WO2022107518A1 - 血液情報推定装置 - Google Patents
血液情報推定装置 Download PDFInfo
- Publication number
- WO2022107518A1 WO2022107518A1 PCT/JP2021/038247 JP2021038247W WO2022107518A1 WO 2022107518 A1 WO2022107518 A1 WO 2022107518A1 JP 2021038247 W JP2021038247 W JP 2021038247W WO 2022107518 A1 WO2022107518 A1 WO 2022107518A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- blood
- blood information
- user
- function
- Prior art date
Links
- 239000008280 blood Substances 0.000 title claims abstract description 101
- 210000004369 blood Anatomy 0.000 title claims abstract description 101
- 230000036772 blood pressure Effects 0.000 claims abstract description 35
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 claims description 16
- 230000004622 sleep time Effects 0.000 claims description 9
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 8
- 235000012000 cholesterol Nutrition 0.000 claims description 8
- 239000008103 glucose Substances 0.000 claims description 8
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 claims description 8
- 230000004807 localization Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 235000015598 salt intake Nutrition 0.000 claims description 4
- 235000019577 caloric intake Nutrition 0.000 claims description 3
- 230000007958 sleep Effects 0.000 claims description 3
- 230000036760 body temperature Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 abstract description 130
- 206010020772 Hypertension Diseases 0.000 abstract description 107
- 208000000348 Masked Hypertension Diseases 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 76
- 238000000034 method Methods 0.000 description 28
- 238000010276 construction Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 14
- 238000012545 processing Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000013500 data storage Methods 0.000 description 6
- 230000011664 signaling Effects 0.000 description 6
- 238000012546 transfer Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000036541 health Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 2
- 235000011941 Tilia x europaea Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000037396 body weight Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000004571 lime Substances 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000006249 magnetic particle Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present invention relates to a blood information estimation device that estimates a user's blood condition.
- Patent Document 1 describes a method for detecting a change in a patient's health status, and particularly predicts the risk of a change in medical symptoms for a patient based on a usage log of a native communication application and a health risk model. There is a description about that.
- Blood pressure measurement in a general examination room focuses only on a temporary point at the time of examination. Since blood pressure changes depending on the environment in which the measurer is placed and the timing of measurement, it is possible to overlook the existence of health risks such as hypertension. That is, while it is possible to measure blood pressure that can be determined to be hypertension when continuously measuring blood pressure at home, there are cases where it is not possible to measure blood pressure that can be determined to be hypertension when measuring blood pressure in a doctor's office or the like. Such a blood pressure state is called masked hypertension. On the other hand, in the technique described in Patent Document 1, although there is a description that a health risk is predicted, it is not possible to grasp a state such as blood pressure, and it is difficult to determine a masked hypertension or the like.
- a blood information estimation device for determining a blood condition such as a user's blood pressure.
- the blood information estimation device of the present invention has a log acquisition unit that acquires a usage log of a user terminal such as a smartphone, and a blood information estimation unit that estimates blood information related to changes in the blood state based on the usage log. Be prepared.
- blood information such as blood pressure can be estimated without the user actively performing a test.
- blood information can be estimated without the user actively performing a test.
- FIG. 10 It is a figure which shows the functional structure of the blood information estimation apparatus 100 in this disclosure. It is a figure which shows the functional structure of the terminal use log acquisition part 20. It is a figure which shows the functional structure of the weather information acquisition unit 30. It is a figure which shows the functional structure of the hypertension detection part 40. It is a figure which shows the relationship between a terminal use log and a lifestyle. It is a figure which shows the teacher data stored in the teacher data storage database 40a. It is a flowchart which shows the operation of the hypertension detection unit 40. It is a flowchart which shows the construction process of the hypertension detection model 44a. It is a flowchart which shows the hypertension detection processing using the hypertension detection model 44a. It is a figure which shows an example of the hardware composition of the blood information estimation apparatus 100 which concerns on one Embodiment of this disclosure.
- FIG. 1 is a diagram showing a functional configuration of the blood information estimation device 100 in the present disclosure.
- the blood information estimation device 100 includes a terminal use log acquisition unit 20, a weather information acquisition unit 30, and a hypertension detection unit 40.
- the terminal usage log acquisition unit 20 is a portion that acquires the terminal usage log of the user terminal operated by the user 10 and the user attribute information of the user of the user terminal.
