WO2023101119A1 - 생체값의 예측 방법 - Google Patents
생체값의 예측 방법 Download PDFInfo
- Publication number
- WO2023101119A1 WO2023101119A1 PCT/KR2022/007876 KR2022007876W WO2023101119A1 WO 2023101119 A1 WO2023101119 A1 WO 2023101119A1 KR 2022007876 W KR2022007876 W KR 2022007876W WO 2023101119 A1 WO2023101119 A1 WO 2023101119A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- value
- biometric
- biometric information
- user
- prediction
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000014509 gene expression Effects 0.000 claims description 15
- 230000008929 regeneration Effects 0.000 claims description 6
- 238000011069 regeneration method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 239000008280 blood Substances 0.000 abstract description 67
- 210000004369 blood Anatomy 0.000 abstract description 67
- 238000004891 communication Methods 0.000 abstract description 36
- 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 abstract description 34
- 239000008103 glucose Substances 0.000 abstract description 34
- 238000005259 measurement Methods 0.000 abstract description 12
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 18
- 206010012601 diabetes mellitus Diseases 0.000 description 15
- 238000012937 correction Methods 0.000 description 8
- 230000002218 hypoglycaemic effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 description 4
- 230000001172 regenerating effect Effects 0.000 description 4
- 230000000630 rising effect Effects 0.000 description 4
- 210000001519 tissue Anatomy 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 3
- 238000010241 blood sampling Methods 0.000 description 3
- 210000001124 body fluid Anatomy 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000013016 Hypoglycemia Diseases 0.000 description 2
- 102000004877 Insulin Human genes 0.000 description 2
- 108090001061 Insulin Proteins 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000010839 body fluid Substances 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 201000001421 hyperglycemia Diseases 0.000 description 2
- 229940125396 insulin Drugs 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010017711 Gangrene Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000007101 Muscle Cramp Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 208000004880 Polyuria Diseases 0.000 description 1
- 208000003251 Pruritus Diseases 0.000 description 1
- 208000005392 Spasm Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 206010052428 Wound Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 210000001789 adipocyte Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009534 blood test Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003345 hyperglycaemic effect Effects 0.000 description 1
- 230000007803 itching Effects 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 210000005229 liver cell Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 206010025482 malaise Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000000663 muscle cell Anatomy 0.000 description 1
- 208000004296 neuralgia Diseases 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000496 pancreas Anatomy 0.000 description 1
- 208000028169 periodontal disease Diseases 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
- 208000016261 weight loss Diseases 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/15—Devices for taking samples of blood
- A61B5/155—Devices specially adapted for continuous or multiple sampling, e.g. at predetermined intervals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- 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
Definitions
- the present invention relates to a method for predicting a biometric value in a blood glucose measurement system, and more specifically, a predictive model is generated through a communication terminal having a small amount of memory and computation, such as a smartphone, which is always carried by a user to manage the biometric value. It is possible to predict the user's future biometric value by applying the user's biometric information to the generated predictive model, and by generating a personalized prediction model based on the user's biometric history information, it does not require the biometric information of other nearby users.
- a biometric value prediction method capable of predicting a user's future biometric value without access to a server.
- Diabetes is a chronic disease that occurs frequently in modern people, and reaches more than 2 million people, which accounts for 5% of the total population in Korea.
- Diabetes is an absolute or relatively insufficient amount of insulin produced by the pancreas due to various causes such as obesity, stress, wrong eating habits, and innate genetics. get sick and get sick
- Blood usually contains a certain concentration of glucose, and tissue cells obtain energy from it.
- Diabetes is characterized by almost no subjective symptoms in the early stages, but as the disease progresses, the symptoms characteristic of diabetes such as next, large meals, polyuria, weight loss, general malaise, itching of the skin, and prolonged wounds on the hands and feet do not heal. As the disease progresses further, complications such as vision impairment, high blood pressure, kidney disease, stroke, periodontal disease, muscle spasms and neuralgia, and gangrene appear.
- a finger prick method is used to manage blood sugar in diabetic patients.
- This blood glucose meter is helpful in managing blood sugar in diabetic patients.
- problems that are difficult to pinpoint the blood sampling type blood glucose meter needs to collect blood every time to measure blood sugar at any time throughout the day, and thus, a diabetic patient has a problem in that the burden of blood collection is great.
- a diabetic patient usually alternates between hyperglycemic and hypoglycemic states, and emergencies occur in hypoglycemic states.
- a hypoglycemic state occurs when sugar levels do not last for a long time and can lead to loss of consciousness or, in the worst case, death. Therefore, immediate detection of hypoglycemic conditions is very important for diabetic patients.
- blood sampling type blood glucose meters that intermittently measure blood sugar have obvious limitations.
- CGMS Continuous Glucose Monitoring System
- the continuous blood glucose measurement system includes a body attached unit inserted into a human body to measure blood sugar using a body fluid such as blood of a user, and a communication terminal configured to communicate with the body attached unit and display a blood glucose level measured by the body attached unit.
- the body attachment unit is partly inserted into the body for a certain period of time, for example, within 3 months (7 weeks, 15 days, 1 month, etc.) and generates a biosignal representing the user's blood sugar level from body fluid. It consists of a transmitter that transmits the received biosignal to the communication terminal in real time or periodically or upon request from the communication terminal.
