing server 10) including a processor (processor 11) that performs a process of inputting the data and the action history information into a learned model (learned model 13) and obtaining a determination result on the presence or absence of symptoms of a respiratory disease of the subject from the learned model.

[0014] (7) Obtain data (measurement processed data) based on measurement data indicating the respiratory state of the subject measured from the subject (user), Obtain action history information regarding the action history of the subject in a period prior to the measurement timing of the measurement data, A process of inputting the data and the action history information into a learned model (learned model 13) and obtaining a determination result on the presence or absence of occurrence of symptoms of a respiratory disease of the subject from the learned model, An information processing program that causes a processor (processor 11) to execute.

[0015] (8) The processor (processor 11) acquires a plurality of pieces of data based on measurement data indicating the respiratory state of the first subject to be measured (monitoring user) measured from the first subject to be measured, action history information regarding the action history of the first subject to be measured in a period prior to the measurement timing of the measurement data, and a determination result by a doctor as to whether or not symptoms of a respiratory disease of the first subject to be measured occurred on the day including the measurement timing, as learning data, executes machine learning based on the plurality of pieces of learning data in a program, and when data (measurement processed data) based on measurement data indicating the respiratory state of the second subject to be measured (user) measured from the second subject to be measured and action history information regarding the action history of the second subject to be measured in a period prior to the measurement timing of the measurement data are input, obtains a learned model (learned model 13) that outputs a determination result as to whether or not symptoms of a respiratory disease of the second subject to be measured occur.

[0016] (9) A learned model (learned model 13) obtained by performing machine learning on data (measurement processed data) based on measurement data indicating the respiratory state of the first subject to be measured (monitoring user) measured from the first subject to be measured, action history information regarding the action history of the first subject to be measured in a period prior to the measurement timing of the measurement data, and a determination result by a doctor as to whether or not symptoms of a respiratory disease of the first subject to be measured occurred on the day including the measurement timing, as learning data, When data (measurement processed data) based on measurement data indicating the respiratory state of the second subject to be measured (user) measured from the second subject to be measured and action history information regarding the action history of the second subject to be measured in a period prior to the measurement timing of the measurement data are input, a learned model (learned model 13) that causes the processor (processor 11) to execute a process of outputting a determination result as to whether or not symptoms of a respiratory disease of the second subject to be measured occur.

[0017] (10) A measuring device (measuring device 40) that measures measurement data indicating the respiratory state of a subject from the subject, a communication unit capable of communicating with a terminal (user terminal 30) that can acquire behavior history information regarding the behavior history of the subject in a period past the measurement timing of the measurement data, an output device, and a processor, wherein the processor transmits the measurement data to the terminal, inputs data based on the measurement data and the behavior history information into a learned model, and receives, from the terminal, a determination result of the presence or absence of symptoms of a respiratory disease of the subject obtained from the learned model, and causes the received determination result to be output from the output device.

Advantages of the Invention

[0018] According to the technology of the present disclosure, it is possible to provide an information processing method, an information processing apparatus, and an information processing program capable of accurately determining the presence or absence of symptoms of a respiratory disease, a learned model used therefor and a method for generating the same, and a measuring device.

Brief Description of the Drawings

[0019]

Figure 1

Embodiments for Carrying Out the Invention

[0020] (Outline of the information processing method according to the technology of the present disclosure) An information processing method is such that a processor acquires data based on measurement data indicating the respiratory state of the person to be measured, which has been measured from the person to be measured, and acquires behavior history information regarding the behavior history of the person to be measured in a period prior to the measurement timing of the measurement data (for example, at least one of medication history information regarding a medication history and exercise history information regarding an exercise history), inputs the data and the behavior history information into a learned model, and performs a process of obtaining a determination result of the presence or absence of symptoms of a respiratory disease of the person to be measured from the learned model.

[0021] In this way, by inputting not only data based on measurement data measured from the person to be measured but also behavior history information based on the past behavior of the person to be measured into the learned model, a determination result of the presence or absence of symptoms of a respiratory disease of the person to be measured can be obtained from the output of the learned model. As a result, compared with a configuration that analyzes measurement data measured from the person to be measured with a specific algorithm to determine the presence or absence of symptoms, such as a wheezing sensor, it becomes possible to determine the presence or absence of symptoms considering the past behavior of the person to be measured, and the determination accuracy can be improved.

