CN110151192A - A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning - Google Patents
A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning Download PDFInfo
- Publication number
- CN110151192A CN110151192A CN201910513061.0A CN201910513061A CN110151192A CN 110151192 A CN110151192 A CN 110151192A CN 201910513061 A CN201910513061 A CN 201910513061A CN 110151192 A CN110151192 A CN 110151192A
- Authority
- CN
- China
- Prior art keywords
- data
- blood sugar
- blood glucose
- cloud server
- patient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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 or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or 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
- A61B5/48—Other medical applications
- A61B5/4848—Monitoring or testing the effects of treatment, e.g. of medication
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient; User input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Emergency Medicine (AREA)
- Optics & Photonics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
本发明涉及一种用于血糖监控与预警的辅助医疗系统，包括：多通道临床血糖数据采集装置、云服务器和多个移动终端；所述临床血糖数据采集装置与所述云服务器通信连接，并能够将采集到的血糖数据发送给所述云服务器；所述云服务器分别与所述多个移动终端通信连接；所述云服务器能够针对获得的血糖数据进行血糖数据预测，获得血糖预测结果数据；多个移动终端能够从所述云服务器处获取血糖预测结果数据。本发明提供的辅助医疗系统，通过多通道传感器的数据采集不仅能够使患者看到自己的实时血糖值与30分钟血糖动态预报，而且还能够协助医生监控区域内多个患者的血糖实时信息与预测信息，并根据血糖监测数据与预测血糖值，实现异常血糖状态的预警功能。
The present invention relates to an auxiliary medical system for blood sugar monitoring and early warning, comprising: a multi-channel clinical blood sugar data collection device, a cloud server and a plurality of mobile terminals; the clinical blood sugar data collection device communicates with the cloud server, and The collected blood glucose data can be sent to the cloud server; the cloud server is respectively connected to the plurality of mobile terminals in communication; the cloud server can perform blood glucose data prediction on the obtained blood glucose data, and obtain blood glucose prediction result data; A plurality of mobile terminals can acquire blood glucose prediction result data from the cloud server. The auxiliary medical system provided by the present invention can not only enable patients to see their own real-time blood sugar level and 30-minute dynamic forecast of blood sugar through the data collection of multi-channel sensors, but also can assist doctors in monitoring real-time blood sugar information and prediction of multiple patients in the area Information, and based on blood glucose monitoring data and predicted blood glucose values, it realizes the early warning function of abnormal blood glucose status.
Description
Technical Field
The invention belongs to the technical field of auxiliary medical treatment, and particularly relates to an auxiliary medical treatment system for blood sugar monitoring and early warning and a using method thereof.
Background
With the rapid development of society, the life rhythm of people is faster and faster, and the incidence of diabetes of people in China is gradually increased. The main cause of diabetes is insulin deficiency or abnormal insulin receptor in human body, which leads to the blood sugar content being higher than the maximum filtering capacity of human body, the main manifestation of the diabetes is hyperglycemia, and the diabetes is divided into type I diabetes and type II diabetes according to different pathogenesis.
Currently, the insulin pump of Meidunli continuously carries out technical innovation by utilizing the strong market advantage, has become the outstanding one in the insulin pump market and occupies most of the insulin market. The insulin pump newly proposed by Meidun dynasty can flexibly adjust the needed insulin basal amount according to the self needs of a patient, and is a semi-closed loop type insulin pump. However, since the mayonnaise pump has no function of predicting blood glucose, there is a delay in administration and it is expensive. In addition, every insulin pump of force of meidun can only be directed against a patient and carry out the output of dosing, and the doctor can only see the undulant condition of blood glucose value of a patient, can't see a plurality of patients ' blood glucose data simultaneously, has increaseed doctor's the work degree of difficulty, consequently needs to provide one kind and can assist the doctor to carry out blood glucose monitoring and unusual early warning system to a plurality of patients in real time.