- the body attachable unit generates a biosignal and transmits it to a communication terminal.
- a blood sugar management application is installed in the communication terminal to receive the biosignal from the body attachable unit, preprocessing such as removing noise from the received biosignal, and performing a biosignal of the received current value. It is output so that the user can check it through procedures such as unit calibration with blood glucose values and calibration using reference blood sugar values.
- the continuous blood glucose measurement system not only measures the user's vital signs in real time and outputs the user's blood sugar value, but also based on the user's blood sugar value history, user's activity history, meal history, and medication administration history such as insulin, etc. of future blood glucose values can be predicted.
- the prediction of the user's future blood glucose value can be performed in various ways. Representatively, a predictive model is generated based on the user's blood glucose value history and other nearby users' blood sugar value histories, and the user's current blood sugar value is based on the generated predictive model. It is possible to predict the user's future blood glucose value by applying .
- the technology for predicting the user's future blood glucose level has an effect of predicting in advance the possibility that the user may fall into hypoglycemia or hyperglycemia, and thus being able to deal with the user before reaching an actual hypoglycemia or hyperglycemia situation.
- the predictive model used for predicting future blood glucose values is created using a large amount of blood sugar history information, meal history information, activity history, etc. It requires a very large memory space for the prediction model and requires a large amount of computation to predict the future blood glucose value by applying the user's biosignal to the predictive model.
- the creation and modification of the predictive model and the prediction of the future blood glucose value using the predictive model must be performed mainly through a separate server, and the communication terminal must always communicate with the server to predict the future blood glucose value.
- the present invention is intended to solve the above-mentioned problems of the conventional methods for predicting future blood glucose values, and an object of the present invention is to use a small memory and memory through a communication terminal such as a smart phone that a user always carries in order to manage blood sugar levels.
- An object of the present invention is to provide a method for predicting a biometric value capable of predicting a user's future blood glucose level with an amount of computation.
- Another object of the present invention is to provide a method for generating a personalized predictive model for a user based on biometric history information of the user and predicting a future biometric value of the user without access to a server.
- Another object to be achieved by the present invention is to calculate the prediction error from the user's predicted biometric value and the actual biometric value, determine the expression characteristics of the prediction error, and relearn or regenerate the predictive model according to the expression characteristics of the prediction error to improve the user's performance.
- An object of the present invention is to provide a method for predicting a biometric value capable of accurately predicting a future biometric value.
- Another object to be achieved by the present invention is a predictive model personalized to a user using a first feature value extracted from preprocessed biometric information and a second feature value extracted from biometric information obtained by time-correction and unit correction of the preprocessed biometric information. It is to provide a way to accurately predict the biometric value of the user through the generated prediction model.
- a method for predicting a user's biometric value using biometric information measured from a sensor of a body attachment unit includes the steps of extracting a first characteristic value from the measured user's biometric information; Correcting the biometric information of and extracting a second feature value from the corrected biometric information, generating a feature vector value by reducing and combining the first feature value and the second feature value, and predicting the generated feature vector value It is characterized in that it includes the step of predicting the biometric value of the user by applying the model.
- the senor is characterized in that it is a sensor that is partially inserted into the user's body for a certain period of time and measures the user's biometric information.
- the method for predicting biometric information according to the present invention further includes the step of preprocessing the measured biometric information by removing noise from the measured biometric information, and the first feature value and the second feature value are obtained from the preprocessed biometric information. characterized in that it is extracted.
- the first feature value is directly extracted from the preprocessed biometric information
- the second feature value is extracted from the corrected biometric information generated by correcting the time delay and unit discrepancy of the preprocessed biometric information.
- the unit mismatch is corrected based on the preprocessed biometric information or the reference biometric value.
- the unit mismatch is characterized in that the preprocessed biometric information is corrected by assigning a weight when ascending or descending.
- unit mismatch is characterized in that it is corrected by a weight assigned according to a difference between a biometric value determined from measured biometric information and a reference biometric value.
- the biometric value prediction method comprises the steps of calculating a prediction error from the difference between the predicted biometric value at a first prediction time point and the biometric value actually measured at the first prediction time point, and a predictive model based on the prediction error. It is characterized in that it further comprises the step of determining whether to re-learn.
- the prediction error when the prediction error is greater than a threshold value or a threshold ratio, it is characterized in that it is determined to relearn the prediction model.
- prediction is made using a subsequent data set generated from user's biometric information measured up to the current point in addition to the previous data set used to generate the predictive model. It is characterized by retraining the model.
- the biometric value prediction method according to the present invention is characterized in that it further comprises a step of determining whether to regenerate the prediction model based on the expression characteristics of the prediction error during unit time.
- the expression characteristic is characterized in that at least one of the number of times the prediction error continuously exceeds the threshold value or the threshold rate during unit time and the total number of times the prediction error exceeds the threshold value or the threshold rate during the unit time.
- the biometric value prediction method according to the present invention has the following effects.
- the biometric value prediction method generates a predictive model through a communication terminal with a small amount of memory and computation, such as a smartphone that the user always carries to manage the biometric value, and uses the generated predictive model to generate the user's biometric value.