[0022] For example, assume a case where the person to be measured is taking a therapeutic drug prescribed by a doctor. If the person to be measured uses a device to determine the presence or absence of symptoms, it is assumed that a result of no symptoms will be output from the device when the airway condition is moderately improved by the medication. On the other hand, when this person to be measured is examined by a doctor in the same state, the doctor will observe the breathing sound, etc. while asking about the medication situation, etc. to determine the effect of the medication, so it is assumed that a stricter determination will be made than the device to avoid missing even a slight sign of symptoms. Thus, a difference in criteria may occur between the determination by the device and the determination by the doctor depending on the medication history of the person to be measured. Furthermore, the airway condition of the person to be measured can change not only depending on the medication history but also depending on the exercise history. For example, a person who exercises frequently tends to have reduced stress, so it is assumed that the improvement of the airway condition progresses. However, also in this case, depending on the content of the exercise history of the person to be measured, the determination result of the doctor may differ from the determination result of the device.

[0023] In the technology of the present disclosure, the presence or absence of symptoms is determined by a learned model obtained by performing machine learning using, as learning data, behavior history information acquired from each of a large number of people (monitoring users described later), data based on measurement data indicating a respiratory state, and a determination result of the presence or absence of symptoms by a doctor's diagnosis. For this reason, it is possible to determine the presence or absence of symptoms considering not only data based on measurement data conventionally used by devices but also behavior history (such as medication history and exercise history). As a result, a result close to the determination by a doctor can be obtained from the learned model, and it is possible to determine the presence or absence of symptoms of a respiratory disease with high accuracy.

[0024] Hereinafter, a configuration example of a respiratory disease symptom determination system including an apparatus that executes an information processing method according to the technology of the present disclosure will be described.

[0025] (System Configuration) FIG. 1 is a schematic diagram showing a schematic configuration of a symptom determination system 100. The users targeted by the symptom determination system 100 are users who have been diagnosed with a respiratory disease by a doctor and have received a prescription for a therapeutic drug, but can also be used by users who have not received a prescription for a therapeutic drug. The symptom determination system 100 includes an information processing server 10, a user terminal 30 such as a smartphone possessed by a user (the person to be measured), and a measuring device 40 possessed by the user. The user terminal 30 and the information processing server 10 are connected to a network 20 such as the Internet and are configured to be able to communicate.

[0026] The measuring device 40 is a device for measuring, from the user, measurement data indicating the respiratory state of the user. The measurement data indicating the respiratory state of the user is respiratory sound data (for example, data of time vs. amplitude value), or vital capacity data (for example, data of exhaled volume vs. flow rate (flow volume curve)), etc.

[0027] The measuring device 40 can include, for example, a sensor unit including a microphone, and in a state where the sensor unit is applied to the user's chest, the microphone measures and records the user's breath sound data. The measuring device 40 can also be a peak flow meter that measures and records the user's vital capacity data (flow volume curve). The measuring device 40 and the user terminal 30 can be connected by wired communication or wireless communication, and the measurement data measured by the measuring device 40 is transmitted to the user terminal 30. Specifically, the measuring device 40 includes a sensor unit (in the case of a peak flow meter, a flow detection unit), a communication unit capable of communicating with the user terminal 30 wirelessly or by wire, an output device such as a display or a speaker, and a device processor that comprehensively controls these components.

[0028] A management application capable of managing the user's action history is installed on the user terminal 30. The management application records in the memory the medication history data indicating the medication history, which is one of the user's action histories, and the exercise history data indicating the exercise history, which is one of the action histories. The management application uses the position detection function, activity amount detection function, various information input function, and various information acquisition function from an external server via the network 20 installed on the user terminal 30 to record the user's medication history data and exercise history data.

[0029] When the user takes the therapeutic drug prescribed by the doctor, the user operates the management application and inputs the date and time of taking the drug. As a result, the management application records this input information as medication history data in the memory.