- the weather information acquisition unit 30 is a part that acquires weather information in the area where the user 10 is located.
- the hypertension detection unit 40 is a part that detects the blood pressure state of the user 10 based on the terminal usage log, the user attribute information, and the weather information acquired by the terminal usage log acquisition unit 20 and the weather information acquisition unit 30, respectively.
- hypertension is assumed as the blood pressure state, but the present invention is not limited to this. Further, in addition to the blood pressure state, other blood states such as blood glucose level, triglyceride, cholesterol and the like may be detected.
- FIG. 2 is a diagram showing a functional configuration of the terminal usage log acquisition unit 20.
- the terminal usage log acquisition unit 20 has a user authentication function 21, a user attribute information acquisition function 22, an application usage information acquisition function 23, a purchase history information acquisition function 24, a location information acquisition function 25, a terminal operation information acquisition function 26, and data transfer. It is configured to include the function 27.
- the user authentication function 21 is a function for authenticating whether or not the user of the user terminal is a legitimately registered user when acquiring user attribute information or terminal usage log from the user terminal.
- the user terminal is a wearable terminal (watch type, glasses type, etc.) in addition to a mobile terminal, a smartphone, and the like.
- the user attribute information acquisition function 22 is a function for directly acquiring user attribute information from the user terminal or the user 10.
- the user attribute information is user attribute information that can affect the blood condition such as the user's age and gender.
- the application usage information acquisition function 23 is a function for acquiring the number of steps, sleep time, weight, etc. of the user acquired in the healthcare-related application (hereinafter abbreviated as the healthcare-related application) as the terminal usage log.
- the healthcare-related application can measure the number of steps by using the gyro function provided in the user terminal and / or the declared value input to the application of the user.
- the behavior of the user terminal is measured using the operation history of the user terminal or the above gyro, and the period during which the behavior cannot be measured is measured as the sleep time.
- the sleep time may be acquired based on the declared value entered by the user in the application.
- the body weight may be estimated from an image such as the face of the user, or may be acquired based on the declared value input to the application of the user or the measured value of the measuring device linked with the user terminal.
- the application usage information acquisition function 23 can measure body temperature and pulse using a healthcare-related application, or can obtain input from a user. In addition, the application usage information acquisition function 23 can acquire a camera image taken by a camera provided in the terminal as a usage log.
- the purchase history information acquisition function 24 acquires the purchase history information of the purchase made by using the payment function of the user terminal as the terminal usage log.
- the payment function includes payment using a QR code or payment using a contactless IC card.
- the purchase history information includes purchase store information, purchase price, purchased product, date, and the like.
- the location information acquisition function 25 is a function of acquiring the user's current position as a terminal usage log, and acquires a position based on GPS information or base localization zone information measured at the user terminal and a WiFi access point.
- the terminal operation information acquisition function 26 is a function for acquiring terminal operation information as a terminal usage log.
- the terminal operation information is information indicating screen on / off, acceleration, illuminance, browsing URL, application used, and the like.
- the terminal operation information is stored as a history in the user terminal, and the terminal operation information acquisition function 26 acquires the history.
- the data transfer function 27 is a function of transferring the user attribute information and the terminal usage log acquired by each acquisition function to the hypertension detection unit 40.
- FIG. 3 is a diagram showing a functional configuration of the weather information acquisition unit 30.
- the weather information acquisition unit 30 includes a user authentication function 31, a user position information acquisition function 32, a weather information acquisition function 33, and a data transfer function 34.
- the user authentication function 31 is a function for authenticating a user. When acquiring weather information, it is necessary to grasp the user's location information, and at that time, user authentication is performed.
- the user position information acquisition function 32 is a function for acquiring the user's position information.
- the location information is acquired from the server of the mobile communication network that manages the location of the user terminal, or is acquired from the user terminal.
- the weather information acquisition function 33 is a function of acquiring weather information according to the user's position information from the weather information database 30a.
- the data transfer function 34 is a function of transferring the acquired weather information to the hypertension detection unit 40.
- FIG. 4 is a diagram showing a functional configuration of the hypertension detection unit 40.
- the hypertension detection unit 40 includes a data acquisition function 41 (log information acquisition unit), a data cleansing function 42, a lifestyle estimation function 43, a hypertension detection model construction function 44 (learning unit), and a hypertension detection function 45 (blood information estimation unit). And the result notification function 46 is included.