Although the change of blood sugar has a certain rule, the blood sugar fluctuation is influenced by many aspects, such as the blood sugar of a human body rises after eating, exercise or over-stress and anxiety, and the blood sugar of the human body drops, so that the blood sugar data is difficult to stabilize near a certain average value. The insulin has time lag when acting, and after the patient injects the insulin, the insulin usually acts after 15 to 30 minutes through metabolic cycle, thereby providing a difficult problem for accurate administration in clinic. Therefore, the solution to the prediction enables the doctor to predict the blood glucose fluctuation of the patient, helps the doctor to determine the insulin dosage better, and can expand the scenes used in blood glucose control in the aspect of blood glucose prediction.
Disclosure of Invention
Technical problem to be solved
Aiming at the existing technical problems, the invention provides an auxiliary medical system for monitoring and early warning of blood sugar and a using method thereof, which can not only enable a patient to see the own real-time blood sugar value and the dynamic forecast of blood sugar within 30 minutes, but also assist the doctor to monitor the real-time blood sugar information and the forecast information of a plurality of patients in an area and realize the function of early warning of high/low blood sugar according to the forecast blood sugar value by collecting information of a plurality of sensors through multiple channels.
(II) technical scheme
In order to achieve the purpose, the invention adopts the main technical scheme that:
an assisted medical system for blood glucose monitoring and early warning, comprising: the system comprises a multi-channel clinical blood glucose data acquisition device, a cloud server and a plurality of mobile terminals;
the multichannel clinical blood glucose data acquisition device is in communication connection with the cloud server and can send acquired blood glucose data to the cloud server;
the cloud server is in communication connection with the plurality of mobile terminals respectively;
the cloud server can predict blood sugar data according to the obtained blood sugar data to obtain blood sugar prediction result data;
the plurality of mobile terminals can obtain blood glucose prediction result data from the cloud server.
Preferably, the clinical blood glucose data acquisition device comprises: a continuous blood glucose monitoring sensor CGM and an insulin infusion information acquisition device sensor CSII;
the insulin infusion information collection device sensor CSII is capable of sending patient insulin injection data to the cloud server;
the continuous blood glucose monitoring sensor CGM is capable of transmitting blood glucose data of a patient to the cloud server.
Preferably, the multichannel clinical blood glucose data acquisition device is a UVA/Padova simulation platform;
the UVA/Padova simulation platform can generate virtual blood glucose data for the cloud server.
Preferably, the plurality of mobile terminals include at least: a patient client for use by a patient and a monitor interface information system client for use by a doctor.
Preferably, the cloud server includes at least: the system comprises a computing module and a cloud storage database;
the computing module can process the obtained blood sugar data into blood sugar prediction result data and store the blood sugar prediction result data into the cloud storage database.
The technical scheme also provides a use method of the medical system based on the above, which comprises the following steps:
the clinical blood sugar data acquisition device sends acquired or simulated blood sugar data of the patient to a cloud storage database;
the cloud storage database sends the received blood glucose data of the patient to the computing module;
the computing module carries out blood sugar prediction by utilizing the received blood sugar data of the patient to obtain blood sugar prediction result data after 30 minutes and feeds the blood sugar prediction result data back to the cloud storage database;
feeding back data information in the cloud storage database to the plurality of mobile terminals;
the data information at least comprises: patient blood glucose data and blood glucose prediction outcome data.
Preferably, the step of: the calculation module uses the received blood sugar data of the patient to predict the blood sugar, and further comprises the following substeps:
s1, preprocessing blood sugar data of the patient;
s2, decomposing the preprocessed blood sugar data by using a variational mode method VMD to obtain a group of sub-modes which are more stable than the original data;
and S3, establishing a GPR model for each sub-mode to predict the sub-modes, obtaining a predicted value of each sub-mode, and fusing and superposing all the obtained predicted values to obtain final blood sugar prediction result data.