[0030] When the user holds the user terminal 30 or wears a smartwatch or the like that can be connected to the user terminal 30 and exercises, the management application acquires the user's exercise history data and records it in the memory. The user's exercise history data includes, for example, the intensity of the exercise (unit: METs) when the exercise is performed, the period during which the exercise is performed, the location where the exercise is performed (either indoors or outdoors), and the environment of the location where the exercise is performed (such as temperature or amount of allergens). The location and environment indicate the situation in which the exercise is being performed. The user's exercise history data may include the amount of activity such as the number of steps or calories burned per unit period (for example, one day). The amount of allergens is defined by, for example, the amount of pollen scattering or PM2.5, etc.

[0031] The intensity of exercise, the number of steps, and the calories burned, etc. can be acquired by the activity detection function of the user terminal 30 or the smartwatch. The location where the exercise is performed can be acquired by the location detection function of the user terminal 30 or the smartwatch. The environment of the location where the exercise is performed can be acquired by the function of acquiring various information of the user terminal 30.

[0032] The information processing server 10 includes a processor 11 and a storage unit 12. The storage unit 12 is configured to include a non-temporary storage medium such as a hard disk or a flash memory in addition to a work memory such as a RAM (Random Access Memory). The storage unit 12 stores an information processing program for the processor 11 of the information processing server 10 to execute an information processing method.

[0033] The processor 11 is a general-purpose processor such as a CPU (Central Processing Unit) that executes software (programs) to perform various functions, a programmable logic device (PLD) that is a processor whose circuit configuration can be changed after manufacturing, such as an FPGA (Field Programmable Gate Array), or a dedicated electric circuit such as an ASIC (Application Specific Integrated Circuit) that is a processor having a circuit configuration designed specifically to execute specific processing. The processor 11 may be composed of one processor, or may be composed of a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs, or a combination of a CPU and an FPGA). More specifically, the hardware structure of the processor 11 is an electric circuit (circuitry) that combines circuit elements such as semiconductor elements. When the processor 11 is composed of a plurality of processors, the installation locations of these plurality of processors do not have to be within the same device, and may be provided in each of a plurality of devices distributed via the network 20.

[0034] The learned model 13 is stored in the storage unit 12. The learned model 13 is generated by executing machine learning on a learning model configured by a program using teacher data (learning data). The learned model 13 may be generated by the processor 11 of the information processing server 10, or may be generated by a processor of a computer different from the information processing server 10. Hereinafter, assuming that the processor 11 generates the learned model 13, the generation method of the learned model 13 will be described.

[0035] (Method for generating a learned model) Processor 11 acquires a sample data group from storage unit 12. Each sample data included in this sample data group contains medication history data and exercise history data (hereinafter referred to as first data) recorded by a monitor user different from the user who uses symptom determination system 100 over a predetermined period (for example, one week, two weeks, or one month, etc.) using the same terminal as user terminal 30. Also, each sample data contains measurement data (hereinafter referred to as second data) obtained by the monitor user measuring measurement data indicating the respiratory state using the same device as measuring device 40 after the end of the above-mentioned predetermined period (for example, the day after the end of the predetermined period). Further, each sample data contains the determination result (hereinafter referred to as third data) of the presence or absence of symptoms of respiratory diseases by the doctor when the monitor user receives a medical examination by the doctor on the day including the timing when the above-mentioned measurement data was measured. Thus, sample data including the first data, the second data, and the third data is generated for each of a large number of monitor users and recorded in storage unit 12 as a sample data group.

[0036] Based on the first data in each sample data of the sample data group acquired by processor 11 from storage unit 12, processor 11 generates medication history information regarding the medication history of the monitor user during the predetermined period. The medication history information is information obtained by processing the medication history data, and is, for example, the number of times of taking medicine (i.e., the frequency of taking medicine) during the predetermined period, or the number of times of taking medicine for each divided period when the predetermined period is divided into a plurality of periods (information indicating the distribution of the timing when taking medicine was performed during the predetermined period), etc.

[0037] Also, based on the first data in each sample data of the sample data group acquired by processor 11 from storage unit 12, processor 11 generates exercise history information regarding the exercise history of the monitor user during the predetermined period. The exercise history information is information obtained by processing the exercise history data, and includes, for example, first information on the amount of exercise during the predetermined period, or second information on the frequency of exercise performed under specific circumstances during the predetermined period, etc. The exercise history information may be composed of a combination of the first information and the second information.