- the data acquisition function 41 is a function for acquiring terminal usage logs, user attribute information, and weather information from the terminal usage log acquisition unit 20 and the weather information acquisition unit 30, respectively.
- the data acquisition function 41 acquires the terminal usage log or the like acquired by the terminal usage log acquisition unit 20 and the weather information acquisition unit 30 for a predetermined period at an arbitrary timing or periodically.
- the user attribute information does not have to be collected if it is stored in advance. Alternatively, it may be collected once and stored.
- the data cleansing function 42 is a function for performing cleansing processing such as missing values and abnormal values of the acquired terminal usage log and weather information for a predetermined period.
- the lifestyle-related estimation function 43 includes exercise amount, commuting / schooling means / time / pattern, stress, fatigue level, regularity of life / sleep, eating frequency, salt intake, and salt intake, based on the terminal usage log and user attribute information. It is a function to estimate lifestyle-related habits such as calorie intake. Further, the lifestyle estimation function 43 may estimate the happiness level based on the terminal usage log and the user attribute information. Happiness is calculated by comprehensively considering the amount of exercise, commuting means, stress, fatigue, etc.
- FIG. 5 is a diagram showing the relationship between the terminal usage log and the lifestyle.
- the lifestyle-related estimation function 43 estimates a lifestyle-related habit based on the relationship shown in FIG.
- the amount of exercise as a lifestyle is shown by, for example, calories burned, and is estimated based on age, gender, number of steps, GPS information, base localization zone information, and acceleration among user attributes and terminal usage logs.
- the commuting / school means / time / pattern indicates the commuting time zone and the like, and is estimated based on the GPS information and the base localization zone information.
- the distance between home and work / school, the travel time, and the travel route are grasped based on the travel time, travel speed, stay position, etc., and commuting / school means and the like are estimated from the distance.
- the stress indicates the degree thereof, for example, in 10 steps.
- the stress is estimated based on the stress estimation algorithm based on the purchase store information, the purchase price, the purchased product, the screen on / off information, the illuminance, the browsing URL, and the application information used.
- Fatigue indicates the degree of fatigue and is estimated based on age, gender, and sleep time. It is estimated that the degree of fatigue is high when the sleep time is short.
- the regularity of life / sleep indicates the degree and is estimated based on the number of steps, sleep time, GPS information, base localization zone information, and screen on / off information.
- the frequency of eating out indicates the number of times of eating out, and is estimated based on the purchased store information, purchased products, GPS information, and base localization zone information.
- the salt intake indicates a specific numerical value or its degree, and is estimated based on the store information and the purchased product.
- the calorie intake indicates a specific numerical value or its degree, and is estimated based on the body weight, the store information, the purchase price, and the purchased product. The above is an example and can be changed as appropriate.
- the lifestyle-related estimation function 43 estimates the corresponding lifestyle-related habits based on each terminal usage log.
- the lifestyle-related estimation function 43 determines a lifestyle-related habit based on a predetermined algorithm. For example, the lifestyle estimation function 43 calculates the amount of exercise according to the number of steps.
- the hypertension detection model construction function 44 is a function for constructing a hypertension detection model (hypertension prediction model) based on the teacher data stored in the teacher data storage database 40a.
- the teacher data is aggregated by the health care application installed in each user terminal in advance.
- FIG. 6 is a diagram showing teacher data stored in the teacher data storage database 40a.
- user attribute information, terminal usage log, lifestyle information, weather information, and blood pressure information are stored for each user and date and time.
- These teacher data are data provided by users in advance, and each user provides information for a predetermined period (for example, several months).
- the hypertension detection model construction function 44 uses user attribute information, terminal usage log, lifestyle information, and weather information as explanatory variables, and has two values of blood pressure information (the average value of the predetermined period or whether the hypertension is determined from the average value). ) Is set as the objective variable, and a hypertension detection model is constructed by performing machine learning.
- blood glucose level information, triglyceride information, or cholesterol information may be stored and an estimation model may be constructed using this as an objective variable.
- the hypertension detection model construction function 44 may construct the hypertension detection model 44a for each user attribute information. For example, the hypertension detection model construction function 44 may learn the hypertension detection model 44a by separating the terminal usage log and the blood information for each age and / and gender.