Preferably, the step S2 further includes the following sub-steps:
s201, aiming at each sub-mode ukThe single-side spectrum is obtained by calculating an analytic signal related to the Hilbert transform, and the method comprises the following steps:
where H (t) is the modal resolution signal, δ (t) is the Dirac distribution, t is the sampling time point, { u {k}＝{u1，...，uK}；
S202, aiming at each sub-mode, by aiming at the center frequency omegakCarrying out exponential term aliasing, and modulating each sub-mode to a corresponding fundamental frequency band, wherein the formula is as follows:
in the formulaIs omegakVector description on the complex plane, { omega }k}＝{ω1，...，ωK}；
S203, estimating the bandwidth of each sub-mode, and calculating the square L of the gradient2Norm, and the constraint condition variation problem corresponding to the position is:
s204, introducing an augmented Lagrange function, obtaining a non-constrained problem by using a secondary penalty function term and a Lagrange multiplier, and finally solving the problem by the following formula:
wherein,is a penalty term and λ is the lagrange multiplier.
Preferably, the step S2 further includes:
a1, by alternate updatingAndto find the optimal solution, the convergence condition is:
wherein epsilon represents a convergence condition in which,representing the fourier transform, n is the number of iterations;
a2, obtaining ukAnd ω 1kFunction:
wherein,representing the current amount of the remaining,representing the center of gravity of the power spectrum of the current mode function.
Preferably, the kernel function of the GPR model in step S3 is:
wherein m is the length of the blood glucose input vector,is an output scale parameter;is the variance of the data.
(III) advantageous effects
The invention has the beneficial effects that: the invention provides an auxiliary medical system for blood sugar monitoring and early warning and a using method thereof, which have the following beneficial effects:
(1) the sensor information of a plurality of patients can be acquired by utilizing multiple channels, so that not only can the patients see the own real-time blood sugar values and the 30-minute dynamic blood sugar forecast, but also the real-time blood sugar information and the forecast information of the plurality of patients in the doctor monitoring area can be assisted.
(2) The system can provide blood sugar abnormity early warning function for the patient, and the patient can compensate for meals or take corresponding measures according to the condition.
(3) The VMD-GPR prediction model adopted by the invention can accurately predict the change trend of blood sugar, and is beneficial to blood sugar control.
Drawings
FIG. 1 is a schematic diagram of an auxiliary medical system for blood glucose monitoring and early warning according to the present invention;
FIG. 2 is a schematic diagram of a VMD-GPR algorithm in a method for using the auxiliary medical system for blood sugar monitoring and early warning provided by the invention;
FIG. 3 is a schematic diagram of an algorithm flow of a VMD-GPR algorithm in a method for using the auxiliary medical system for blood sugar monitoring and early warning provided by the invention;
FIG. 4 is a schematic diagram illustrating comparison between actual blood glucose values and predicted blood glucose outputs in a method of using an auxiliary medical system for blood glucose monitoring and early warning according to the present invention;
FIG. 5 is a diagram illustrating the effect of a predicted part of a method for using an assistant medical system for blood glucose monitoring and early warning according to the present invention;
FIG. 6 is a simulation diagram of prediction and early warning in a method of using an auxiliary medical system for blood glucose monitoring and early warning according to the present invention;
fig. 7 is a schematic diagram of a doctor monitoring interface information system of an auxiliary medical system for blood glucose monitoring and early warning according to the present invention.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.
Example one
As shown in fig. 1: the embodiment discloses an auxiliary medical system for blood sugar monitoring and early warning, including: the system comprises a multi-channel clinical blood glucose data acquisition device, a cloud server and a plurality of mobile terminals.
The multichannel clinical blood glucose data acquisition device is in communication connection with the cloud server and can send acquired blood glucose data to the cloud server. The cloud server is in communication connection with the plurality of mobile terminals respectively; the cloud server can predict blood sugar data according to the obtained blood sugar data to obtain blood sugar prediction result data; the plurality of mobile terminals can obtain blood glucose prediction result data from the cloud server.