[0038] For the first piece of information, for example, the amount of physical activity (MET·hour) at a predetermined intensity (e.g., 3 METs) or higher is used. For example, if exercise at an intensity of 3 METs is performed for 1 hour and exercise at an intensity of 5 METs is performed for 1 hour during a predetermined period, then (3 METs × 1 hour) + (5 METs × 1 hour) = 8 [MET·hour] is generated as the first piece of information on the amount of exercise. As the first piece of information on the amount of exercise, the number of times or the time during which physical activity at a predetermined intensity or higher has been performed during a predetermined period may be generated. Also, as the first piece of information on the amount of exercise, the cumulative number of steps or the cumulative calories burned during a predetermined period may be generated.

[0039] As the second piece of information, for example, indoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed indoors during a predetermined period and outdoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed outdoors during a predetermined period are generated.

[0040] The outdoor exercise information may be further subdivided. For example, the outdoor exercise information may be divided into first outdoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed in a state where the amount of allergens is at a predetermined level or higher and second outdoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed in a state where the amount of allergens is less than the predetermined level.

[0041] In addition to or instead of the first outdoor exercise information and the second outdoor exercise information, third outdoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed in a state where the temperature is at a predetermined level or higher and fourth outdoor exercise information indicating the number of times or the time during which exercise at a predetermined intensity or higher has been performed in a state where the temperature is less than the predetermined level may be generated. Indoors, outdoors, outdoors with an allergen amount at a predetermined level or higher, outdoors with an allergen amount less than the predetermined level, outdoors with a temperature at a predetermined level or higher, and outdoors with a temperature less than the predetermined level each constitute a specific situation.

[0042] Furthermore, based on the second data (measurement data) in each sample data of the sample data group acquired from the storage unit 12, the processor 11 generates measurement processed data obtained by processing this second data into a form suitable for learning.

[0043] As measurement and processing data, feature values extracted from measurement data (respiratory sound data or vital capacity data) are used. Feature values that can exhibit a significant difference between a person without a respiratory disease and a person with a respiratory disease can be appropriately adopted.

[0044] When the measurement data is respiratory sound data, for example, the processor 11 generates data of frequency vs. amplitude values from the respiratory sound data (data of time vs. amplitude values), and in this data, a plurality of predetermined frequencies (frequencies at which the difference in amplitude is particularly large between a person with a respiratory disease and a person without a respiratory disease) are selected, and the amplitude values corresponding to each of these frequencies are obtained as measurement and processing data.

[0045] Alternatively, the processor 11 may process the respiratory sound data to generate data of frequency vs. sound pressure, and obtain, as measurement and processing data, the ratio between the peak value of the sound pressure in this data and the width between the frequencies corresponding to the minimum values of the sound pressure on both sides of the peak value.

[0046] Or, the processor 11 may process the respiratory sound data to generate three-dimensional data of frequency, sound pressure, and time, and in this three-dimensional data, select the frequencies during the period when the sound pressure reaches the maximum value as measurement and processing data. Also, the processor 11 may obtain, as measurement and processing data, feature values (for example, the number of times the amplitude becomes a certain level or more and the time thereof, etc.) that can be directly extracted from the respiratory sound data without performing frequency analysis on the respiratory sound data.

[0047] It is known that the vital capacity data (flow-volume curve) measured by a peak flow meter has a difference in shape between a person without a respiratory disease and a person with a respiratory disease. Therefore, when the measurement data is vital capacity data, the processor 11 extracts a flow rate (for example, a flow rate corresponding to 50% or 25% of the maximum value of the exhaled volume, etc.) that can identify the difference in shape from the flow-volume curve as the vital capacity data, and obtains this flow rate as measurement and processing data.

[0048] Alternatively, the processor 11 may extract the flow rates corresponding to each of a plurality of ratios (e.g., 90%, 80%, 70%, etc.) with respect to the maximum value of the exhaled volume from the flow volume curve, and use these as measurement processed data.

[0049] Alternatively, the processor 11 generates data with the absolute exhaled volume on the horizontal axis and the flow rate on the vertical axis from the vital capacity data. In this data, it is known that there is a difference in the centroid position of the absolute exhaled volume between a person without a respiratory disease and a person with a respiratory disease. Therefore, the processor 11 may specify the centroid value of the absolute exhaled volume from this absolute exhaled volume vs. flow rate data, and use this centroid value as measurement processed data.