- the hypertension detection function 45 inputs the terminal usage log, weather information and user attribute information acquired by the data acquisition function 41, and the lifestyle information estimated by the lifestyle estimation function 43 into the hypertension detection model, and the blood pressure information is output as the output. It is a function to estimate and detect hypertension. It is important to input at least the terminal usage log, but the accuracy will be further improved if lifestyle information, weather information, and user attribute information are taken into consideration in addition to the terminal usage log.
- the result notification function 46 is a function for notifying the user of blood pressure information.
- the result notification function 46 notifies the user terminal owned by the user of blood pressure information.
- the result notification function 46 notifies the blood glucose level information, the triglyceride information, and the cholesterol information when the blood glucose level information, the triglyceride information, and the cholesterol information are estimated.
- the result notification function 46 may notify the lifestyle habits estimated by the lifestyle habit estimation function 43 that can increase the risk of hypertension of the user.
- FIG. 7 is a flowchart showing the operation.
- the data acquisition function 41 obtains the terminal usage log of the user who wants to estimate the hypertension acquired by the terminal usage log acquisition unit 20 for an arbitrary predetermined period, and the weather information of the user's area location acquired by the weather information acquisition unit 30. Obtained from the user terminal (S100).
- the data cleansing function 42 performs cleansing such as removal of abnormal values and interpolation of missing values with respect to the terminal usage log and weather information acquired in the process S100 (S101).
- the hypertension detection model construction function 44 constructs the hypertension detection model 44a from the teacher data in an arbitrary predetermined period stored in the teacher data storage database 40a (S102).
- the lifestyle-related estimation function 43 estimates the lifestyle-related habits based on the terminal usage log (S103). For example, the lifestyle-related estimation function 43 estimates a lifestyle-related habit based on the relationship shown in FIG.
- the hypertension detection function 45 inputs the terminal usage log, lifestyle, and weather information of the user's location to the hypertension detection model 44a of the user who wants to detect the hypertension, and the hypertension detection model 44a is the blood pressure which is the hypertension detection result. Information is output (S104).
- the result notification function 46 notifies the user terminal of the hypertension detection result (S105).
- the hypertension detection model 44a is constructed in the process 102, but this process is not always necessary.
- the hypertension detection model 44a may be constructed in advance, and the process S103 may be executed after the process S101.
- FIG. 8 is a flowchart showing detailed processing of the hypertension detection model construction function 44.
- the high blood pressure detection model construction function 44 includes user attributes, terminal usage logs, lifestyle information, weather information, blood information (here, blood pressure value), etc. for an arbitrary period from the teacher data stored in the teacher data storage database 40a. Acquire learning data (including learning usage log, learning lifestyle information, learning blood information, etc.) (S103-1).
- the hypertension detection model construction function 44 averages a plurality of blood pressure values for each user with respect to the acquired data (S103-2).
- the teacher data includes a plurality of data (blood information) in time series in the same user, and a temporary abnormal value is eliminated by calculating the average value. It should be noted that the median value or the moving average value at any time point may be used instead of the average value.
- the hypertension detection model construction function 44 labels each user whether or not he / she has hypertension (which may further include the degree of hypertension) based on the averaged blood pressure value (S103-3).
- the hypertension detection model construction function 44 constructs a hypertension detection model 44a that estimates an averaged blood pressure value or a hypertension label from each user's terminal usage log, lifestyle, and weather information of the location in the area in the teacher data (S103-). 4).
- the hypertension detection model construction function 44 performs machine learning using the terminal usage log, lifestyle, and weather information of the location in the area of each user as explanatory variables, and the blood pressure value or hypertension label as the objective variable.
- the machine learning method used does not matter. For example, it may be a classical linear model, a method such as SVM, XGBoost, or LightGBM, or deep learning such as DNN may be used.
- the hypertension detection model construction function 44 can learn the hypertension detection model 44a based on the terminal usage log of the user terminal or the like.
- FIG. 9 is a flowchart showing the process.
- the hypertension detection function 45 inputs the terminal usage log of the user who wants to detect the hypertension, the lifestyle, and the weather information of the user's area position into the hypertension detection model 44a (S104-1).
- the lifestyle here is the information estimated in S103.
- the hypertension detection function 45 receives the blood pressure value of the user or the label (or the probability of hypertension or the blood pressure value) of whether or not the user is hypertension from the hypertension detection model 44a (S104-2).
- the hypertension detection function 45 identifies the cause of hypertension or a lifestyle that can increase the risk of hypertension for the user (S104-3).