- the user's future biometric value can be predicted by applying the information.
- the biometric value prediction method generates a prediction model personalized for the user based on the user's biometric history information, so that the biometric information of other nearby users is not required and the user's future biometric value is not accessed to a server. can predict
- the biometric value prediction method calculates the prediction error from the user's predicted biometric value and the actual biometric value, determines the expression characteristics of the prediction error, and relearns or regenerates the prediction model according to the expression characteristics of the prediction error. By doing so, it is possible to accurately predict the user's future biometric value.
- the biometric value prediction method uses a first feature value extracted from preprocessed biometric information and a second feature value extracted from corrected biometric information obtained by time-correction and unit correction of the preprocessed biometric information to provide information to the user.
- a personalized predictive model By generating a personalized predictive model, it is possible to accurately predict the biometric value of the user through the generated predictive model.
- FIG. 1 is a schematic diagram showing a blood glucose measurement system according to an embodiment of the present invention.
- FIG. 2 is a functional block diagram for explaining the biometric value prediction device according to the present invention.
- FIG. 3 is a functional block diagram for explaining an example of a feature value generation unit according to the present invention.
- FIG. 4 is a functional block diagram for explaining an example of a learning unit according to the present invention.
- FIG. 5 is a flowchart for explaining a biometric value prediction method according to the present invention.
- FIG. 6 is a flowchart for explaining an example of a step of re-learning a predictive model in the present invention.
- FIG. 7 is a flowchart for explaining an example of a step of regenerating a predictive model in the present invention.
- FIG. 8 is a diagram for explaining an example of time delay correction.
- FIG. 9 is a diagram for explaining an example of a unit mismatch correction method.
- 10 is a diagram for explaining another example of a method for correcting unit mismatch.
- 11 and 12 are diagrams for explaining an example of determining whether to relearn a predictive model.
- FIG. 13 is a diagram for explaining an example of regenerating a predictive model.
- a continuous blood glucose measurement system that continuously measures biometric information indicating blood glucose value through a body attachment unit attached to the user's body for a certain period of time and transmits the measured biometric information to a communication terminal.
- the body attachable unit may measure various types of biometric information and transmit the measured biometric information to the communication terminal, which falls within the scope of the present invention.
- FIG. 1 is a schematic diagram showing a blood glucose measurement system according to an embodiment of the present invention.
- a blood glucose measurement system 1 includes a body attachment unit 10 and a communication terminal 30 .
- the body attachment unit 10 is attached to the body.
- one end of the sensor of the body attachment unit 10 is inserted into the skin to measure the user's blood sugar using bodily fluids during the use period of the sensor.
- the displayed biometric information is continuously measured.
- the communication terminal 30 is a terminal capable of receiving biometric information from the body attachment unit 10 and displaying the received biometric information to a user, for example, a smartphone, a tablet PC, or a laptop computer.
- a mobile terminal capable of communicating with may be used.
- the communication terminal 13 is not limited thereto, and may be any type of terminal as long as it has a communication function and can install programs or applications.
- the body attachment unit 10 transmits the measured biometric information to the communication terminal 30 at the request of the communication terminal 30 or at each set time, data communication between the body attachment unit 10 and the communication terminal 30
- the body attachable unit 10 and the communication terminal 30 may be connected to each other through a wired communication method such as a USB cable or the like, or through a wireless communication method such as infrared communication, NFC communication, or Bluetooth.
- the communication terminal 30 predicts the user's future biometric value based on the received biometric information and provides the predicted biometric value to the user.
- the communication terminal 30 may provide a high blood sugar or low blood sugar alarm to the user based on the predicted biological value or provide a necessary prescription to the user together with the low blood sugar or low blood sugar alarm.
- the communication terminal 30 may store the received biometric information for a certain period of time, and the communication terminal 30 may generate a predictive model using the stored biometric information.
- the communication terminal 30 monitors and compares the predicted biometric value for a certain time in the future with the actual biometric value actually measured after a certain period of time, and based on the prediction error between the predicted biometric value and the actual biometric value or the prediction error. Predictive models created based on expression features can be retrained or recreated.
- FIG. 2 is a functional block diagram for explaining the biometric value prediction device according to the present invention.
- the biometric value prediction device can be implemented in a communication terminal. Looking more specifically with reference to FIG. Stores the received biometric information.
- the storage unit 130 may store the received biometric information by mapping it to the reception time.
- the biometric value determiner 180 determines the user's biometric value from the received biometric information, outputs the determined biometric value to the user, or maps the received biometric value to the storage unit 130 and stores it.
- biometric information can be measured through a sensor inserted into the user's body for a certain period of time.
- biometric information it may be biometric information representing the user's blood sugar information, and the biometric value is blood sugar determined from the biometric information. can be a value
- the biometric value determined from the biometric information may be stored in the storage unit 130 together with the biometric information received from the body attachable unit. Creates a feature value vector used for
- the prediction unit 170 uses the prediction model stored in the storage unit 130 to determine the predicted biometric value after a certain time based on the current point in time.
- the prediction unit 170 converts the generated feature value vector to the prediction model. It is applied to determine the predicted biometric value.
