Medical examination support method, health support method, medical examination support device, and health support device

Abstract

Provided is a medical examination support method, a health support method, a medical examination support device, and a health support device that are capable of determining sensor data with a high degree of granularity. This medical examination support method includes: an acquisition step for acquiring sensor data detected for a user by a sensor and lifestyle information about the lifestyle of the user and recording the data and information on a time-series basis; an extraction step for extracting lifestyle-related information selected from the lifestyle information, the selected lifestyle-related information relating to the sensor data; and an output step for outputting the related information and the sensor data.

Description

Examination support method, health support method, examination support device, and health support device

[0001] The present disclosure relates to a medical examination support method, a health support method, a medical examination support device, and a health support device.

[0002] In recent years, with the rise in health awareness and the need to reduce medical costs and improve patients' quality of life (QOL), an increasing number of people are managing their health by reviewing their lifestyle habits, utilizing daily activity records and vital signs data, even before they become ill, rather than simply going to the hospital after realizing they have an illness, as was the case in the past. Furthermore, the widespread use of mobile devices has made such management easier in terms of technology and infrastructure.

[0003] For example, Patent Document 1 discloses a technique for predicting a user's future physical condition based on a sensor information history including information related to the user acquired from sensors around the user.

[0004] International Publication No. 2019 / 116679

[0005] Incidentally, the daily records made using the various sensors described above are not only important for maintaining the user's health, but also serve as important background data in the event that a subjective symptom appears.

[0006] However, sensor data such as step count, heart rate, and weight obtained from sensors can only reveal daily changes in a user, and even if something changes in the user's behavior, it is difficult to infer what has happened from that alone. For example, if a user who strives to walk 10,000 steps every day suddenly drops their step count, it is difficult to infer whether they are taking a break from walking due to poor health or whether other circumstances have caused this. In other words, if there is a change in step count, such as if a user who used to walk while working from home changes jobs and now commutes by car, it is impossible to make a correct judgment without checking the details of the change. Failure to make this correct judgment could lead to a more serious illness, but conventional technologies such as those described in Patent Document 1 make it impossible to make a correct judgment.

[0007] The present disclosure has been made in consideration of the above, and aims to provide a medical examination support method, a medical examination support method, a health support method, a medical examination support device, and a health support device that are capable of making highly granular judgments on sensor data.

[0008] In order to solve the above-mentioned problems and achieve the objectives, the medical examination support method according to the present disclosure is a medical examination support method executed by a medical examination support device having a processor, and includes an acquisition step in which the processor acquires sensor data detected by a sensor for a user and lifestyle habit information related to the user's lifestyle and records them in chronological order, an extraction step in which selected lifestyle habit-related information selected from the lifestyle habit information and related to the sensor data is extracted, and an output step in which the selected lifestyle habit-related information and the sensor data are output.

[0009] Although the user is assumed to be the person managing their health, the system can also be used to provide support such as diagnosis to medical professionals examining the person.

[0010] Furthermore, in the medical examination support method according to the present disclosure, in the above disclosure, each of the sensor data and the lifestyle habit information includes a plurality of items, the acquiring step acquires a plurality of sensor data detected by a plurality of sensors, and the extracting step selects specific behavioral history information from behavioral history information of a plurality of users based on an item included in sensor data that shows a characteristic trend among the plurality of sensor data, and extracts the specific behavioral history information as the selected lifestyle habit-related information.

[0011] Furthermore, in the medical examination support method according to the present disclosure, in the above disclosure, the medical examination support device is capable of accessing a knowledge database composed of at least symptoms caused by lifestyle habits, treatment methods for the symptoms, and sensor data caused by the symptoms, and the processor further executes a symptom reception step of receiving an input of the user's symptoms, and a search step of searching the knowledge database for sensor data features and lifestyle habit features related to the received symptoms, and the extraction step extracts the selected lifestyle habit-related information based on a search result of the search step.

[0012] In addition, in the above-described diagnosis support method according to the present disclosure, the output step creates report information based on the related information and the sensor data, and outputs the selected lifestyle-related information and the report information.

[0013] In addition, in the medical examination support method according to the present disclosure, in the above disclosure, the sensor data includes at least vital data of the user, and the processor further executes a quality determination step of determining whether the vital data recorded in chronological order is good or bad.

[0014] In addition, in the above disclosure, the extraction step extracts the selected lifestyle-related information based on a determination result of whether the vital data is good or bad and a search result of the search step.

[0015] In addition, in the above-described diagnosis support method according to the present disclosure, the output step outputs a transition state of the user based on the vital data.

[0016] In addition, in the medical examination support method according to the present disclosure, in the above disclosure, the output step outputs a message recommending that the patient visit a relevant medical institution that has been searched for in the knowledge database based on the symptoms if the judgment result of the vital data is negative.

[0017] In addition, in the above disclosure, the output step of the medical examination support method according to the present disclosure, when an external device requests output of the selected lifestyle-related information, outputs to the external device only the related information that has been previously permitted by the user.

[0018] Also, a health support method according to the present disclosure is a health support method executed by a health support device having a processor, the health support method including: an acquisition step in which the processor acquires a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle and records them in chronological order; an extraction step in which a knowledge database is searched and health-related information related to health associated with vital data of a specific item of the sensor data group; and an output step in which the health-related information and lifestyle history information corresponding to the health-related information are output from the recording results recorded in chronological order.

[0019] Also, the health support method according to the present disclosure, as disclosed above, further includes a determination step in which the processor determines specific vital data from the plurality of items of vital data that shows a change or a specific trend, and the extraction step performs a lifestyle habit item search using the knowledge database according to the specific vital data of the user.

[0020] Also, in the health support method according to the present disclosure, in the above disclosure, the processor further includes a symptom input step of accepting input of a user's symptoms, and the extraction step searches the knowledge database and extracts the health-related information in accordance with the symptom input of the user.

[0021] Further, in the health support method according to the present disclosure, in the above disclosure, the knowledge database is a recording medium in which at least one vital data related to health and disease or lifestyle habits trends are organized and recorded by disease.

[0022] Also, in the health support method according to the present disclosure, in the above disclosure, the processor further includes a detection step of detecting a change in the specific vital data and the timing of the change, and the output step outputs history information of the lifestyle habits including a period preceding the timing of the change.

[0023] Also, a health support method according to the present disclosure is a health support method executed by a health support device having a processor, the health support method including: an acquisition step in which the processor acquires an output of a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the lifestyle of the user, and records the multiple items of lifestyle habit information in chronological order; and an output step in which lifestyle history information corresponding to changes in vital data of a specific item of the sensor data group is output from the recording results of the chronological recording of the multiple items of lifestyle habit information.

[0024] Also, a health support method according to the present disclosure is a health support method executed by a health support device having a processor, the health support method including: an acquisition step in which the processor acquires and records in chronological order sensor data detecting a user's vital data and lifestyle habit information relating to the user's lifestyle; and an output step in which the processor infers the future health state by inputting the time series information of the sensor data and the time series information of the lifestyle habit into an inference model trained with training data in which the time series information of the lifestyle habit and the time series information of the vital data for the period corresponding to the data acquisition are annotated with the name of the disease that has developed, its symptoms, and diagnosis results.

[0025] Also, a medical examination support device according to the present disclosure includes an acquisition unit that acquires sensor data detected by a sensor for a user and lifestyle habit information related to the user's lifestyle and records them in chronological order, an extraction unit that extracts selected lifestyle habit-related information selected from the lifestyle habit information, the selected lifestyle habit-related information being related to the sensor data, and an output control unit that outputs the selected lifestyle habit-related information and the sensor data.