[0050] The processor 11 sets, as teacher data, a data set of the medication history information, exercise history information, and measurement processed data corresponding to the monitored user generated as described above, and the third data (the determination result of the presence or absence of symptoms by a doctor) corresponding to the monitored user, and causes a machine learning based on the plurality of data sets corresponding to a plurality of monitored users to be executed on a learning model to generate a learned model 13. The medication history information and the exercise history information each constitute behavior history information regarding the behavior history.

[0051] When the learned model 13 is input with the medication history information and exercise history information during a predetermined period and the measurement processed data generated based on the measurement data measured from the user after the predetermined period, it has learned various parameters so as to output a determination result of the presence or absence of symptoms of the respiratory disease of the user. The method of machine learning is not particularly limited, and for example, any method such as logistic regression, decision tree, random forest, gradient boosting decision tree, neural network, etc. can be used.

[0052] (Use of the learned model) First, with the user terminal 30 and the measuring device 40 connected, the measuring device 40 measures measurement data. The measurement data measured by the measuring device 40 and its measurement date and time information are transmitted from the measuring device 40 to the user terminal 30 and acquired by the management app of the user terminal 30. When the management app acquires the measurement data, it reads out the medication history data and exercise history data recorded in the past period up to the period before the above-mentioned predetermined period from the measurement date (measurement timing) of the measurement data from the memory, and transmits them to the information processing server 10 together with the measurement data.

[0053] When the processor 11 acquires the medication history data, exercise history data, and measurement data transmitted from the user terminal 30, it generates medication history information based on the medication history data, generates exercise history information based on the exercise history data, and generates measured and processed data based on the measurement data.

[0054] Next, the processor 11 inputs the generated medication history information, exercise history information, and measured and processed data into the learned model 13, and acquires the determination result of the presence or absence of respiratory disease symptoms as the output of the learned model 13. When the processor 11 acquires this determination result, it transmits this determination result to the management app of the user terminal 30. The management app performs processing to display the received determination result on the display device of the user terminal 30 or output it as voice from the speaker. As a result, the user can know the presence or absence of symptoms. Alternatively, the management app transmits the received determination result to the measuring device 40. When the device processor of the measuring device 40 receives the determination result, it causes the output device to output the determination result. As a result, the determination result may be output from the display or speaker of the measuring device 40. By performing the measurement to the result output by the measuring device 40, the value of the measuring device 40 can be enhanced.

[0055] (Modification example of the learned model) The learned model 13 is obtained by performing machine learning using, as teacher data, a data set of medication history information, exercise history information, measured and processed data, and third data (judgment result by a doctor), but is not limited thereto.

[0056] For example, the learned model 13 may be obtained by performing machine learning using, as teacher data, a data set of either medication history information or exercise history information, measured and processed data, and third data (judgment result by a doctor). In this case, the processor 11 may input either the user's medication history information or exercise history information and the measured and processed data to the learned model 13, and obtain a judgment result on the presence or absence of symptoms from the learned model 13.

[0057] Further, the learned model 13 may be one obtained by performing machine learning so as to output a judgment result on the presence or absence of symptoms of a respiratory disease, with at least one of medication history information, exercise history information, information on the user's sleep history (for example, average sleep time per day during a period or average value of sleep scores during a period), information on the user's drinking history (for example, average alcohol consumption per day during a period or number of drinking occasions during a period), information on the user's smoking history (for example, number of cigarettes smoked per day during a period or number of cigarettes smoked during a period), or information on the user's bathing history (for example, bathing time per day during a period or number of bathing occasions during a period) and the measured and processed data as inputs. The sleep history, drinking history, smoking history, and bathing history are all one of the user's behavior histories.

[0058] Machine learning may be further executed by including user information in the above-described data set.

[0059] User information refers to information regarding the attributes (such as gender, age, physique (BMI), or nationality, etc.) of the monitored user who is the source of the measurement data included in the sample data. The processor 11 generates, for example, medication history information, exercise history information, and measurement processed data based on each sample data in the sample data group, and uses these, user information, and the third data as teacher data, and executes machine learning on the learning program based on this teacher data to generate a learned model 13. Thereby, when medication history information, exercise history information, measurement processed data, and user information about an arbitrary user are input, a learned model 13 can be generated that outputs a determination result on the presence or absence of symptoms of the respiratory disease of that user. In this way, by further using user information, it is possible to more accurately determine the presence or absence of the user's symptoms.