It should be noted that: the multichannel clinical blood glucose data acquisition device can be used for simultaneously acquiring blood glucose data of one or more patients in one region and sending the acquired blood glucose data to the cloud server.
Wherein the plurality of mobile terminals include at least: a patient client for use by a patient and a monitor interface information system client for use by a doctor.
In practical application, the patient client can be an APP (application) or other mobile terminals installed on the mobile phone client of the patient, and the monitoring interface information system client used by a doctor in the same way can be a mobile phone or a computer and other equipment.
The clinical blood glucose data acquisition device in this embodiment includes: a continuous blood glucose monitoring sensor CGM and an insulin infusion information acquisition device sensor CSII; the insulin infusion information collection device sensor CSII can send patient insulin injection data to the cloud server.
The continuous blood glucose monitoring sensor CGM is capable of transmitting blood glucose data of a patient to the cloud server.
Alternatively, the clinical blood glucose data collecting device in this embodiment may also be a UVA/Padova simulation platform, that is, a virtual data generation platform.
When the clinical data are not enough to drive the related algorithm, the virtual data of the UVA/Padova simulation platform are used for assisting generation.
The UVA/Padova simulation platform can provide virtual blood glucose data for the cloud server, and can simultaneously generate virtual blood glucose data of one or more patients.
Finally, it should be noted that in this embodiment, the cloud server at least includes: the system comprises a computing module and a cloud storage database.
The computing module can process the obtained blood sugar data into blood sugar prediction result data and store the blood sugar prediction result data into the cloud storage database.
Correspondingly, the cloud server in this embodiment can also provide information such as blood glucose abnormal alarm and blood glucose intelligent evaluation for the monitoring interface information client and the patient client according to the blood glucose data of the patient and the blood glucose prediction result data.
The embodiment also provides a use method of the medical system based on the above embodiment, which includes the following steps:
the multichannel clinical blood sugar data acquisition device transmits acquired or simulated blood sugar data of a patient to a cloud storage database;
the cloud storage database sends the received blood glucose data of the patient to the computing module;
the computing module carries out blood sugar prediction by utilizing the received blood sugar data of the patient to obtain blood sugar prediction result data after 30 minutes and feeds the blood sugar prediction result data back to the cloud storage database;
feeding back data information in the cloud storage database to the plurality of mobile terminals;
the data information at least comprises: patient blood glucose data and blood glucose prediction outcome data.
Of course, the data information described herein also includes abnormal blood glucose alarms and intelligent blood glucose assessment.
As shown in fig. 2 and 3: the steps described in this embodiment: the calculation module uses the received blood sugar data of the patient to predict the blood sugar, and further comprises the following substeps:
s1, preprocessing blood sugar data of the patient;
s2, decomposing the preprocessed blood sugar data by using a variational mode method VMD to obtain a group of sub-modes which are more stable than the original data;
and S3, establishing a GPR model for each sub-mode to predict the sub-modes, obtaining a predicted value of each sub-mode, and fusing and superposing all the obtained predicted values to obtain final blood sugar prediction result data.
The step S2 in this embodiment further includes the following sub-steps:
s201, aiming at each sub-mode ukThe single-side spectrum is obtained by calculating an analytic signal related to the Hilbert transform, and the method comprises the following steps:
where H (t) is the modal resolution signal, δ (t) is the Dirac distribution, t is the sampling time point, { u {k}＝{u1，...，uK}；
S202, aiming at each sub-mode, by aiming at the center frequency omegakCarrying out exponential term aliasing, and modulating each sub-mode to a corresponding fundamental frequency band, wherein the formula is as follows:
in the formulaIs omegakVector description on the complex plane, { omega }k}＝{ω1，...，ωK}；
S203, estimating the bandwidth of each sub-mode, and calculating the square L of the gradient2Norm, and the constraint condition variation problem corresponding to the position is:
s204, introducing an augmented Lagrange function, obtaining a non-constrained problem by using a secondary penalty function term and a Lagrange multiplier, and finally solving the problem by the following formula:
wherein,is a penalty term and λ is the lagrange multiplier.