[0026] Also, a health support device according to the present disclosure includes an acquisition unit that acquires a sensor data group that detects multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle and records them in chronological order; an extraction unit that searches a knowledge database and extracts health-related information related to health that is associated with the vital data of a specific item of the sensor data group; and an output control unit that outputs the health-related information and lifestyle history information corresponding to the health-related information from the recording results recorded in chronological order.

[0027] The health support device according to the present disclosure includes an acquisition unit that acquires an output of a sensor data group that detects multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle, and records the multiple items of lifestyle habit information in chronological order; and an output control unit that outputs lifestyle history information corresponding to changes in vital data of a specific item of the sensor data group from the recording results of the multiple items of lifestyle habit information recorded in chronological order.

[0028] Also, a health support device according to the present disclosure includes an acquisition unit that acquires and records in chronological order sensor data that detects a user's vital data and lifestyle information related to the user's lifestyle, and an output control unit that infers the user's future health condition by inputting the time series information of the sensor data and the time series information of the lifestyle into an inference model trained with training data in which the time series information of the lifestyle and the time series information of the vital data for the period corresponding to the data acquisition are annotated with the name of the disease that has developed, its symptoms, and diagnostic results.

[0029] According to the present disclosure, an effect is achieved in that highly granular judgments can be made on sensor data.

[0030] FIG. 1 is a schematic diagram of a medical examination support system according to an embodiment. FIG. 2 is a block diagram showing the functional configuration of a mobile terminal according to an embodiment. FIG. 3 is a diagram showing an example of time-series information recorded by a time-series information recording unit of a recording unit included in a mobile terminal according to an embodiment. FIG. 4 is a block diagram showing the functional configuration of a medical system according to an embodiment. FIG. 5 is a diagram showing an example of knowledge data registered in a knowledge database of a recording unit included in a medical system according to an embodiment. FIG. 6 is a timing chart showing an outline of processing executed by a mobile terminal according to an embodiment. FIG. 7 is a timing chart showing an outline of processing executed by a mobile terminal when a user inputs symptoms. FIG. 8 is a diagram showing an example of an image displayed by a display unit during the processing of FIG. 7. FIG. 9 is a diagram showing another example of an image displayed by a display unit during the processing of FIG. 7. FIG. 10 is a timing chart showing an outline of processing between a mobile terminal and a medical terminal when a user visits a medical institution. FIG. 11 is a diagram showing an example of an image displayed by a doctor terminal during the processing of FIG. 10. FIG. 12 is a flowchart showing an outline of processing executed by a mobile terminal according to an embodiment. FIG. 13 is a flowchart showing an outline of processing executed by a medical system according to an embodiment.

[0031] Hereinafter, embodiments for carrying out the present disclosure will be described in detail with reference to the drawings. Note that the present disclosure is not limited to the following embodiments. Furthermore, the drawings referred to in the following description merely show a rough outline of the shape, size, and positional relationship to the extent that the contents of the present disclosure can be understood. In other words, the present disclosure is not limited to the shape, size, and positional relationship exemplified in each drawing. Furthermore, in the following description, a mobile phone is used as an example of a medical examination support device, but other devices such as tablet terminal devices and personal computers can also be used.

[0032] [Overview of Medical Examination Support System] Fig. 1 is a schematic diagram of a medical examination support system according to one embodiment. The medical examination support system 1 shown in Fig. 1 includes a mobile terminal 10 that functions as a medical examination support device, and a medical system 20. The mobile terminal 10 and the medical system 20 are connected to each other via a network N100 so that they can communicate bidirectionally. This network N100 is configured, for example, by an Internet network or a mobile phone network. A user U1 accesses the medical system 20 using the mobile terminal 10.

[0033] [Functional Configuration of Mobile Terminal] Figure 2 is a block diagram showing the functional configuration of the mobile terminal 10. The mobile terminal 10 shown in Figure 2 acquires and chronologically records sensor data detected by sensors such as a smart toilet or a scale, as well as lifestyle information related to the user's lifestyle. It then extracts related information related to the sensor data from the lifestyle information and outputs the related information and the sensor data. While the related information is described as lifestyle information related to the sensor data, it can also include information other than lifestyle information, such as health-related information or selected lifestyle-related information. For example, if the sensor data indicates a rise in body temperature, and an infectious disease characterized by such symptoms is prevalent, the mobile terminal 10 can search for this information (such information may be stored in the knowledge database 242 described below) and communicate it to the user, providing them with information on self-restraint, symptom alleviation, treatment strategies, and mental preparation.

[0034] 2 includes a communication unit 11, a sensor group 12, an input unit 13, a display unit 14, a recording unit 15, and a control unit 16. In one embodiment, the mobile terminal 10 functions as a diagnosis support device or a health support device.

[0035] Under the control of the control unit 16, the communication unit 11 transmits various information to the medical system 20 via the network N100 and receives various information from the medical system 20. The communication unit 11 also receives vital signs, health information, and a user's behavioral history regarding electronic payments using two-dimensional codes such as QR Codes (registered trademarks) from external sensors, such as a smart tray or a weighing scale, that are connected to the mobile terminal 10 via Bluetooth® or Wi-Fi® communication, and outputs the information to the control unit 16. Here, vital signs include blood pressure, electrocardiogram, blood oxygen, heart rate, pulse, body temperature, etc. Health information includes uric acid levels, weight, blood glucose levels, etc. Under the control of the control unit 16, the communication unit 11 also receives environmental information about the mobile terminal 10 from an external weather server (not shown) and outputs the information to the control unit 16. Here, environmental information includes weather information (e.g., sunny, cloudy, etc.), temperature, humidity, warnings (e.g., dry weather warning, migraine warning), and alarms. Furthermore, a smart toilet is a toilet (toilet bowl) equipped with sensors such as a modular urine test sensor that can be incorporated into the toilet seat and a camera capable of capturing video of feces and urine. The smart toilet detects important parameters in the user's urine, such as glucose, pH, uric acid, urea, protein, red blood cells, and fecal occult blood, and detects 11 urine test indicators, including uric acid, urinary protein, and occult blood, as well as the presence or absence of fecal occult blood. Here, the 11 indicators are urine pH, urinary protein, urinary glucose, urinary bilirubin (urinary urobilinogen), urinary ketone bodies, urinary occult blood, urine specific gravity, urine color, nitrite, urinary white blood cells, and urine turbidity. The communication unit 11 is configured using a communication module.

[0036] The sensor group 12 acquires various information related to the user of the mobile terminal 10, such as vital sign information, step count information, and sleep information, and outputs the information to the control unit 16. The sensor group 12 is configured using, for example, a GPS (Global Positioning System) sensor, an acceleration sensor, a blood glucose level sensor such as a pulse oximeter, a humidity sensor, a direction sensor, and a gyro sensor.

[0037] The input unit 13 receives various inputs in response to external operations and outputs them to the control unit 16. The input unit 13 is configured using buttons, switches, a touch panel, and the like.

[0038] The display unit 14 displays various information related to the mobile terminal 10 under the control of the control unit 16. The display unit 14 is configured using a liquid crystal display, an organic electroluminescent display (OLED), or the like.

[0039] Recording unit 15 records various information related to mobile terminal 10. Recording unit 15 has a program recording unit 151 that records various programs executed by mobile terminal 10, a time information recording unit 152 that records time information related to the user of mobile terminal 10, and a mobile terminal identification information recording unit 153 that records identification information for identifying mobile terminal 10. Recording unit 15 is configured using a volatile memory, a non-volatile memory, a memory card, an SSD (Solid State Drive), etc.