- the predicted biometric value is a predicted biometric value that the user will have after a certain period of time has elapsed from the current point in time.
- the biometric value of the user is predicted in advance after a certain period of time has elapsed using the predicted biometric value, and the user is alarmed based on the predicted biometric value. or provide necessary prescriptions.
- a low blood sugar alarm may be provided to the user or a prescription to eat food may be provided.
- the storage unit 130 stores the predicted biological value determined by the prediction unit 170 and the actual biological value determined by the biological value determining unit 180.
- the learning unit 190 stores the actual biological value determined after a certain period of time and The user's predicted biometric values predicted before time are monitored and compared with each other.
- the learning unit 190 relearns the prediction model stored in the storage unit 130 based on the size or ratio of the prediction error between the predicted biometric value and the actual biometric value, or uses the predictive model based on the expression characteristics of the prediction error.
- a new predictive model may be regenerated by learning again from the beginning, and the predictive model stored in the storage unit 130 may be updated with the generated new predictive model.
- FIG. 3 is a functional block diagram for explaining an example of a feature value generation unit according to the present invention.
- the pre-processing unit 151 removes or reduces noise from the biometric information received through the transceiver.
- Biometric information measured through the body attachment unit or received from the body attachment unit may include noise.
- the sensor since a sensor of the body attachment unit is partially inserted into the human body, the sensor may move whenever the person moves, and as the sensor moves, biometric information data measured by the body attachment unit may include noise.
- biometric information when transmitted from the body-attached unit to the communication terminal, it may be affected by ambient electromagnetic waves, and as a result, noise may be included in biometric information received from the communication terminal.
- the pre-processor 151 performs outlier processing and filtering on the received biometric information or performs low-pass filtering on the biometric information for which outlier processing has been completed.
- the first feature value extractor 153 extracts a first feature value from the preprocessed biometric information
- the second feature value extractor 157 extracts a second feature value from the calibrated biometric information corrected by the corrector 155. do.
- the preprocessed biometric information received from the body attachment unit is current value information that varies differently according to the user's biometric value
- the calibrated biometric information is the biometric information preprocessed by the calibration unit 155 that is time-delay corrected or unit discrepancy corrected. means information.
- the calibration unit 155 calibrates the preprocessed biometric information and provides the calibrated biometric information to the second feature value extraction unit 157.
- the calibration unit corrects the time delay of the preprocessed biometric information or the biometric information of current value. is calibrated in units of biometric values, for example, units of blood glucose values.
- the feature vector value generation unit 159 generates a feature vector value by simply combining the first feature value and the second feature value or by reducing and combining the first feature value and the second feature value in a resource reduction method.
- FIG. 4 is a functional block diagram for explaining an example of a learning unit according to the present invention.
- the prediction error calculation unit 191 monitors the actual biometric value determined after a certain period of time and the predicted biometric value of the user predicted in advance before a certain amount of time, and compares them with the actual biometric value and predicted biometric value. Calculate the prediction error between biological values. For example, a predicted biometric value after time t has elapsed based on the current point in time is determined from the feature vector value, and a prediction error between actual biometric values determined using biometric information after actual time t has elapsed is calculated.
- the prediction error feature determiner 195 is configured to display prediction errors such as the number of times the prediction error exceeds a threshold value or threshold ratio during unit time or the number of times the prediction error consecutively exceeds the threshold value or threshold ratio during unit time. judge the characteristics
- the condition determination unit 193 determines the re-learning condition based on whether the prediction error exceeds a set threshold or whether the prediction error ratio to the actual biological value or the predicted biometric value exceeds a set threshold ratio, or the occurrence of prediction errors. Based on the feature, it is determined whether the regeneration condition of the predictive model is satisfied.
- the re-learning unit 197 re-learns the predictive model stored in the storage unit when the re-learning condition is satisfied, and updates the predictive model with the re-learned predictive model.
- a predictive model stored in the storage unit is newly generated and the predictive model is updated with the newly generated predictive model.
- FIG. 5 is a flowchart for explaining a biometric value prediction method according to the present invention.
- the user's biometric information is received (S110).
- the user's biometric information may be received from a body attachment unit that is attached to the user's body for a certain period of time and continuously measures the user's biometric information.
- the communication terminal pre-processes the received biometric information (S130). Looking at the pre-processing process in more detail, data out of a predetermined range is found among received biometric information for singular value processing and filtering, and the corresponding biometric information is processed. At this time, if it is determined that the biometric information has a singular value, the corresponding biometric information may be removed and processed. However, it is not limited thereto, and biometric information having a singular value may be corrected and used if necessary. Low-pass filtering may be performed on the biometric information processed with the singular value. The low-band filtering may remove components corresponding to the high-band and leave only biometric information corresponding to the low-band.
- An average value for the low-pass filtered biometric information may be calculated and processed using the low-pass filtered biometric information, and a cut average value may be used. Pretreatment can be performed in various ways depending on the field to which the present invention is applied, which falls within the scope of the present invention.
- a first feature value is extracted from the preprocessed biometric information (S140).
- the pre-processed biometric information may be a user's biometric value measured by the body attachment unit, for example, a current value indicating a blood sugar level.
- the first feature value is a feature value such as difference, slope, deviation, average, rms value, sharpness, etc. of biometric information extracted from statistical techniques, or a feature extracted by frequency domain analysis of biometric information such as Fourier transform or wavelet transform. is the value
- calibrated biometric information is generated by correcting the preprocessed biometric information (S150), and a second characteristic value is extracted from the calibrated biometric information (S150).
- a second characteristic value is extracted from the calibrated biometric information (S150).
- time delay or unit mismatch included in the preprocessed biometric information may be corrected.
- a time delay occurs between the time when the user's biometric information is actually measured by the body attachment unit and the time point when the user's biometric information is received by the communication terminal. It may occur according to the physical structure until it is measured and generated, or it may occur due to the computation time required to generate biometric information.
- the preprocessed biometric information is current value information representing the user's biometric value, and since the biometric value is not self-contained, the unit discrepancy must be corrected from the current value to the actual user's biometric value.
- Unit discrepancy can be corrected using a reference biometric value measured through a blood sampling type biometric value measuring device using a separate sensor strip (blood test strip) and collected blood. For example, if the current value of the biometric information is 10nA and the reference biometric value measured at this time is 100mg/dL, the calibration slope (A) is set to 10, and then the current value of the biometric information is multiplied by the slope to determine the user's biometric value. .
- the unit mismatch when calibrating the unit mismatch, can be corrected by assigning a weight according to whether the biometric value is increasing or decreasing or how much the difference is between the measured biometric value and the reference biometric value. .
- a second feature value is extracted using the calibrated biometric information (S160).
- the second feature value is a feature value such as difference, slope, deviation, average, rms value, sharpness, etc. of calibrated biometric information extracted from a statistical technique, or extracted by frequency domain analysis of calibrated biometric information such as Fourier transform or wavelet transform is a feature value.
- a feature vector value is generated from the first feature value and the second feature value by simple combining or resource reduction of the first feature value and the second feature value (S170).
- the generated feature vector value is applied to the predictive model to generate a predicted biometric value after a certain time (S190).
- the predictive model is used to generate predicted biological values after a certain time by using feature vector values. For example, the number of components constituting the feature vector value (x) generated at regular intervals is 10, and each feature vector value If the label y for is the predicted biological value after a certain time, the input (x) and label (y) of each feature vector value are expressed as in Equation (1) below.
- the feature vector value generated from feature value 1 and feature value 2 into the predictive model the predicted biological value y' after a certain time is output.
- the predictive model uses the user's feature vector as training data, and machine learning such as SVM (Support Vector Machine) and GMM (Gaussian Mixture Model), deep learning such as CNN (Convolution Neutal Network) and RNN (Recurrent Neural Network) , reinforcement learning such as model-free RL and model-based RL, and deep reinforcement learning such as DQN (Deep Q Network).
- machine learning such as SVM (Support Vector Machine) and GMM (Gaussian Mixture Model)
- deep learning such as CNN (Convolution Neutal Network) and RNN (Recurrent Neural Network)
- reinforcement learning such as model-free RL and model-based RL
- DQN Deep reinforcement learning
- the first feature value and the second feature value have very many features. If a predictive model is to be generated with such data, the learning rate is slow and the performance is likely to be poor because the dimension of the data is large. To this end, a predictive model may be generated by simply combining the first feature value and the second feature value, or by selecting or reducing a feature among them. Projection and manifold learning, which are methods of reducing the dimension of data, ) and principal component analysis (PCA), which is a representative dimensionality reduction algorithm, or feature selection algorithms such as Lasso, etc., may be used. Various well-known techniques may be used to generate feature vector values from the first feature value and the second feature value, and a detailed description thereof will be omitted.
- PCA principal component analysis
- the present invention by generating a predictive model using both the first feature value and the second feature value generated from the user's biometric information, it is possible to accurately predict the user's biometric value personalized to the user without using the data of other nearby users. It is possible to generate a predictive model with the first feature value and the second feature value, and apply the feature vector value generated from the first feature value and the second feature value to the predictive model to have an effect of accurately predicting the biometric value of the user.
- FIG. 6 is a flowchart for explaining an example of a step of re-learning a predictive model in the present invention.
- the prediction error is obtained from the difference between the predicted biometric value at the first prediction time point generated using the feature vector value and the actual biometric value measured using the actual biometric value at the first predicted time point. Calculate (S211).
- the re-learning requirement is determined to be satisfied when the prediction error exceeds the threshold value or the threshold ratio, or the prediction error exceeds the threshold value or the threshold ratio and the average value of the prediction errors for a first predetermined time is the threshold average value. It may be determined that it is satisfied, or it may be determined that it is satisfied when the prediction error exceeds the threshold value or the threshold ratio and the prediction error continuously exceeds the threshold value or the threshold ratio for a second time thereafter.
- the predictive model is re-learned and the previously used predictive model is updated with the re-learned predictive model (S217).
- the re-learning of the predictive model is characterized by using a later data set generated from the user's biometric information measured up to the current point in time in addition to the previous data set used to generate the predictive model stored in the storage unit.
- the data set is characterized in that it is a feature vector value generated from the first feature value and the second feature value.