- the hypertension detection model construction function 44 may specify a lifestyle that increases the risk of hypertension from the magnitude of the coefficient (for example, the weighting coefficient of the middle layer in machine learning) related to each feature of the hypertension detection model 44a.
- the lifestyle may be specified from an index for evaluating the importance of the feature amount by using an interpretation method of a prediction model of machine learning such as LIME or SHAP.
- the hypertension detection function 45 is a function for constructing a hypertension detection model, which lifestyle is such that when the user has high blood pressure (or the probability of having high blood pressure is high), the user has a small amount of exercise or high stress. Estimate the output of 44, that is, whether it affected or did not affect the label of hypertension (or the probability of hypertension or the blood pressure value).
- the blood information estimation device 100 of the present disclosure has a data acquisition function 41 that functions as a log acquisition unit that acquires a terminal usage log of a user terminal such as a mobile terminal, and blood information related to changes in the blood state based on the terminal usage log. It is provided with a high blood pressure detection function 45 that functions as an estimation unit for estimating.
- the blood condition blood pressure, blood glucose level, triglyceride, or cholesterol
- blood pressure blood pressure
- blood glucose level blood glucose level
- triglyceride or cholesterol
- the blood condition was estimated in consideration of the user attribute information, the weather information, and the lifestyle information, but at least the terminal usage log may be used.
- the blood information estimation device 100 of the present disclosure uses at least one of blood pressure, blood glucose level, triglyceride, and cholesterol as blood information.
- the blood information estimation device 100 of the present disclosure uses at least one of steps, sleep time, position information, screen on / off information, acceleration, illuminance, browsing URL, purchase history, or used application information as a terminal usage log. Estimate blood information.
- the lifestyle-related estimation function 43 is at least one of the user's exercise amount, exercise time, calories burned, sleep time, sleep quality, regularity, and stress based on the terminal usage log.
- the lifestyle-related information including the above is estimated, and the hypertension detection function 45 estimates blood information based on the lifestyle-related information.
- blood information can be estimated in consideration of lifestyle habits, and more accurate blood information can be estimated.
- the blood information estimation device 100 of the present disclosure includes a hypertension detection model that outputs blood information according to a terminal usage log.
- the hypertension detection function 45 estimates blood information using a hypertension detection model.
- the hypertension detection model construction function 44 learns based on the average value of blood information in a predetermined period as blood information at the time of learning, and constructs a hypertension detection model.
- Blood information especially blood pressure, blood glucose level, triglyceride information, and cholesterol information fluctuates. Therefore, if a hypertension detection model based only on a certain temporary point is constructed, accurate estimation cannot be performed. For example, if learning is performed based on blood pressure information only in the examination room, accurate estimation results cannot be obtained. In the present disclosure, the estimation accuracy can be improved by learning based on the average value of blood pressure information.
- the hypertension detection model construction function 44 of the present disclosure learns the hypertension detection model based on the terminal usage log and blood information in a predetermined age and / or gender, and the hypertension detection function 45 is the user's age and / or Blood information may be estimated by applying a hypertension detection model according to gender.
- the hypertension detection function 45 of the present disclosure identifies the lifestyle habit that is the basis of the estimated blood information. For example, when it is determined that hypertension is high, the lifestyle that contributed to the determination is specified.
- the hypertension detection function 45 can identify a lifestyle habit by using an interpretation method (LIME or SHAP) as to what kind of interpretation the hypertension detection model 44a has performed.
- each functional block may be realized using one physically or logically coupled device, or two or more physically or logically separated devices can be directly or indirectly (eg, for example). , Wired, wireless, etc.) and may be realized using these plurality of devices.
- the functional block may be realized by combining the software with the one device or the plurality of devices.
- Functions include judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, and assumption. Broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc., but limited to these I can't.
- a functional block (configuration unit) that makes transmission function is called a transmitting unit (transmitting unit) or a transmitter (transmitter).
- the realization method is not particularly limited.
- the blood information estimation device 100 may function as a computer for processing the blood information estimation method of the present disclosure.
- FIG. 10 is a diagram showing an example of the hardware configuration of the blood information estimation device 100 according to the embodiment of the present disclosure.
- the blood information estimation device 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.
- the word “device” can be read as a circuit, device, unit, etc.
- the hardware configuration of the blood information estimation device 100 may be configured to include one or more of the devices shown in the figure, or may be configured not to include some of the devices.