[0040] 3 is a diagram showing an example of the temporal information recorded by the temporal information recording unit 152. Here, the mobile terminal 10 is capable of acquiring and chronologically recording a group of sensor data in which a sensor detects multiple items of vital data of the user and multiple items of lifestyle habit information related to the lifestyle of the user.

[0041] As shown in Figure 3, the temporal information K1 records, under the control of the control unit 16, temporal information that records in chronological order each of sensor data detected by a smart toilet, a weighing scale, etc., acquired via the communication unit 11, and lifestyle habit information related to the user's daily life and job hunting.

[0042] The vital data (including, for example, step counts) that a user can obtain varies depending on the device available. Furthermore, since different vital data are associated with different illnesses and health monitors, it is preferable for the mobile device 10 to record multiple vital data. The same can be said for the mobile device 10 when recording lifestyle habits.

[0043] The mobile device 10 acquires a set of sensor data that detects multiple items of vital data of the user and multiple items of lifestyle information related to the user's lifestyle, and records them in chronological order so that they can be correlated. This makes it possible to determine the temporal correlation between changes in vital data due to changes in physical condition and changes in lifestyle. Specifically, the time-series information K1 includes, for example, the user's lifestyle habits, such as preferences, whether or not they drink alcohol, whether or not they smoke, and their behavioral history, which the user answers and enters for each item in a questionnaire that is divided into several items periodically.

[0044] Other examples include analyzing vital data such as the number of steps taken, body temperature, pulse rate, brain waves, breath, blood flow, blood pressure, weight, and composition information from excrement from sensors (for example, wearable devices such as wristwatches, rings, necklaces, clothing, bedding, glasses, masks, smart toilets, smart baths, and smart beds (smart means having a processor, sensors, information processing units, and input / output units) installed in a home (smart home), and other devices (mobile terminals 10 and smartphones may also be equipped with sensors)) to determine drinking, smoking, dietary history, eating habits, etc.

[0045] The mobile device 10 may also obtain information such as the user's location, frequency, and time of day from GPS information. It may also analyze the user's daily shopping (e.g., using receipts or electronic payment results) for several predetermined items to determine changes in lifestyle habits over time for each item. Furthermore, the mobile device 10 can also determine environmental information, such as the weather at the time, based on the location and date and time, using online information from the user's location and shopping information. The behavioral history may include the average number of steps taken each year, the presence or absence of occult blood in feces, the frequency of daily toilet visits, and dietary trends based on shopping history and payment information. For example, dietary trends may include the ratio of grains, meat, fish, and vegetables. Specifically, the dietary trends for 2017 in the behavioral history of the historical information K1 indicate a 3:2:2:3 ratio of grains, meat, fish, and vegetables.

[0046] When the mobile device 10 captures a shopping history by photographing a receipt, it can determine when, how much, and what items were purchased by reading text or codes containing the date, items purchased, quantity, price, and location. If quantity data is not available, it can determine the amount purchased from the relationship between the average weight and price of the food item at that time based on the price. If the amount is an annual average, this amount can be compared year by year. It is also possible to convert the daily intake based on the period leading up to the purchase of the same item.

[0047] Furthermore, the mobile terminal 10 can substitute or use electronic payment details in addition to receipts, and can determine the type and quantity of stored items, kept items, cooked items, etc. using a smart refrigerator or smart cooker.

[0048] The mobile device 10 can also infer a user's preferences based on access to recipe sites. Specifically, if information is obtained that shows that a user frequently searches for fish dishes in one year, but then searches for meat dishes become more frequent in another year, it is possible to determine changes in lifestyle habits over time. If such a database is used in conjunction with the mobile device 10, for example, it becomes possible to present effective health support information.

[0049] By acquiring, in chronological order, sensor data detected by a specific sensor for the user via a mobile terminal 10 or the like, and lifestyle information regarding the user's lifestyle obtained using a mobile terminal 10 or the like, it becomes possible to display and present health-related information in association with information on changes in lifestyle that preceded it.

[0050] This is because some health-related information can be determined from the sensor data. By organizing and extracting these relationships, it is possible to help users recognize lifestyle habits that may be the cause or reason for changes in health-related data, and encourage them to improve their lifestyle habits.

[0051] In addition, since there are diseases that develop due to changes or trends in lifestyle (differences from the average lifestyle of many people or the lifestyle of healthy people), information about changes or trends in lifestyle may be recorded as a cause item, although this is not shown in Figure 3.

[0052] In other words, by obtaining and recording the sensor data that detects the user's vital signs and lifestyle information related to the user's lifestyle in chronological order, the knowledge DB 242 described below can be searched and health-related information can be extracted from the time-series changes and trends (differences from average information), making it possible to output not only the health-related information but also information about changes in lifestyle that may have caused it.

[0053] This is expected to not only assist in diagnosis at the time of onset of the disease but also to improve lifestyle habits at the stage of minute changes. The knowledge DB 242 records lifestyle information on the lifestyle habits of patients with a specific disease as time-series information, and records the changes (tendencies) and trends (such as deviations from the average value) of the lifestyle habits.

[0054] Of course, just having the items as shown in Figure 3 makes it clear which information items can be effectively used for diagnosis, etc., so it would also be an improvement to be able to selectively display lifestyle habit information for that item even if it does not include information on changes or trends, because this would allow immediate confirmation of the corresponding lifestyle history information.

[0055] By accumulating time-series information on lifestyle changes and trends (even without lifestyle changes, the same habits may affect health depending on age) and time-series information on sensor data, such as vital data, from pre-disease states to disease-onset states at the same time as the lifestyle time-series information, it is possible to provide an inference model that infers future health conditions by inputting lifestyle changes and trends and vital data. The inference model can be learned and acquired by annotating the time-series information on lifestyle changes and trends and the time-series information on sensor data, such as vital data, with the name of the disease that has developed, its symptoms, and diagnostic results. Such an inference model may also be provided in a system that is associated with and linked to a knowledge database. In this case, a system can be created that receives necessary information through communication with the knowledge database and outputs health-related advice. Advice may be added to the annotations of the training data used to create the inference model, and advice may be inferred, or advice may be generated from the inference results. The advice is transmitted to the user's mobile device 10 via the communication unit 21.

[0056] Returning to Figure 2, we will continue to explain the configuration of the mobile terminal 10. The control unit 16 is implemented using a processor having hardware such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a CPU (Central Processing Unit), and a memory that is a temporary storage area used by the processor. The control unit 16 includes an acquisition unit 161, a symptom reception unit 162, a search unit 163, a good / bad judgment unit 164, an extraction unit 165, and an output control unit 166.

[0057] The acquisition unit 161 acquires sensor data and lifestyle habit information from the external smart toilet, the scale, and the sensor group 12, and records the data in chronological order in the temporal information recording unit 152 of the recording unit 15. Each of the sensor data and lifestyle habit information includes multiple items. Furthermore, the acquisition unit 161 acquires multiple sensor data detected by multiple sensors.

[0058] The symptom receiving unit 162 receives input of the user's symptoms by the user inputting the symptoms via the input unit 13 .

[0059] The search unit 163 determines, based on the user's symptoms input by the symptom receiving unit 162, whether or not it is possible to search for vital data features corresponding to the user's symptoms and lifestyle features that are the cause of the symptoms from the knowledge DB 242 of the medical system 20, which is composed of at least symptoms caused by lifestyle habits, treatment methods for the symptoms, and sensor data caused by the symptoms.