Accordingly, the step S2 further includes:
a1, by alternate updatingAndto find the optimal solution, the convergence condition is:
wherein epsilon represents a convergence condition in which,representing the fourier transform, n is the number of iterations;
a2, obtaining ukAnd ωkFunction:
wherein,representing the current amount of the remaining,representing the center of gravity of the power spectrum of the current mode function.
Finally, it should be noted that: the kernel function of the GPR model in step S3 is:
wherein m is the length of the blood glucose input vector,is an output scale parameter;is the variance of the data.
Example two
The method of using the medical system provided in this embodiment may further include the steps of:
s1, if the patient is a real patient, first collecting sensor data, such as CGM blood glucose data and CSII injection data.
And if no clinical data exist, selecting a matlab simulation module to produce virtual patient data for system testing.
And S2, if the patient is a real patient, taking the sensor data of all the patients in the area diagnosed by the doctor and storing the sensor data by using MySQL cloud, and if the patient is a virtual patient, storing the data of a plurality of virtual patients together in the cloud.
And S3, predicting the blood glucose data of a plurality of patients stored in the data cloud by using a Python language through a VMD-GPR prediction model in a multi-channel mode, and feeding the prediction result back to the data cloud.
And S4, feeding back the data information in the data cloud to the patient client and the monitoring interface end information system of the doctor. The patient can see the real-time blood sugar value of the patient in the mobile terminal, forecast dynamic forecast in 30 minutes, early warning of blood sugar abnormity and intelligently evaluate the blood sugar abnormity. In the blood sugar early warning, firstly, a blood sugar dynamic prediction result is combined, and a clinically adopted blood sugar safety threshold range is combined to design a blood sugar abnormity on-line early warning system.
S5, the doctor can consult the real-time blood sugar values of all patients in the area to be treated, the dynamic predicted value of the blood sugar within 30 minutes, and give out administration suggestions and meal reminders for the blood sugar early warning patients by logging in the monitoring interface information system (IMS).
1. Randomly selecting one patient from the matlab platform, preprocessing the blood glucose data detected by the CGM of the patient, resampling the blood glucose data to obtain the blood glucose value of the patient, and displaying the blood glucose data of the VMD-GPR prediction model in the simulation for nearly 3 days as shown in FIG. 4, wherein a solid line is a real value and a dotted line is a predicted value.
As shown in fig. 5: aiming at the effect graph of the prediction part, the VMD-GPR model can accurately predict the blood sugar change trend by comparing the prediction sample with the test sample, and the RMSE (root mean square error) obtained by the evaluation function is 5.99, so that the online prediction result is accurate and the precision is high.
2. As shown in the figure, the blood sugar early warning part is divided into a step of starting a hyperglycemia warning when the blood sugar value exceeds 180mg/dl, a step of starting a hyperglycemia warning when the blood sugar value is 140mg/dl-180mg/dl, a step of starting a hypoglycemia warning when the blood sugar value is 70mg/dl-80mg/dl and a step of starting a hypoglycemia warning when the blood sugar value is below 70 mg/dl.
As shown in fig. 6: blood sugar prediction data are simulated in matlab aiming at the early warning system.
In the simulation result chart, + is a hyperglycemia alarm, ○ is a hyperglycemia early warning, and blood glucose value is in a normal range.
3. As shown in fig. 7: for the 30-minute glucose dynamic prediction part of the multichannel (three virtual patients as an example).