- the processor 1001 For each function in the blood information estimation device 100, by loading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, the processor 1001 performs an operation and controls communication by the communication device 1004. It is realized by controlling at least one of reading and writing of data in the memory 1002 and the storage 1003.
- predetermined software program
- the processor 1001 operates, for example, an operating system to control the entire computer.
- the processor 1001 may be configured by a central processing unit (CPU: Central Processing Unit) including an interface with a peripheral device, a control device, an arithmetic unit, a register, and the like.
- CPU Central Processing Unit
- the terminal usage log acquisition unit 20, the hypertension detection unit 40, and the like described above may be realized by the processor 1001.
- the processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these.
- a program program code
- the hypertension detection unit 40 may be realized by a control program stored in the memory 1002 and operating in the processor 1001, and may be realized in the same manner for other functional blocks.
- the memory 1002 is a computer-readable recording medium, and is composed of at least one such as a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). May be done.
- the memory 1002 may be referred to as a register, a cache, a main memory (main storage device), or the like.
- the memory 1002 can store a program (program code), a software module, or the like that can be executed to carry out the blood information estimation method according to the embodiment of the present disclosure.
- the storage 1003 is a computer-readable recording medium, and is, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a photomagnetic disk (for example, a compact disk, a digital versatile disk, a Blu-ray). It may consist of at least one (registered trademark) disk), smart card, flash memory (eg, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like.
- the storage 1003 may be referred to as an auxiliary storage device.
- the storage medium described above may be, for example, a database, server or other suitable medium containing at least one of the memory 1002 and the storage 1003.
- the communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, or the like.
- the communication device 1004 includes, for example, a high frequency switch, a duplexer, a filter, a frequency synthesizer, and the like in order to realize at least one of frequency division duplex (FDD: Frequency Division Duplex) and time division duplex (TDD: Time Division Duplex). It may be composed of.
- FDD Frequency Division Duplex
- TDD Time Division Duplex
- the input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts an input from the outside.
- the output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside.
- the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).
- each device such as the processor 1001 and the memory 1002 is connected by the bus 1007 for communicating information.
- the bus 1007 may be configured by using a single bus, or may be configured by using a different bus for each device.
- the blood information estimation device 100 includes hardware such as a microprocessor, a digital signal processor (DSP: Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). It may be configured to include, and a part or all of each functional block may be realized by the hardware. For example, processor 1001 may be implemented using at least one of these hardware.
- DSP Digital Signal Processor
- ASIC Application Specific Integrated Circuit
- PLD Programmable Logic Device
- FPGA Field Programmable Gate Array
- information notification includes physical layer signaling (for example, DCI (Downlink Control Information), UCI (Uplink Control Information)), higher layer signaling (for example, RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, etc. It may be carried out by notification information (MIB (Master Information Block), SIB (System Information Block)), other signals, or a combination thereof.
- RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.
- the input / output information and the like may be stored in a specific location (for example, a memory) or may be managed using a management table. Input / output information and the like can be overwritten, updated, or added. The output information and the like may be deleted. The input information or the like may be transmitted to another device.
- the determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (Boolean: true or false), or by comparing numerical values (for example, a predetermined value). It may be done by comparison with the value).
- the notification of predetermined information (for example, the notification of "being X") is not limited to the explicit notification, but is performed implicitly (for example, the notification of the predetermined information is not performed). May be good.
- Software whether called software, firmware, middleware, microcode, hardware description language, or other names, is an instruction, instruction set, code, code segment, program code, program, subprogram, software module.
- Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, features, etc. should be broadly interpreted.
- software, instructions, information, etc. may be transmitted and received via a transmission medium.
- the software uses at least one of wired technology (coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL: Digital Subscriber Line), etc.) and wireless technology (infrared, microwave, etc.) to create a website.
- wired technology coaxial cable, optical fiber cable, twisted pair, digital subscriber line (DSL: Digital Subscriber Line), etc.
- wireless technology infrared, microwave, etc.
- the information, signals, etc. described in this disclosure may be represented using any of a variety of different techniques.
- data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may be represented by a combination of.
- a channel and a symbol may be a signal (signaling).
- the signal may be a message.
- the component carrier CC: Component Carrier
- CC Component Carrier
- the information, parameters, etc. described in the present disclosure may be expressed using an absolute value, a relative value from a predetermined value, or another corresponding information. It may be represented.