[0060] The quality determining unit 164 determines whether the user's vital data is good or bad based on the change over time in the user's sensor data recorded by the time information recording unit 152 of the recording unit 15 .

[0061] The extraction unit 165 extracts selected lifestyle-related information related to the sensor data, which is selected from the lifestyle information included in the temporal information recording unit 152, based on the search results obtained by the search unit 163 from the knowledge DB 242 and the determination result of the pass / fail determination unit 164. Here, the related information refers to either the selected lifestyle-related information or health-related information related to health associated with vital data of a specific item in the sensor data group. In the following description, the term "related information" will be used to refer to either the selected lifestyle-related information or the health-related information.

[0062] The output control unit 166 displays the results of the related information extracted by the extraction unit 165 on the display unit 14. Specifically, the output control unit 166 displays a display image including a message of vital data according to the symptoms, a message of lifestyle habit information of the related information extracted by the extraction unit 165, and the created report information on the display unit 14. The output control unit 166 also outputs the health-related information and the lifestyle habit history information corresponding to the health-related information in chronological order from the recording results recorded in the temporal information recording unit 152.

[0063] [Configuration of Medical System] Next, a description will be given of the functional configuration of the medical system 20. Fig. 4 is a block diagram showing the functional configuration of the medical system 20. The medical system 20 shown in Fig. 4 includes a communication unit 21, an input unit 22, an output unit 23, a recording unit 24, and a server control unit 25.

[0064] The communication unit 21 receives various information from the mobile terminal 10 and medical terminals used by external doctors and the like via the network N100 under the control of the server control unit 25, and transmits various information to the mobile terminal 10 or the doctor's terminal. The communication unit 21 is configured using a communication module and the like.

[0065] The input unit 22 receives various inputs in response to external operations and outputs them to the server control unit 25. The input unit 22 is configured using buttons, switches, a touch panel, and the like.

[0066] The output unit 23 displays various information related to the medical system 20 under the control of the server control unit 25. The output unit 23 is configured using a liquid crystal display, an organic EL display, or the like.

[0067] The recording unit 24 records various information executed by the medical system 20. The recording unit 24 has a program recording unit 241 that records various programs executed by the medical system 20, and a knowledge database 242 (hereinafter simply referred to as "knowledge DB 242").

[0068] The knowledge DB 242 stores various types of knowledge corresponding to the symptoms and conditions of patients in a systematized and organized manner. Specifically, the knowledge DB 242 stores symptoms, which are registered or accumulated elements, in association with knowledge information Q1 indicating the relevance of these symptoms. Here, the knowledge information Q1 refers to the causes, treatments, lifestyle habits, and vital signs of each of multiple diseases corresponding to the patient's symptoms and conditions.

[0069] Fig. 5 is a diagram showing an example of knowledge data registered in the knowledge DB 242. As shown in Fig. 5, the knowledge DB 242 is configured so that when a specific symptom appears, it is possible to search for the names of diseases and illnesses that may accompany the symptom. In addition, the knowledge DB 242 is configured so that the causes and treatments of the disease and illness may differ, and these are also organized and recorded.

[0070] Lifestyle-related diseases can worsen or improve depending on lifestyle habits, so these are also recorded for each disease or illness. While typical examples of lifestyle habits are shown here, there may be cases where the deterioration is due to a specific change or a steady tendency that differs from that of healthy people, even if the change is not a specific change. For example, in the case of diet, information such as "eating more meat" or "eating more meat dishes" (the difference from the average value can be quantified as a trend) can be recorded and organized as change information or trend information to be used as one of the causes of illness in the knowledge DB 242.

[0071] Conversely, information (change information, trend information) for improving lifestyle habits for treatment or symptom relief, such as "eat less meat" or "eat less meat dishes (specific numerical target)," may be recorded in the knowledge DB 242. The knowledge DB 242 may be configured so that these can be changed according to race, sex, and age.

[0072] In other words, the knowledge DB 242 may be a recording medium that records health- and disease-related information organized by health disorder or disease, and is characterized by recording lifestyle information regarding the lifestyle habits of patients with specific diseases as time-series information, along with changes and trends.

[0073] Furthermore, as shown in FIG. 5, in the knowledge DB 242, when the symptom is bleeding during defecation, the knowledge information Q1 stores, in association with each other, the candidate disease 1 "colon cancer," the dietary cause "high meat intake," the age "xx years or older," the treatment method "surgery, etc.", the lifestyle dietary habits "meat intake" and exercise "none," and the vital information "fecal occult blood."

[0074] Vital information may also include other disease-specific characteristics such as body temperature, blood pressure, pulse rate, and weight, and disease candidates may be searched for from these items. In addition to the items, normal values ​​and dangerous variations may also be included, making it possible to search for information such as whether a sudden rise in body temperature suggests a specific infectious disease.

[0075] The diet, exercise, etc. listed in the "Lifestyle" section above include lifestyle information related to the lifestyle characteristics of patients with a particular disease. For example, obesity may be caused by high calorie diets or insufficient exercise, and such characteristics may be recorded and configured in the knowledge DB 242.

[0076] 5 simply lists items such as "diet" and "exercise," but more precisely, more detailed information may be included. If calories are the issue, specific numerical targets by gender, age, and height may be recorded in the knowledge DB 242.

[0077] Therefore, the knowledge DB 242 may be configured to record information on changes that indicate the possibility of developing illness if the calorie target is exceeded and a specific value is exceeded, or information on trends such as the risk of developing illness increasing if a specific calorie value continues even if there is not much deviation from the target.

[0078] In this way, knowledge DB 242 only needs to be able to compare changes and trends in the user's lifestyle information with standard values ​​using changes (differential over time) and trends (integral over time), and may also be configured to record characteristic information on changes and trends that pose risks as described here.

[0079] Although one example is shown here, the knowledge DB 242 is a database that records health- and disease-related information organized by health disorder or disease that doctors, medical professionals, patients, and their families can refer to when deciding on medical procedures. For this reason, the knowledge DB 242 records the relationship between symptoms and their treatments, procedures, and prescriptions organized according to specific rules.

[0080] Since symptoms may be different illnesses, diseases, or conditions, knowledge DB242 also organizes information on treatment methods for each disease, as well as factors that make a person more susceptible to disease (race, age, sex, body shape, weight, living environment such as climate, occupational information including exercise, work type such as working from home, and lifestyle habits (including diet, supplements, and medication habits)).This information can be used as a reference for diagnosis and treatment, etc., if necessary.

[0081] Furthermore, in order to improve patients' quality of life, it is said that the construction of a medical support system (Clinical Decision Support System (CDSS)) will be essential in the future. Here, the knowledge DB 242 is assumed to be a recording medium in which health- and disease-related information is organized and recorded by health disorder or disease.

[0082] However, in the knowledge DB 242 shown in Fig. 5, lifestyle information relating to the lifestyles of users (patients with a specific disease, illness, or illness, or people in a pre-illness state) is acquired and recorded in chronological order. The mobile terminal 10 searches the knowledge DB 242 and extracts health-related information or selected lifestyle-related information from the time-series changes and trends (differences from average information (data)), thereby acquiring and outputting not only the health-related information but also information on changes in lifestyle that may have been the cause of the health-related information.