- FIG. 7 is a flowchart for explaining an example of a step of regenerating a predictive model in the present invention.
- the expression characteristics of the prediction error are determined (S231).
- the expression characteristics of the prediction error are the average value of the prediction error during unit time, the number of times that the prediction error exceeds the threshold value or threshold rate during unit time, the number of consecutive times that the prediction error exceeds the threshold value or threshold rate during unit time, and the unit
- the time-to-prediction error may be a threshold or a ratio of time exceeding a threshold ratio, and the like.
- the regeneration condition of the predictive model is when the average value of prediction errors during unit time exceeds a first threshold average value, the number of prediction errors exceeding the threshold value or threshold ratio during unit time exceeds the first threshold number of times, or during unit time The number of times that the prediction error consecutively exceeds the threshold value or the threshold ratio exceeds the second threshold number of times, or the ratio of time in which the prediction error exceeds the threshold value or the threshold ratio with respect to unit time exceeds the first threshold ratio, or the like; It may be a combination of these.
- the predictive model is regenerated using the training data, and the previously used predictive model is updated with the regenerated predictive model (S235).
- the regeneration of the predictive model is characterized by using a later data set generated from the user's biometric information measured up to the current point in time in addition to the previous data set used to generate the predictive model stored in the storage unit.
- the data set is characterized in that it is a feature vector value generated from the first feature value and the second feature value.
- FIG. 8 is a diagram for explaining an example of time delay correction.
- FIG. 9 is a diagram for explaining an example of a unit mismatch correction method.
- the biometric information received from the body-attached unit in the continuous blood glucose measurement system is stored at predetermined time intervals (t 1 , t 2 , t 3 , t 4 %), for example, 12 Hourly, every 24 hours, unit discrepancies should be corrected using reference biometric values.
- the unit discrepancy When calibrating the unit discrepancy, it is possible to correct it by assigning a weight considering whether the biometric information (indicated by a solid line) is rising or falling, and multiplying the assigned weight by the calibration slope (A).
- weights when the biometric information is ascending, weights may be allocated in inverse proportion to the ascending speed, and when the biometric information is descending, weights may be allocated in proportion to the descending speed.
- the weight when the biometric information is rising, the weight may be assigned a low value in inverse proportion to the rising speed (lower values such as 0.90, 0.80, 0.70, etc. as the rising speed increases), and when the biometric information is falling, the weight is It can be assigned a higher value proportional to the rate of descent (the higher the rate of descent, the higher the value is 1.10, 1.20, 1.30).
- 10 is a diagram for explaining another example of a method for correcting unit mismatch.
- the biometric information received from the body-attached unit in the continuous blood glucose measurement system is stored at predetermined time intervals (t 1 , t 2 , t 3 , t 4 %), for example, 12 Hourly, every 24 hours, unit discrepancies should be corrected using reference biometric values.
- unit mismatch When unit mismatch is corrected, it may be corrected based on the difference between the reference biometric value and the measured biometric value (indicated by a solid line). Based on the difference between the reference biometric value and the measured biometric value, a weight is assigned to reduce the difference (for example, a weight is calculated and assigned so that the calibration slope has an average value of the reference biometric value and the measured biometric value), or A weight may be assigned to reduce the difference only when the difference between the measured biological values is out of a critical range.
- 11 and 12 are diagrams for explaining an example of determining whether to relearn a predictive model.
- the prediction error (d 1 ) between the predicted biometric value predicted at the first prediction time point (t 1 ) and the measured biometric value actually measured at the first predicted time point is the threshold value or threshold range.
- the prediction error (d 2 ) between the predicted biometric value predicted at the second prediction time point (t 2 ) and the measured biometric value actually measured at the second prediction time point (t 2 ) is out of the threshold value or threshold range, the first predicted time point
- the predictive model may be re-learned at the time point and the second prediction time point, respectively.
- FIG. 13 is a diagram for explaining an example of regenerating a predictive model.
- the total number of prediction errors between the predicted biometric value predicted for a certain unit time (t D ) and the measured biometric value actually measured at the corresponding time exceeds the threshold value or threshold range is the threshold number of times.
- the prediction error between the predicted biometric value predicted for a certain unit time (t D ) and the measured biometric value actually measured at the corresponding time exceeds the threshold value or the number of consecutive deviations from the threshold range, or When all of these combinations are satisfied, the predictive model may be regenerated.
- the above-described embodiments of the present invention can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium.
- the computer-readable recording medium includes a magnetic storage medium (eg, ROM, floppy disk, hard disk, etc.), an optical reading medium (eg, CD-ROM, DVD, etc.), and a carrier wave (eg, Internet transmission through).
- a magnetic storage medium eg, ROM, floppy disk, hard disk, etc.
- an optical reading medium eg, CD-ROM, DVD, etc.
- a carrier wave eg, Internet transmission through
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Optics & Photonics (AREA)
- Hematology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Emergency Medicine (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
Claims (12)
- 센서로부터 측정한 생체 정보를 이용하여 사용자의 생체값을 예측하는 방법에 있어서,측정한 사용자의 생체 정보로부터 제1 특징값을 추출하는 단계;측정한 사용자의 생체 정보를 보정하고 보정한 생체 정보로부터 제2 특징값을 추출하는 단계;상기 제1 특징값과 상기 제2 특징값을 축소 결합하여 특징 벡터값을 생성하는 단계; 및생성한 특징 벡터값을 예측 모델에 적용하여 사용자의 생체값을 예측하는 단계를 포함하는 것을 특징으로 하는 생체값의 예측 방법.