- the radio resource may be indexed.
- determining and “determining” used in this disclosure may include a wide variety of actions.
- “Judgment” and “decision” are, for example, judgment (judging), calculation (calculating), calculation (computing), processing (processing), derivation (deriving), investigation (investigating), search (looking up, search, inquiry). It may include (eg, searching in a table, database or another data structure), ascertaining as “judgment” or “decision”.
- judgment and “decision” are receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. It may include (for example, accessing data in memory) to be regarded as “judgment” or “decision”.
- judgment and “decision” are considered to be “judgment” and “decision” when the things such as solving, selecting, choosing, establishing, and comparing are regarded as “judgment” and “decision”. Can include. That is, “judgment” and “decision” may include considering some action as “judgment” and “decision”. Further, “judgment (decision)” may be read as “assuming", “expecting”, “considering” and the like.
- connection means any direct or indirect connection or connection between two or more elements and each other. It can include the presence of one or more intermediate elements between two “connected” or “combined” elements.
- the connection or connection between the elements may be physical, logical, or a combination thereof.
- connection may be read as "access”.
- the two elements use at least one of one or more wires, cables and printed electrical connections, and as some non-limiting and non-comprehensive examples, the radio frequency region.
- Electromagnetic energies with wavelengths in the microwave and light (both visible and invisible) regions, etc. can be considered to be “connected” or “coupled” to each other.
- each of the above devices may be replaced with a "part”, a “circuit”, a “device”, or the like.
- the term "A and B are different” may mean “A and B are different from each other”.
- the term may mean that "A and B are different from C”.
- Terms such as “separate” and “combined” may be interpreted in the same way as “different”.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
Claims (9)
- ユーザ端末の利用ログを取得するログ取得部と、
前記利用ログに基づいて、血液の状態の変動に関する血液情報を推定する血液情報推定部と、
を備える血液情報推定装置。 - 前記血液情報は、血圧、血糖値、中性脂肪、およびコレステロールの少なくとも一つである、
請求項1に記載の血液情報推定装置。 - 前記血液情報推定部は、
前記利用ログに加えて、ユーザの属性情報、気象情報、または生活習慣情報の少なくとも一つを考慮して、血液情報を推定する、
請求項1または2に記載の血液情報推定装置。 - 前記血液情報推定部は、
前記利用ログに基づいて、ユーザの運動量、通勤および通学の手段および時間およびパターン、ストレス、疲労度、幸福度、生活および睡眠の規則正しさ、外食頻度、塩分摂取量、カロリー摂取量の少なくとも一つを含む生活習慣情報を推定し、当該生活習慣情報に基づいて、血液情報を推定する、
請求項1~3のいずれか一項に記載の血液情報推定装置。 - 前記利用ログは、歩数、睡眠時間、体重、体温、脈拍、カメラ画像、購入店情報、購入金額、購入商品、GPS情報、基地局在圏情報、画面オンオフ情報、加速度、ジャイロ、照度、閲覧URLおよび使用アプリ情報の少なくとも一つを含む、
請求項1~4のいずれか一項に記載の血液情報推定装置。 - 前記利用ログに応じた血液情報を出力する血液情報の予測モデルを備え、
前記血液情報推定部は、前記予測モデルを利用した血液情報を推定する、
請求項1~5のいずれか一項に記載の血液情報推定装置。 - 教師データとして記憶されている学習用利用ログおよび学習用血液情報に基づいて、前記予測モデルを学習する学習部をさらに備え、
当該学習部による学習時における前記学習用血液情報は、所定期間における平均値に基づいた情報である、
請求項6に記載の血液情報推定装置。 - 前記血液情報推定部は、前記予測モデルが推定した血液情報に対して影響力のある生活習慣を特定する、
請求項6または7に記載の血液情報推定装置。 - 前記予測モデルは、所定の年代および/または性別における利用ログと血液情報とに基づいて学習され、
前記血液情報推定部は、ユーザの年代および/または性別に応じた予測モデルを適用して、血液情報を推定する、
請求項6~8のいずれか一項に記載の血液情報推定装置。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/249,320 US20230395265A1 (en) | 2020-11-19 | 2021-10-15 | Blood information estimating apparatus |
JP2022563635A JPWO2022107518A1 (ja) | 2020-11-19 | 2021-10-15 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020192432 | 2020-11-19 | ||
JP2020-192432 | 2020-11-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022107518A1 true WO2022107518A1 (ja) | 2022-05-27 |
Family
ID=81708982