[0083] In addition, information on related medical institutions, testing equipment, testing facilities, medical devices, specialists, medical departments, doctors at related medical institutions, and patient medical history information corresponding to symptoms may be registered and stored in a more systematized and organized state in the knowledge information Q1. In this case, since it is necessary to consult a doctor, related medical institutions (hospital name and address, specialty, whether or not a specialist is present), etc. are registered in the knowledge information Q1. Note that, for each symptom, the knowledge information Q1 is merely an example, and related medical institutions, treatment methods, ingredient information, effect information, specialists, medical departments, side effects, dosage and administration, and doctors at related medical institutions are registered in association with each other. In addition, the medical history information includes the patient's medical history and current underlying diseases, such as diabetes, anemia, and hypertension.

[0084] 4, the configuration of the medical system 20 will be described. The server control unit 25 includes an acquisition unit 251, a search unit 252, a determination unit 253, and a communication control unit 254.

[0085] The acquisition unit 251 acquires various information for updating the knowledge DB 242 via the communication unit 21 and the network N100, and updates the state in which various knowledge corresponding to the patient's symptoms and condition in the knowledge DB 242 is systematized and organized.

[0086] The search unit 252 searches the knowledge DB 242 for relevant information related to the user's symptoms, based on the user's symptoms received from the mobile terminal 10 .

[0087] The determination unit 253 determines whether or not there has been an input communication of the user's symptoms from the mobile terminal 10 via the network N100 and the communication unit 21.

[0088] The communication control unit 254 transmits to the mobile terminal 10 the search result of the related information related to the user's symptoms searched from the knowledge DB 242 by the search unit 252 .

[0089] [Outline of Mobile Terminal Processing] Next, an outline of the processing executed by the mobile terminal 10 will be described. Fig. 6 is a timing chart showing an outline of the processing executed by the mobile terminal 10. In Fig. 6, from the top, (a) shows the sensor data of the smart toilet acquired by the mobile terminal 10, (b) shows the number of steps acquired from the sensor group 12, and (c) shows payment information.

[0090] As shown in Fig. 6, the mobile terminal 10 communicates with an external smart toilet every time the user urinates in the toilet, acquires sensor data (stool test and urine test) detected by the smart toilet, and records the data in chronological order in the time-series information recording unit 152 of the recording unit 15. Furthermore, the mobile terminal 10 acquires the user's step count and payment information from the sensor group 12. In this case, as shown in Fig. 6, if the user visually observes occult blood or bleeding in their stool at 1:00 PM, they input the symptoms into the mobile terminal 10.

[0091] Fig. 7 is a timing chart showing an outline of the processing executed by the mobile terminal 10 when the user inputs symptoms. In Fig. 7, (a) from the top shows the processing timing of the mobile terminal 10, and (b) shows the access timing of the medical system 20. Fig. 8 is a diagram showing an example of an image displayed by the display unit 14 during the processing of Fig. 7. Fig. 9 is a diagram showing another example of an image displayed by the display unit 14 during the processing of Fig. 7.

[0092] As shown in Fig. 7, the user operates the input unit 13 to input their own symptoms. For example, as shown in Fig. 8, the user inputs their own symptoms, such as bleeding during bowel movements, via the input unit 13 in response to an input image P1 displayed on the display unit 14, the input image P1 including the user's step count. Note that the input image P1 includes a transition state of the user's step count H1, which is part of the vital data detected by the sensor group 12. Note that the mobile device 10 may display transitions of the user's weight, blood sugar level, blood pressure, etc., instead of the step count H1, and the display can be changed according to the user's settings.

[0093] Next, the mobile terminal 10 searches the knowledge DB 242 of the medical system 20 for vital data features according to the corresponding disease from the symptoms input via the input unit 13 and for lifestyle habit features that are causes corresponding to the vital data, which is sensor data, among the lifestyle habit information. Note that the mobile terminal 10 may also search the knowledge DB 242 for related medical institutions included in the knowledge information corresponding to the symptoms.

[0094] Subsequently, the mobile device 10 searches the historical information recording unit 152 for vital data characteristics and causes (lifestyle characteristics) corresponding to the disease candidates retrieved from the knowledge DB 242 based on the search results from the knowledge DB 242, and displays a display image corresponding to the search results. Specifically, as shown in FIG. 9 , the mobile device 10 displays a display image P2. This display image P2 includes vital data and lifestyle information corresponding to the symptoms input by the user via the input unit 13. Specifically, the mobile device 10 displays a message M1 indicating that occult blood has been detected in the feces this year as vital data, and a message M2 indicating a change in dietary habits (eating more meat) compared to two years ago as lifestyle information. While FIG. 9 shows only vital data and lifestyle information, if the search results from the knowledge DB 242 include relevant medical institutions that can treat the symptoms, the relevant medical institutions may be included in the display image P2 and displayed on the display unit 14. This allows the user to understand the cause and current situation of the symptoms. Although not shown here, other health-related information that can be searched in the knowledge DB 242 may also be presented as needed.

[0095] Next, an overview of the processing between the mobile terminal 10 and the medical terminal when a user visits a medical institution will be described based on the display image. Fig. 10 is a timing chart showing an overview of the processing between the mobile terminal 10 and the medical terminal when a user visits a medical institution. In Fig. 10, from the top, (a) shows the doctor terminal, (b) shows the access timing of the knowledge DB 242, and (c) shows the timing of the mobile terminal 10. Fig. 11 is a diagram showing an example of an image displayed by the doctor terminal during the processing of Fig. 10.

[0096] 10 , a doctor inputs the symptoms of a patient user using the doctor terminal 200, searches the knowledge DB 242 of the medical system 20 for vital data features according to the corresponding disease based on the user's symptoms and lifestyle habit features that are causes of the vital data (sensor data) among the lifestyle habit information, and obtains the search results. The doctor then uses the doctor terminal 200 to communicate with the user's mobile terminal 10 and requests the mobile terminal 10 to provide information on the vital data features according to the corresponding disease based on the user's symptoms and lifestyle habit features that are causes of the vital data (sensor data) among the lifestyle habit information.

[0097] Subsequently, the mobile terminal 10 outputs the information previously authorized by the user to the doctor terminal 200 in response to a request from the doctor terminal 200. In this case, the doctor terminal 200 displays an image corresponding to the information from the mobile terminal 10. Specifically, as shown in FIG. 11 , the doctor terminal 200 displays a display image P3. This display image P3 includes vital data and lifestyle information corresponding to the symptoms. Specifically, the vital data displays a message M3 indicating that fecal occult blood has been detected this year, and the lifestyle information displays a message M4 indicating a change in dietary habits (more meat) compared to two years ago. This allows the doctor to quickly determine the user's illness based on abnormalities in the user's vital data and changes in lifestyle. Furthermore, the mobile terminal 10 only outputs information authorized by the user to the doctor terminal 200, thereby protecting the user's privacy. It is noteworthy here that, in order to determine the lifestyle habits that triggered the change in vital data, information prior to the change is displayed to clarify the causal relationship.

[0098] [Processing Executed by the Mobile Terminal] Next, a description will be given of processing executed by the mobile terminal 10. Fig. 12 is a flowchart showing an outline of processing executed by the mobile terminal 10.

[0099] 12 , when the user has made an input to the input unit 13 (step S101: Yes), the control unit 16 displays a Top screen on the display unit 14 (step S102). After step S102, the mobile terminal 10 proceeds to step S103. On the other hand, when the control unit 16 determines that the user has not made an input to the input unit 13 (step S101: No), the mobile terminal 10 continues this determination.

[0100] In step S103, the acquisition unit 161 acquires sensor data and lifestyle habit information from the external smart toilet, the scale, and the sensor group 12, and records the data in chronological order in the time-series information recording unit 152.