The technical principles of the present invention have been described above in connection with specific embodiments, which are intended to explain the principles of the present invention and should not be construed as limiting the scope of the present invention in any way. Based on the explanations herein, those skilled in the art will be able to conceive of other embodiments of the present invention without inventive efforts, which shall fall within the scope of the present invention.
Claims (10)
1. An auxiliary medical system for blood glucose monitoring and early warning, comprising: the system comprises a multi-channel clinical blood glucose data acquisition device, a cloud server and a plurality of mobile terminals;
the multichannel clinical blood glucose data acquisition device is in communication connection with the cloud server and can send acquired blood glucose data to the cloud server;
the cloud server is in communication connection with the plurality of mobile terminals respectively;
the cloud server can predict blood sugar data according to the obtained blood sugar data to obtain blood sugar prediction result data;
the plurality of mobile terminals can obtain blood glucose prediction result data from the cloud server.
2. The medical system of claim 1,
the multichannel clinical blood glucose data acquisition device comprises: a continuous blood glucose monitoring sensor CGM and an insulin infusion information acquisition device sensor CSII;
the insulin infusion information collection device sensor CSII is capable of sending patient insulin injection data to the cloud server;
the continuous blood glucose monitoring sensor CGM is capable of transmitting blood glucose data of a patient to the cloud server.
3. The medical system of claim 1,
the clinical blood glucose data acquisition device is a UVA/Padova simulation platform;
the UVA/Padova simulation platform can provide virtual blood glucose data for the cloud server.
4. The medical system of claim 2 or 3,
the plurality of mobile terminals include at least: a patient client for use by a patient and a monitor interface information system client for use by a doctor.
5. The medical system of claim 4,
the cloud server includes at least: the system comprises a computing module and a cloud storage database;
the computing module can process the obtained blood sugar data into blood sugar prediction result data and store the blood sugar prediction result data into the cloud storage database.
6. A method of use of a medical system according to any of claims 1-5, comprising the steps of:
the multichannel clinical blood sugar data acquisition device transmits acquired or simulated blood sugar data of a patient to a cloud storage database;
the cloud storage database sends the received blood glucose data of the patient to the computing module;
the computing module carries out blood sugar prediction by utilizing the received blood sugar data of the patient to obtain blood sugar prediction result data after 30 minutes and feeds the blood sugar prediction result data back to the cloud storage database;
feeding back data information in the cloud storage database to the plurality of mobile terminals;
the data information at least comprises: patient blood glucose data and blood glucose prediction outcome data.
7. The medical system of claim 6, wherein the steps of: the calculation module uses the received blood sugar data of the patient to predict the blood sugar, and further comprises the following substeps:
s1, preprocessing blood sugar data of the patient;
s2, decomposing the preprocessed blood sugar data by using a variational mode method VMD to obtain a group of sub-modes which are more stable than the original data;
and S3, establishing a GPR model for each sub-mode to predict the sub-modes, obtaining a predicted value of each sub-mode, and fusing and superposing all the obtained predicted values to obtain final blood sugar prediction result data.
8. The medical system according to claim 7, wherein the step S2 further comprises the sub-steps of:
s201, aiming at each sub-mode ukThe single-side spectrum is obtained by calculating an analytic signal related to the Hilbert transform, and the method comprises the following steps:
where H (t) is the modal resolution signal, δ (t) is the Dirac distribution, t is the sampling time point, { u {k}＝{u1，...，uK}；
S202, aiming at each sub-mode, by aiming at the center frequency omegakCarrying out exponential term aliasing, and modulating each sub-mode to a corresponding fundamental frequency band, wherein the formula is as follows:
in the formulaIs omegakVector description on the complex plane, { omega }k}＝{ω1，...，ωK}；
S203, estimating the bandwidth of each sub-mode, and calculating the square L of the gradient2Norm, and the constraint condition variation problem corresponding to the position is:
s204, introducing an augmented Lagrange function, obtaining a non-constrained problem by using a secondary penalty function term and a Lagrange multiplier, and finally solving the problem by the following formula:
wherein,is a penalty term and λ is the lagrange multiplier.