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/038247 WO2022107518A1 (ja) | 2020-11-19 | 2021-10-15 | 血液情報推定装置 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20230395265A1 (ja) |
JP (1) | JPWO2022107518A1 (ja) |
WO (1) | WO2022107518A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016529606A (ja) * | 2013-07-18 | 2016-09-23 | サムスン エレクトロニクス カンパニー リミテッド | 習慣を用いた診断装置及び診断管理装置及び方法 |
JP2018191722A (ja) * | 2017-05-12 | 2018-12-06 | 株式会社Splink | サーバシステム、サーバシステムによって実行される方法及びプログラム |
WO2020040253A1 (ja) * | 2018-08-24 | 2020-02-27 | 株式会社Nttドコモ | 予測解釈装置、及び予測解釈方法 |
-
2021
- 2021-10-15 WO PCT/JP2021/038247 patent/WO2022107518A1/ja active Application Filing
- 2021-10-15 JP JP2022563635A patent/JPWO2022107518A1/ja active Pending
- 2021-10-15 US US18/249,320 patent/US20230395265A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016529606A (ja) * | 2013-07-18 | 2016-09-23 | サムスン エレクトロニクス カンパニー リミテッド | 習慣を用いた診断装置及び診断管理装置及び方法 |
JP2018191722A (ja) * | 2017-05-12 | 2018-12-06 | 株式会社Splink | サーバシステム、サーバシステムによって実行される方法及びプログラム |
WO2020040253A1 (ja) * | 2018-08-24 | 2020-02-27 | 株式会社Nttドコモ | 予測解釈装置、及び予測解釈方法 |
Also Published As
Publication number | Publication date |
---|---|
US20230395265A1 (en) | 2023-12-07 |
JPWO2022107518A1 (ja) | 2022-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Palumbo et al. | Fall risk assessment tools for elderly living in the community: can we do better? | |
Stanley et al. | The new measuring multimorbidity index predicted mortality better than Charlson and Elixhauser indices among the general population | |
Kang et al. | Utilizing home healthcare electronic health records for telehomecare patients with heart failure: a decision tree approach to detect associations with rehospitalizations | |
US20190172579A1 (en) | Contextually Grouping Sensor Channels For Healthcare Monitoring | |
JP2018041189A (ja) | 通信端末、サーバ装置、店舗推奨方法、プログラム | |
WO2021039840A1 (ja) | 需要予測装置 | |
US11514334B2 (en) | Maintaining a knowledge database based on user interactions with a user interface | |
WO2020040253A1 (ja) | 予測解釈装置、及び予測解釈方法 | |
US20180366024A1 (en) | Providing suggested behavior modifications for a correlation | |
Bhatia et al. | IoT-inspired smart home based urine infection prediction | |
Cassidy et al. | Tuberculosis diagnosis and treatment under uncertainty | |
US20220301004A1 (en) | Click rate prediction model construction device | |
WO2022107518A1 (ja) | 血液情報推定装置 | |
Massad et al. | Knowledge of cervical cancer screening among women attending urban colposcopy clinics. | |
WO2022254944A1 (ja) | データ収集解析装置 | |
JP2021077313A (ja) | 健康状態予測システム、健康状態予測方法、及び、健康状態予測システム用のプログラム | |
Levin | Use of genetic algorithms to solve biomedical problems. | |
Rataj et al. | Usefulness of measuring bilirubin levels in cord blood for predicting hyperbilirubinemia in newborns | |
Geng et al. | Segmentation of retinal image vessels based on fully convolutional network with depthwise separable convolution and channel weighting | |
JP6876295B2 (ja) | サーバ装置 | |
JP2022156706A (ja) | 傷病状態推定装置 | |
US11604831B2 (en) | Interactive device | |
WO2023218763A1 (ja) | ユーザ行動提案装置および推定モデル生成装置 | |
Mayhew et al. | Optimization of genomic classifiers for clinical deployment: evaluation of Bayesian optimization for identification of predictive models of acute infection and in-hospital mortality | |
Brink et al. | Predicting 30-day mortality using point-of-care testing; an external validation and derivation study |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21894392 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022563635 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18249320 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21894392 Country of ref document: EP Kind code of ref document: A1 |