[0060] In the above description, it is assumed that the processor 11 generates medication history information, exercise history information, and measurement processed data, but it is not limited to this. For example, the terminal-side processor that executes the management application of the user terminal 30 generates medication history information, exercise history information, and measurement processed data, and by transmitting the generated medication history information, exercise history information, and measurement processed data to the information processing server 10, the processor 11 may obtain the medication history information, exercise history information, and measurement processed data. Also, when the terminal-side processor generates medication history information, exercise history information, and measurement processed data, it may be configured such that the learned model 13 is incorporated into the management application. In this case, the terminal-side processor inputs the medication history information, exercise history information, and measurement processed data into the learned model 13 to obtain a determination result on the presence or absence of symptoms.

Description of Reference Numerals

[0061] 10 Information processing server 11 Processor 12 Storage unit 13 Model 20 Network 30 User terminal 40 Measuring device 100 Symptom determination system

Claims

1. The processor, Data is obtained based on measurement data indicating the respiratory status of the subject, measured from the subject. Behavioral history information regarding the subject's behavioral history during a period prior to the measurement timing of the aforementioned measurement data is obtained. An information processing method that inputs the aforementioned data and the aforementioned behavioral history information into a trained model and performs the process of obtaining a result from the trained model indicating whether or not the subject has symptoms of a respiratory disease.

2. The information processing method according to claim 1, The aforementioned behavioral history information includes at least one of medication history information relating to medication history and exercise history information relating to exercise history.

3. The information processing method according to claim 2, The aforementioned medication history information includes an information processing method that includes the number of times medication was taken during the aforementioned period.

4. The information processing method according to claim 2 or 3, The aforementioned exercise history information includes an information processing method that includes information on the amount of exercise.

5. The information processing method according to claim 2 or 3, The exercise history information includes an information processing method that includes information on the frequency of exercise performed under specific circumstances.

6. Data is obtained based on measurement data indicating the respiratory status of the person being measured, measured from the person being measured. Behavioral history information regarding the subject's behavioral history during a period prior to the measurement timing of the aforementioned measurement data is obtained. An information processing device comprising a processor that inputs the aforementioned data and the aforementioned behavioral history information into a trained model and performs a process to obtain from the trained model a result of determining whether or not the subject has symptoms of a respiratory disease.

7. Data is obtained based on measurement data indicating the respiratory status of the person being measured, measured from the person being measured. Behavioral history information regarding the subject's behavioral history during a period prior to the measurement timing of the aforementioned measurement data is obtained. The process involves inputting the aforementioned data and the aforementioned behavioral history information into a trained model to obtain a result from the trained model indicating whether or not the subject has symptoms of respiratory disease. An information processing program that causes a processor to execute.

8. The processor, Multiple data sets are acquired as training data, including: data based on measurement data indicating the respiratory status of the first subject measured by the first subject; behavioral history information relating to the first subject's behavioral history during a period prior to the measurement timing of the measurement data; and the results of a physician's judgment on whether or not the first subject experienced symptoms of respiratory disease on the day including the measurement timing. A method for generating a trained model, which involves having a program perform machine learning based on the aforementioned multiple training data, and when data based on measurement data indicating the respiratory state of a second subject measured by the second subject, and behavioral history information relating to the behavioral history of the second subject in a period prior to the measurement timing of the measurement data are input, a trained model is obtained that outputs a result of determining whether or not symptoms of respiratory disease have occurred in the second subject.

9. A trained model is machine-learned using the following as training data: data based on measurement data indicating the respiratory status of a first subject measured from the first subject, behavioral history information relating to the first subject's behavioral history in a period prior to the measurement timing of the measurement data, and the results of a physician's judgment on whether or not the first subject experienced symptoms of respiratory disease on the day including the measurement timing. A trained model that, upon receiving data based on measurement data indicating the respiratory status of a second subject measured by the second subject, and behavioral history information relating to the second subject's behavioral history during a period prior to the measurement timing of the said measurement data, causes the processor to execute a process that outputs a determination result regarding whether or not the second subject has developed symptoms of a respiratory disease.

Images