9. The prediction method according to claim 8, wherein the step S2 further comprises:
a1, by alternate updatingAndto find the optimal solution, the convergence condition is:
wherein epsilon represents a convergence condition in which,representing the fourier transform, n is the number of iterations;
a2, obtaining ukAnd ωkFunction:
wherein,representing the current amount of the remaining,representing the center of gravity of the power spectrum of the current mode function.
10. The method according to claim 9, wherein the kernel function of the GPR model in step S3 is:
wherein m is the length of the blood glucose input vector,is an output scale parameter;is the variance of the data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910513061.0A CN110151192A (en) | 2019-06-14 | 2019-06-14 | A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910513061.0A CN110151192A (en) | 2019-06-14 | 2019-06-14 | A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110151192A true CN110151192A (en) | 2019-08-23 |
Family
ID=67628924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910513061.0A Pending CN110151192A (en) | 2019-06-14 | 2019-06-14 | A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110151192A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110600128A (en) * | 2019-09-24 | 2019-12-20 | 东北大学 | Blood sugar management system for insulin dependent diabetes mellitus patient and use method |
| CN111128327A (en) * | 2019-12-30 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and device |
| CN111631730A (en) * | 2020-05-15 | 2020-09-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia warning method and system based on fusion of sensor data and physiological information |
| CN112370053A (en) * | 2020-10-16 | 2021-02-19 | 湖州美奇医疗器械有限公司 | Monitoring method for blood sugar data communication and application method |
| CN113796858A (en) * | 2021-11-18 | 2021-12-17 | 湖州美奇医疗器械有限公司 | Reference Offset Calibration Algorithm System for Blood Glucose Data Monitoring |
| CN115363571A (en) * | 2022-08-31 | 2022-11-22 | 重庆联芯致康生物科技有限公司 | Machine learning blood glucose monitoring system and method based on CGM sensor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104605862A (en) * | 2010-01-26 | 2015-05-13 | 霍夫曼-拉罗奇有限公司 | Methods and systems for processing glucose data measured from a person having diabetes |
| CN108670202A (en) * | 2012-12-31 | 2018-10-19 | 德克斯康公司 | The long-range monitoring of analysis measurement |
| US20180317817A1 (en) * | 2017-05-05 | 2018-11-08 | Samsung Electronics Co., Ltd. | Method of predicting blood glucose level using near-infrared (nir) spectroscopy data |
| CN109859850A (en) * | 2019-03-06 | 2019-06-07 | 东北大学 | Blood glucose prediction method based on variational mode decomposition and extreme learning machine |
-
2019
- 2019-06-14 CN CN201910513061.0A patent/CN110151192A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104605862A (en) * | 2010-01-26 | 2015-05-13 | 霍夫曼-拉罗奇有限公司 | Methods and systems for processing glucose data measured from a person having diabetes |
| CN108670202A (en) * | 2012-12-31 | 2018-10-19 | 德克斯康公司 | The long-range monitoring of analysis measurement |
| US20180317817A1 (en) * | 2017-05-05 | 2018-11-08 | Samsung Electronics Co., Ltd. | Method of predicting blood glucose level using near-infrared (nir) spectroscopy data |
| CN109859850A (en) * | 2019-03-06 | 2019-06-07 | 东北大学 | Blood glucose prediction method based on variational mode decomposition and extreme learning machine |
Non-Patent Citations (1)
| Title |
|---|
| KONSTANTIN DRAGOMIRETSKIY等: "Variational Mode Decomposition", 《IEEE TRANSACTIONS ON SIGNAL PROCESSING》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110600128A (en) * | 2019-09-24 | 2019-12-20 | 东北大学 | Blood sugar management system for insulin dependent diabetes mellitus patient and use method |
| CN111128327A (en) * | 2019-12-30 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and device |