- 제 1 항에 있어서,상기 센서는 일정기간 동안 사용자의 신체에 일부 삽입되어 사용자의 생체 정보를 연속하여 측정하는 센서인 것을 특징으로 하는 생체값의 예측 방법.
- 제 2 항에 있어서, 상기 생체 정보의 예측 방법은측정한 생체 정보에서 노이즈를 제거하여 측정한 생체 정보를 전처리하는 단계를 더 포함하며,상기 제1 특징값과 상기 제2 특징값은 전처리된 생체 정보로부터 추출되는 것을 특징으로 하는 생체값의 예측 방법.
- 제 3 항에 있어서,상기 제1 특징값은 전처리된 생체 정보로부터 직접 추출되고,상기 제2 특징값은 전처리된 생체 정보를 시간 지연과 단위 불일치를 보정하여 생성되는 보정 생체 정보로부터 추출되는 것을 특징으로 하는 생체값의 예측 방법.
- 제 4 항에 있어서, 상기 단위 불일치는전처리된 생체 정보 또는 기준 생체값에 기초하여 보정되는 것을 특징으로 하는 생체값의 예측 방법.
- 제 5 항에 있어서, 상기 단위 불일치는상기 전처리된 생체 정보가 상승 또는 하강시 가중치를 부여하여 보정되는 것을 특징으로 하는 생체값의 예측 방법.
- 제 5 항에 있어서, 상기 단위 불일치는측정한 생체 정보로부터 판단된 생체값와 기준 생체값의 차이에 따라 할당되는 가중치에 의해 보정되는 것을 특징으로 하는 생체값의 예측 방법.
- 제 4 항에 있어서, 상기 생체값의 예측 방법은제1 예측 시점의 예측된 생체값와 상기 제1 예측 시점에 실제 측정한 생체값의 차이로부터 예측 오차를 계산하는 단계; 및상기 예측 오차에 기초하여 예측 모델을 재학습할지 결정하는 단계를 더 포함하는 것을 특징으로 하는 생체값의 예측 방법.
- 제 8 항에 있어서,상기 예측 오차가 임계값 또는 임계 비율보다 큰 경우 예측 모델을 재학습하는 것으로 결정하는 것을 특징으로 하는 생체값의 예측 방법.
- 제 8 항에 있어서, 상기 생체값의 예측 방법은단위 시간 동안 예측 오차의 발현 특징에 기초하여 상기 예측 모델을 재생성할지 결정하는 단계를 더 포함하는 것을 특징으로 하는 생체값의 예측 방법.
- 제 10 항에 있어서, 상기 발현 특징은상기 단위 시간 동안 상기 예측 오차가 임계값 또는 임계 비율을 연속하여 초과하는 횟수 및 상기 단위 시간 동안 상기 예측 오차가 임계값 또는 임계 비율을 초과하는 전체 횟수 중 적어도 어느 하나인 것을 특징으로 하는 생체값의 예측 방법.
- 제 8 항에 있어서, 상기 생체값의 예측 방법에서예측 모델의 재학습 또는 예측 모델의 재생성은 상기 예측 모델을 생성하는데 이용한 이전 데이터 세트 이외에 현재 시점까지 측정한 사용자의 생체 정보로부터 생성되는 이후 데이터 세트를 이용하는 것을 특징으로 하는 생체값의 예측 방법.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2022401221A AU2022401221A1 (en) | 2021-12-03 | 2022-06-02 | Biometric value prediction method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210171649A KR20230083550A (ko) | 2021-12-03 | 2021-12-03 | 생체값의 예측 방법 |
KR10-2021-0171649 | 2021-12-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023101119A1 true WO2023101119A1 (ko) | 2023-06-08 |
Family
ID=86612432
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/007876 WO2023101119A1 (ko) | 2021-12-03 | 2022-06-02 | 생체값의 예측 방법 |
Country Status (3)
Country | Link |
---|---|
KR (1) | KR20230083550A (ko) |
AU (1) | AU2022401221A1 (ko) |
WO (1) | WO2023101119A1 (ko) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050037903A (ko) * | 2003-10-20 | 2005-04-25 | 케이제이헬스케어 주식회사 | 혈당측정 기능을 갖는 이동통신 단말기와, 이를 이용한검진 시스템 및 방법 |
KR20120080270A (ko) * | 2011-01-07 | 2012-07-17 | 동명대학교산학협력단 | 지능형 생체신호 처리시스템 및 그가 적용된 휴대용 생체신호 처리기 |
KR20210012791A (ko) * | 2019-07-26 | 2021-02-03 | 한국전자통신연구원 | 기계학습 기반 예측 모델 재학습 장치 및 그 방법 |
KR20210015045A (ko) * | 2019-07-31 | 2021-02-10 | 서울대학교산학협력단 | 혈당측정장치 및 이를 이용하는 혈당측정시스템 |
KR20210107428A (ko) * | 2020-02-24 | 2021-09-01 | 주식회사 에이티센스 | 기계 학습 기반의 심장질환 예측 모델 구축 장치, 심장질환 예측 모델 구축 방법, 기계 학습 기반으로 구축된 모델을 이용하여 심장질환 여부를 출력하는 심장질환 측정 장치, 방법 및 상기 방법들을 실행하기 위한 컴퓨터 프로그램들 |
-
2021
- 2021-12-03 KR KR1020210171649A patent/KR20230083550A/ko not_active Application Discontinuation
-
2022
- 2022-06-02 WO PCT/KR2022/007876 patent/WO2023101119A1/ko active Application Filing
- 2022-06-02 AU AU2022401221A patent/AU2022401221A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20050037903A (ko) * | 2003-10-20 | 2005-04-25 | 케이제이헬스케어 주식회사 | 혈당측정 기능을 갖는 이동통신 단말기와, 이를 이용한검진 시스템 및 방법 |
KR20120080270A (ko) * | 2011-01-07 | 2012-07-17 | 동명대학교산학협력단 | 지능형 생체신호 처리시스템 및 그가 적용된 휴대용 생체신호 처리기 |
KR20210012791A (ko) * | 2019-07-26 | 2021-02-03 | 한국전자통신연구원 | 기계학습 기반 예측 모델 재학습 장치 및 그 방법 |
KR20210015045A (ko) * | 2019-07-31 | 2021-02-10 | 서울대학교산학협력단 | 혈당측정장치 및 이를 이용하는 혈당측정시스템 |
KR20210107428A (ko) * | 2020-02-24 | 2021-09-01 | 주식회사 에이티센스 | 기계 학습 기반의 심장질환 예측 모델 구축 장치, 심장질환 예측 모델 구축 방법, 기계 학습 기반으로 구축된 모델을 이용하여 심장질환 여부를 출력하는 심장질환 측정 장치, 방법 및 상기 방법들을 실행하기 위한 컴퓨터 프로그램들 |
Also Published As
Publication number | Publication date |
---|---|
KR20230083550A (ko) | 2023-06-12 |
AU2022401221A1 (en) | 2024-05-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021107335A1 (ko) | 연속혈당측정시스템에서 혈당값을 교정하는 방법 | |
US11937920B2 (en) | Cloud big data-based intelligent real-time dynamic blood glucose monitoring system and method | |
WO2005110029A2 (en) | Method and apparatus for real time predictive modeling for chronically ill patients | |
WO2021015389A1 (ko) | 연속 혈당 측정 시스템에서 생체 정보를 분실없이 송수신하는 방법 | |
EP4098194A1 (en) | Method for calculating calibration sensitivity of sensor for insertion into body | |
CN111568445B (zh) | 一种基于谵妄动态预测模型的谵妄风险监测方法及系统 | |
CN108847284B (zh) | 人体生物年龄测算装置及系统 | |
WO2020111787A1 (en) | Method for providing recommendations for maintaining a healthy lifestyle basing on daily activity parameters of user, automatically tracked in real time, and corresponding system | |
WO2022114793A1 (ko) | 빅데이터 기반의 당뇨병 발병 위험도 예측 시스템, 예측 방법, 및 프로그램 | |
CN112437629A (zh) | 确定被监测对象的生命体征的可靠性 | |
CN111000569A (zh) | 一种异常血糖智能认知的监护系统 | |
WO2023101119A1 (ko) | 생체값의 예측 방법 | |
CN117133464B (zh) | 一种老年人健康智能监测系统及监测方法 | |
WO2022114791A1 (ko) | 빅데이터 기반의 질환 발병 위험도 예측 시스템, 예측 방법, 및 프로그램 | |
CN116188946B (zh) | 一种基于神经网络的血糖浓度预测系统 | |
WO2022065569A1 (ko) | 혈당 조절 시스템 및 방법 | |
JP2020529234A (ja) | 嚥下障害分類モデルの信号品質を判定するための方法及びデバイス | |
WO2023017921A1 (ko) | 연속혈당 데이터를 이용한 당 관리 장치 및 그 방법 | |
CN112133398A (zh) | 血糖管控方法、系统及存储介质 | |
Reeves et al. | Novel technologies for detection and prevention of diabetic foot ulcers | |
WO2023136574A1 (ko) | 연속생체 정보 측정 시스템에서 생체 신호를 교정하는 방법 | |
CN114557690B (zh) | 一种用于连续葡萄糖监测的校准系统及方法 | |
WO2022124790A1 (en) | Systems and methods for atrial fibrillation burden estimation, notification and management in daily free-living scenarios | |
CN108335750B (zh) | 动态分析血糖值的方法、系统与计算机存储介质 | |
CN108968975A (zh) | 基于人工智能的血糖值的测量方法及设备 |
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: 22901480 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: AU2022401221 Country of ref document: AU |
|
ENP | Entry into the national phase |
Ref document number: 2022901480 Country of ref document: EP Effective date: 20240429 |
|
ENP | Entry into the national phase |
Ref document number: 2022401221 Country of ref document: AU Date of ref document: 20220602 Kind code of ref document: A |