[0101] Next, if the symptom receiving unit 162 receives the user's symptom input via the input unit 13 (step S104: Yes), the search unit 163 communicates with the knowledge DB 242 via the network N100 (step S105). After step S104, the mobile terminal 10 proceeds to step S106, which will be described later. On the other hand, if the symptom receiving unit 162 does not receive the user's symptom input via the input unit 13 (step S104: No), the mobile terminal 10 proceeds to step S112, which will be described later. Note that in S104, the user (patient or medical professional) manually inputs the symptoms. However, the search unit 163, which will be described later, can detect abnormalities in the user's physical condition using sensor data and use this as a substitute. Symptoms may also be automatically determined based on other information input or operations by the user, such as by "character extraction" or "voice determination." Manual input can also be performed using text input, a questionnaire response method, or an item check method.

[0102] In step S106, the search unit 163 determines whether vital data features and causative lifestyle habit features can be searched for in the knowledge DB 242 based on the user's symptoms input by the symptom receiving unit 162. If it is determined that vital data features and causative lifestyle habit features can be searched for in the knowledge DB 242 (step S106: Yes), the mobile device 10 proceeds to step S107, described below. Here, the search unit 163 may determine only vital data features and, as a result, determine lifestyle habit features when providing guidance. If there is an acquisition step by the acquisition unit 161 that outputs a group of sensor data detecting multiple items of vital data of the user and acquires multiple items of lifestyle habit information related to the user's lifestyle, the search unit 163 may determine only whether the vital data is normal or abnormal. In this case, when a problem (a characteristic trend) is detected, the search unit 163 may also be applied to identify the cause by comparing multiple pieces of lifestyle habit information previously recorded in the historical information recording unit 152 in chronological order. Furthermore, the search unit 163 can easily determine and extract lifestyle history information corresponding to changes in vital data for a specific item from the recording results of the temporal information recording unit 152, without using the knowledge DB 242, by using information and programs that associate vital data with lifestyle data.

[0103] In step S107, the quality determination unit 164 determines whether the user's vital data is good or bad based on the changes over time in the user's sensor data recorded by the time information recording unit 152. The term "good or bad" may refer to a specific change, exceeding a specific threshold, or a continuing trend that differs from normal values. Here, the quality determination unit 164 determines the user's vital data as "bad" if, based on the changes over time in the user's sensor data, the user's weight included in the vital data has increased over time, if the user's step count included in the vital data is below a reference value considered to be a health index but the user's weight has decreased over time, or if occult blood is detected in the vital data. On the other hand, the quality determination unit 164 determines the user's vital data as "good" if, based on the changes over time in the user's sensor data, the user's weight included in the vital data has decreased over time, if the user's step count included in the vital data is equal to or greater than a reference value considered to be a health index and the user's weight has increased over time, or if occult blood is not detected in the vital data. Although the quality determination unit 164 uses only the user's weight as a criterion for determining whether the vital data is good or bad, the quality of the vital data may be determined based on a sleep log based on the vital data, blood glucose level, 11 urine test indicators, and the presence or absence of occult blood in the feces. These sensor data are recorded in chronological order in the time-series information recording unit 152, and the search unit 163 may search for health-related information related to changes or abnormal values ​​in the sensor data, and present and display the information together.

[0104] Furthermore, since the sensor data is time-series information, it is possible to obtain information such as changes over time and the continuation of a particular state for a long period of time. Therefore, the search unit 163 can also search for information such as when such a state occurred and when it began. This timing information may be presented and displayed. Furthermore, for health guidance and diagnostic support, it is important to determine whether a change in sensor data is caused by lifestyle habits, aging, or a combination of these, so lifestyle habit information may be presented and displayed. The health-related information and information on the preceding lifestyle changes may be output.

[0105] Furthermore, the search unit 163 may search the knowledge DB 242 to search for diseases that indicate trends based on changes and trends in vital data, extract health-related information related to a specific item of vital data, and output corresponding lifestyle history information. It is assumed that the health-related information may provide guidance such as "You have a tendency toward XX, so be careful." If the trend can be improved by improving lifestyle habits such as diet, sleep, and exercise, such relationships are also recorded in the knowledge DB 242, making it possible to provide guidance such as "Pay attention to lack of exercise."

[0106] In addition, changes in vital data and the timing of the changes may be detected, and when specific vital data changes, history information on the lifestyle habits, including the period preceding the timing of the change, may be output in order to identify and confirm the lifestyle habits that caused the change.

[0107] Thereafter, the extracting unit 165 extracts relevant information related to the vital data from the lifestyle habit information included in the temporal information recording unit 152, based on the search results obtained by the search unit 163 from the knowledge DB 242 and the determination result of the health determination unit 164 (step S108). Specifically, the extracting unit 165 selects, from the lifestyle habit information included in the temporal information recording unit 152, a change in dietary tendency (eating a lot of meat) related to occult blood in the feces of the vital data, and extracts it as relevant information, based on the search results according to the symptoms obtained by the search unit 163 from the knowledge DB 242 and the determination result of the vital data by the health determination unit 164.

[0108] Next, the output control unit 166 displays the related information extracted by the extraction unit 165 on the display unit 14 (step S109). Specifically, the output control unit 166 displays a message M1 of vital data corresponding to the symptoms, a message M2 of lifestyle habit information of the related information extracted by the extraction unit 165, and a display image P2 (see FIG. 9 described above) including the created report information on the display unit 14. In this case, when the search result obtained by the search unit 163 from the knowledge DB 242 includes multiple related medical institutions corresponding to the symptoms, the output control unit 166 may recommend a medical visit to a related medical institution corresponding to the location information of the mobile terminal 10 by displaying a message on the display unit 14. Of course, the output control unit 166 may also connect to the medical system 20 and make an appointment for the user's treatment at the recommended medical institution. Here, other health-related information searchable in the knowledge DB 242 may also be presented.

[0109] Next, the output control unit 166 outputs the useful information retrieved by the search unit 163 from the knowledge DB 242 (step S110). Here, useful information refers to advice information, such as information on symptoms, their improvement, and prevention of infection, such as multiple potential diseases and multiple medical institutions where the user can receive treatment. A doctor may view the information. While the flow from S105 to S110 has been explained in several steps for clarity, the information retrieved and recorded in chronological order from sensor data detecting the user's vital signs and lifestyle information on the user's lifestyle may be used as input to search the knowledge DB 242 to extract health-related information related to the sensor data (because the required sensor information varies depending on the disease. For example, body temperature is important for influenza, while weight is rarely directly related). Health support may also be provided by outputting information on changes in lifestyle habits that preceded the information. For example, if information is obtained that a user has caught influenza after going out in a crowded place, the user may be encouraged to be more careful when going out. It is also possible to provide caution to the patient's future lifestyle and to their family and colleagues. These data may be used to create an inference model trained with training data annotated with the name of the disease, symptoms, and diagnosis results of the time-series information on lifestyle habits and the time-series information on vital signs corresponding to the time of data acquisition. At this time, by inputting the time-series information on the sensor data and the time-series information on lifestyle habits, it is possible to infer the patient's future health condition and provide advice. After step S110, the mobile terminal 10 proceeds to step S111, which will be described later.

[0110] In step S111, if the user ends the operation of the mobile terminal 10 (step S111: Yes), the mobile terminal 10 returns to step S101. On the other hand, if the user does not end the operation of the mobile terminal 10 (step S111: No), the mobile terminal 10 returns to step S103.

[0111] In step S106, if the search unit 163 cannot search the knowledge DB 242 for the vital data feature and the lifestyle feature that is the cause (step S106: No), the mobile terminal 10 proceeds to step S110, which will be described later.

[0112] In step S112, the mobile terminal 10 executes processing in another mode, for example, a mode corresponding to an application stored in the mobile terminal 10. After step S112, the mobile terminal 10 proceeds to step S111.

[0113] [Processing of Medical System] Next, a description will be given of processing executed by the medical system 20. Fig. 13 is a flowchart showing an outline of processing executed by the medical system 20.

[0114] 13 , the determination unit 253 determines whether or not there has been an input communication of the user's symptoms from the mobile terminal 10 via the network N100 and the communication unit 21 (step S201). If the determination unit 253 determines that there has been an input communication of the user's symptoms from the mobile terminal 10 (step S201: Yes), the medical system 20 proceeds to step S202, which will be described later. On the other hand, if the determination unit 253 determines that there has not been an input communication of the user's symptoms from the mobile terminal 10 (step S201: No), the medical system 20 proceeds to step S201, which will be described later.

[0115] Next, the search unit 252 inputs the user's symptoms received from the knowledge DB 242 via the mobile terminal 10 (step S202), searches for useful information from the knowledge DB 242, and outputs the useful information (step S203). Here, the useful information is useful information corresponding to the symptoms, such as multiple candidate diseases, multiple treatment methods, multiple surgical procedures, and medical history information.

[0116] The determination unit 253 then determines whether vital data features and causative lifestyle features can be retrieved from the knowledge DB 242 based on the user's symptoms input via the mobile terminal 10 (step S204). If the determination unit 253 determines that vital data features and causative lifestyle features can be retrieved from the knowledge DB 242 based on the user's symptoms input via the mobile terminal 10 (step S204: Yes), the medical system 20 proceeds to step S205, described below. The lifestyle features may be simple items or may include features in more detailed items. Alternatively, they may be information on "changes (changes over time)" or "trends (continuity over time)" of lifestyle features indicated by the items. This enables more detailed information to be narrowed down. For example, information presented when lifestyle features have changed or deviate from the average situation is more persuasive than when there are no lifestyle problems. On the other hand, if the determination unit 253 determines that it is not possible to search for vital data characteristics and causative lifestyle characteristics from the knowledge DB 242 based on the user's symptoms input via the mobile terminal 10 (step S204: No), the medical system 20 proceeds to step S206, which will be described later.

[0117] In step S205, the communication control unit 254 transmits the search results from the knowledge DB 242 to the mobile device 10 or the doctor's terminal. Specifically, the communication control unit 254 transmits search results including vital data characteristics and lifestyle characteristics that are causative of the user's symptoms to the mobile device 10 or the doctor's terminal. In this case, obtaining information like messages M1 and M2 in FIG. 9 is preferable for the user. That is, this is because it can be used as a reference to suggest that changes in vital data may be caused by previous lifestyle changes. If lifestyle changes have not changed, age-related changes or other causes can be considered, thereby narrowing down the focus of health maintenance and diagnosis. Therefore, it is possible to display only changes in lifestyle, or to present the absence of lifestyle changes as reference information. However, information from before the time the symptoms were noticed or before the time the vital data changed is important. Because lifestyle changes after the onset of symptoms are generally unlikely to be related to the onset of those symptoms, such restrictions may be imposed. After step S205, the medical system 20 returns to step S201.

[0118] In step S206, the communication control unit 254 transmits to the mobile terminal 10 or the doctor terminal a message indicating that information corresponding to the user's symptoms could not be found from the knowledge DB 242. After step S206, the medical system 20 returns to step S201.

[0119] According to the embodiment described above, the output control unit 166 displays the results of the related information extracted by the extraction unit 165 and the sensor data on the display unit 14, making it possible to make highly granular judgments on the sensor data.

[0120] Furthermore, according to one embodiment, the extraction unit 165 selects and extracts relevant information related to the sensor data from the lifestyle habit information recorded by the temporal information recording unit 152 based on the search results obtained by the search unit 163, so that it is possible to select and extract lifestyle habit information with high granularity according to the symptoms from multiple pieces of lifestyle habit information.

[0121] Furthermore, according to one embodiment, the output control unit 166 displays on the display unit 14 a message M1 of vital data corresponding to the symptoms, a message M2 of lifestyle habit information of related information extracted by the extraction unit 165, and a display image P2 including the created report information, so that the user can understand the contents caused by the lifestyle habit.

[0122] Furthermore, according to one embodiment, the quality determination unit 164 determines whether the user's vital data is good or bad based on the changes over time in the user's sensor data recorded in the time-series information recording unit 152, so that the timing at which the vital data changed can be easily grasped.

[0123] Furthermore, according to one embodiment, the extraction unit 165 extracts relevant information related to the vital data from the lifestyle habit information included in the temporal information recording unit 152 based on the search results obtained by the search unit 163 from the knowledge DB 242 and the determination result of the pass / fail determination unit 164, so that it is possible to identify the user's lifestyle habit that is causing the symptoms by tracing back from the time when the user's vital data changed.

[0124] Furthermore, according to one embodiment, the output control unit 166 outputs the transition state of the user based on the vital data, allowing the user to intuitively understand his or her own condition.

[0125] Furthermore, according to one embodiment, if the vital data is judged as negative by the pass / fail judgment unit 164, the output control unit 166 outputs a message recommending that the user visit a medical institution that the search unit 163 has found in the knowledge DB 242 based on the symptoms, so that the user can identify the medical institution that best suits the symptoms.

[0126] Various inventions can be formed by appropriately combining multiple components disclosed in the diagnosis support system according to the embodiment of the present disclosure described above. For example, some components may be omitted from all the components described in the diagnosis support system according to the embodiment of the present disclosure described above. Furthermore, the components described in the diagnosis support system according to the embodiment of the present disclosure described above may be appropriately combined.

[0127] Furthermore, in the diagnosis support system according to an embodiment of the present disclosure, the above-described "unit" can be read as "means" or "circuit," etc. For example, a control unit can be read as control means or a control circuit.

[0128] In addition, the program to be executed by the diagnostic support system according to one embodiment of the present disclosure is provided as file data in an installable or executable format recorded on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), a USB medium, or a flash memory.

[0129] Furthermore, the program executed by the diagnosis support system according to one embodiment of the present disclosure may be configured to be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.

[0130] In the description of the flowcharts in this specification, expressions such as "first," "then," and "continue" are used to clearly indicate the order of processing between steps. However, the order of processing required to implement the present invention is not uniquely determined by these expressions. In other words, the order of processing in the flowcharts described in this specification can be changed as long as there is no contradiction. Furthermore, programs are not limited to such simple branching processes; branching may be performed by comprehensively determining more judgment items. In such cases, artificial intelligence technology such as machine learning may be used in combination, such as by prompting the user to perform manual operations and repeating learning. Furthermore, deep learning may be performed by learning the operation patterns used by many experts and incorporating more complex conditions.

[0131] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that have undergone various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the disclosure of the present invention.

[0132] The present technology can also be configured as follows. (Supplementary Note 1) A program causing a medical examination support device having a processor to execute: an acquisition step of acquiring sensor data detected by a sensor on a user and lifestyle habit information related to the user's lifestyle, and recording them in chronological order; an extraction step of extracting selected lifestyle habit-related information selected from the lifestyle habit information, the selected lifestyle habit-related information being associated with the sensor data; and an output step of outputting the selected lifestyle habit-related information and the sensor data. (Supplementary Note 2) A program causing a health support device having a processor to execute: an acquisition step of acquiring a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle, and recording them in chronological order; an extraction step of searching a knowledge database and extracting health-related information related to health associated with a specific item of vital data in the sensor data group; and an output step of outputting the health-related information and lifestyle history information corresponding to the health-related information from the chronologically recorded recording results. (Supplementary Note 3) A program causing a health support device having a processor to execute the following steps: an acquisition step of acquiring output of a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle, and recording the multiple items of lifestyle habit information in chronological order, and an output step of outputting lifestyle history information corresponding to changes in vital data of a specific item of the sensor data group from recording results of recording the multiple items of lifestyle habit information in chronological order. (Supplementary Note 4) A program causing a health support device having a processor to execute the following steps: an acquisition step of acquiring each of sensor data detecting the user's vital data and the lifestyle habit information related to the user's lifestyle, and recording them in chronological order, and an output step of inferring what the user's future health condition will be by inputting the time series information of the sensor data and the time series information of the lifestyle habit into an inference model trained with training data annotated with the names, symptoms, and diagnosis of diseases that have developed, based on the time series information of the lifestyle habit and time series information of the vital data for periods corresponding to the data acquisition.

[0133] REFERENCE SIGNS LIST 1 Diagnosis support system 10 Portable terminal 11, 21 Communication unit 12 Sensor group 13, 22 Input unit 14 Display unit 15, 24 Recording unit 16 Control unit 20 Medical system 25 Server control unit 151, 241 Program recording unit 152 Temporal information recording unit 153 Portable terminal identification information recording unit 161, 251 Acquisition unit 162 Symptom reception unit 163, 252 Search unit 164 Pass / fail judgment unit 165 Extraction unit 166 Output control unit 200 Doctor terminal 241 Program recording unit 242 Knowledge database 253 Judgment unit 254 Communication control unit

Claims

1. A medical examination support method executed by a medical examination support device having a processor, the method including: an acquisition step in which the processor acquires sensor data detected by a sensor for a user and lifestyle habit information related to the user's lifestyle and records them in chronological order; an extraction step in which selected lifestyle habit related information selected from the lifestyle habit information, the selected lifestyle habit related information being related to the sensor data; and an output step in which the selected lifestyle habit related information and the sensor data are output.

2. A medical examination support method according to claim 1, wherein each of the sensor data and the lifestyle habit information includes a plurality of items, the acquisition step acquires a plurality of sensor data detected by a plurality of sensors, and the extraction step selects specific behavioral history information from the behavioral history information of a plurality of users based on an item included in sensor data that shows a characteristic trend among the plurality of sensor data, and extracts the specific behavioral history information as the selected lifestyle habit-related information.

3. A medical examination support method according to claim 2, wherein the medical examination support device is capable of accessing a knowledge database comprising at least symptoms caused by lifestyle habits, treatment methods for the symptoms, and sensor data caused by the symptoms, and the processor further executes a symptom reception step of receiving an input of the user's symptoms, and a search step of searching the knowledge database for sensor data features and lifestyle habit features related to the received symptoms, and the extraction step extracts the selected lifestyle habit-related information based on the search results of the search step.

4. A medical examination support method according to claim 3, wherein the output step comprises creating report information based on the related information and the sensor data, and outputting the selected lifestyle-related information and the report information.

5. A medical examination support method according to claim 4, wherein the sensor data includes at least vital data of the user, and the processor further executes a quality determination step of determining whether the vital data recorded in chronological order is good or bad.

6. A medical examination support method according to claim 5, wherein the extraction step extracts the selected lifestyle-related information based on the result of determining whether the vital data is good or bad and the search results of the search step.

7. A medical examination support method according to claim 6, wherein the output step outputs a transition state of the user based on the vital data.

8. A medical examination support method according to claim 7, wherein the output step outputs a message recommending a visit to a related medical institution found in the knowledge database according to the symptoms when the determination result of the vital data is negative.

9. A medical examination support method according to claim 8, wherein the output step, when a request for output of the selected lifestyle-related information is received from an external device, outputs to the external device only the related information that has been permitted in advance by the user.

10. A health support method executed by a health support device having a processor, the health support method including: an acquisition step in which the processor acquires a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle and records them in chronological order; an extraction step in which a knowledge database is searched and health-related information related to health associated with a specific item of vital data in the sensor data group; and an output step in which the health-related information and lifestyle history information corresponding to the health-related information are output from the recording results recorded in chronological order.

11. A health support method as described in claim 10, wherein the processor further includes a determination step of determining specific vital data from the plurality of items of vital data that shows a change or a specific trend, and the extraction step includes a lifestyle habit item search using the knowledge database performed according to the specific vital data of the user.

12. A health support method according to claim 10, wherein the processor further includes a symptom input step of accepting input of a user's symptoms, and the extraction step searches the knowledge database and extracts the health-related information in accordance with the user's symptom input.

13. A health support method according to claim 10, wherein the knowledge database is a recording medium in which at least one of vital data related to health and disease or lifestyle habits trends is organized and recorded by disease.

14. A health support method according to claim 10, wherein the processor further includes a detection step of detecting a change in the specific vital data and the timing of the change, and the output step outputs history information of the lifestyle habits including the period preceding the timing of the change.

15. A health support method executed by a health support device having a processor, the health support method including: an acquisition step in which the processor acquires outputs of a sensor data group detecting multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle, and records the multiple items of lifestyle habit information in chronological order; and an output step in which lifestyle history information corresponding to changes in vital data of a specific item of the sensor data group is output from the recording results of the multiple items of lifestyle habit information recorded in chronological order.

16. A health support method executed by a health support device having a processor, comprising: an acquisition step in which the processor acquires sensor data detecting a user's vital data and lifestyle information related to the user's lifestyle and records them in chronological order; and an output step in which the processor infers what future health condition the user will have by inputting the time series information of the sensor data and the time series information of the lifestyle into an inference model trained with training data in which the time series information of the lifestyle and the time series information of the vital data for the period corresponding to the data acquisition are annotated with the name of the disease that has developed, its symptoms, and diagnosis results.

17. A medical examination support device comprising: an acquisition unit that acquires sensor data detected by a sensor on a user and lifestyle habit information related to the user's lifestyle and records them in chronological order; an extraction unit that extracts selected lifestyle habit related information selected from the lifestyle habit information, the selected lifestyle habit related information being related to the sensor data; and an output control unit that outputs the selected lifestyle habit related information and the sensor data.

18. A health support device comprising: an acquisition unit that acquires a sensor data group that detects multiple items of vital data of a user and multiple items of lifestyle information related to the user's lifestyle and records them in chronological order; an extraction unit that searches a knowledge database and extracts health-related information related to health associated with a specific item of vital data in the sensor data group; and an output control unit that outputs the health-related information and lifestyle history information corresponding to the health-related information from the recording results recorded in chronological order.

19. A health support device comprising: an acquisition unit that acquires the output of a sensor data group that detects multiple items of vital data of a user and multiple items of lifestyle habit information related to the user's lifestyle, and records the multiple items of lifestyle habit information in chronological order; and an output control unit that outputs lifestyle history information corresponding to changes in vital data of a specific item of the sensor data group from the recording results of the multiple items of lifestyle habit information recorded in chronological order.

20. A health support device comprising: an acquisition unit that acquires and records in chronological order sensor data that detects a user's vital data and lifestyle information related to the user's lifestyle; and an output control unit that infers the user's future health condition by inputting the time series information of the sensor data and the time series information of the lifestyle into an inference model trained with training data in which the time series information of the lifestyle and the time series information of the vital data for the period corresponding to the data acquisition are annotated with the name of the disease that has developed, its symptoms, and diagnosis results.

Images