| WO2021135688A1 (en) * | 2019-12-30 | 2021-07-08 | 中国科学院深圳先进技术研究院 | Method and device for early warning of hypoglycemia |
| CN111128327B (en) * | 2019-12-30 | 2023-05-26 | 中国科学院深圳先进技术研究院 | Method and device for early warning of hypoglycemia |
| CN111631730A (en) * | 2020-05-15 | 2020-09-08 | 中国科学院深圳先进技术研究院 | Hypoglycemia warning method and system based on fusion of sensor data and physiological information |
| CN111631730B (en) * | 2020-05-15 | 2023-06-06 | 中国科学院深圳先进技术研究院 | Hypoglycemia early warning method and system based on fusion of sensing data and physiological information |
| CN112370053A (en) * | 2020-10-16 | 2021-02-19 | 湖州美奇医疗器械有限公司 | Monitoring method for blood sugar data communication and application method |
| CN113796858A (en) * | 2021-11-18 | 2021-12-17 | 湖州美奇医疗器械有限公司 | Reference Offset Calibration Algorithm System for Blood Glucose Data Monitoring |
| CN115363571A (en) * | 2022-08-31 | 2022-11-22 | 重庆联芯致康生物科技有限公司 | Machine learning blood glucose monitoring system and method based on CGM sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110151192A (en) | A kind of auxiliary medical system and its application method for blood Sugar Monitoring and early warning | |
| US20210169409A1 (en) | Systems of centralized data exchange for monitoring and control of blood glucose | |
| JP7600197B2 (en) | A system and computer program for predicting hyperthyroidism using a wearable device | |
| CN103959291B (en) | Glucose predictions device based on the regularization network with adaptively selected core and regularization parameter | |
| CN103889317B (en) | A Unified Platform for Monitoring and Controlling Blood Glucose Levels in Diabetics | |
| EP2654564B1 (en) | Calibration of a handheld diabetes managing device that receives data from a continuous glucose monitor | |
| US20200211706A1 (en) | Intelligent traditional chinese medicine diagnosis method, system and traditional chinese medicine system | |
| US9262586B2 (en) | Representation of large, variable size data sets on small displays | |
| AU2019237860A1 (en) | Systems and methods for personalized medication therapy management | |
| CN103370006A (en) | Handheld diabetes management device with bolus calculator | |
| EP3654835A1 (en) | Physiological monitoring system | |
| CN110249390A (en) | For analyzing the computer implemented method and portable device and computer program product of the glucose monitoring data of the glucose level in instruction body fluid | |
| US20120165639A1 (en) | Storage of calibration data at a continuous glucose monitor | |
| CN114067529A (en) | Daily monitoring system for heart failure prediction and early warning | |
| CN110364268A (en) | Diabetic Internet-based is health management system arranged and method | |
| CN113782196A (en) | Health management method, device and system | |
| Rodriguez-Rodriguez et al. | Forecasting glycaemia for type 1 diabetes mellitus patients by means of IoMT devices | |
| CN110689959A (en) | Medical health management method and device | |
| CN116269284A (en) | A blood pressure measuring device for an electronic sphygmomanometer | |
| Putra et al. | Continuous glucose monitoring: A non-invasive approach for improved daily healthcare | |
| US9084585B1 (en) | System and method to classify left ventricular and mitral valve function | |
| Wang et al. | Research on Dynamic Assessment of Glucose-Lipid Metabolism and Personalized Drug Response Prediction Based on Wearable Multimodal Sensing | |
| US20250372222A1 (en) | Systems and methods for maintaining data integrity in a health analysis platform by assessing and modifying time-series outliers in filtered healthcare data | |
| CN118335358B (en) | Electrocardiogram terminal equipment monitoring and early warning method, system and medium based on big data | |
| EP4564359A1 (en) | System for diagnosis decision support by an ai assisted and optimized care assistance tool, and associated method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |