Noninvasive blood glucose monitoring system and implementation method

Through a blood sugar monitoring system combining metabolic thermal non-invasive sensors and minimally invasive sensors, real-time non-invasive measurements are performed using blood sugar prediction models and artificial intelligence, solving the pain, complexity and accuracy of blood sugar monitoring in the existing technology, achieving high Accurate and easy blood sugar monitoring.

CN118902444APending Publication Date: 2024-11-08SUN YAT SEN UNIV
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411113529.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing blood sugar monitoring technology has problems such as finger pain, complex operation, inability to reflect the continuous change trend of blood sugar, and the measurement accuracy is affected by external factors.

Method used

Metabolic thermal non-invasive sensors combined with minimally invasive sensors and artificial intelligence, use blood sugar prediction models to measure blood sugar values ​​in real time and improve measurement accuracy through electrical signal calibration.

Benefits of technology

It realizes high-precision, real-time, non-invasive blood sugar monitoring, simplifies operation, reduces patient pain and inconvenience, and improves the effectiveness of blood sugar monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118902444A_ABST
    Figure CN118902444A_ABST
Patent Text Reader

Abstract

The invention discloses a noninvasive blood glucose monitoring system and an implementation method. The system comprises a control module used for receiving physiological index data measured by a metabolic heat noninvasive sensor and performing blood glucose prediction based on the physiological index data through a blood glucose prediction model to obtain a blood glucose value; the analog front end is detachably connected with the control module; the analog front end is used for acquiring an electric signal through a minimally invasive sensor if the blood glucose value needs to be calibrated, and transmitting the electric signal to the control module connected with the analog front end; the electric signal corresponds to a real result of a blood glucose value of a measured object; and the control module is used for receiving the electric signal of the analog front end and constructing or updating the blood glucose prediction model based on the electric signal. According to the embodiment of the invention, real-time non-invasive measurement of the blood glucose level can be realized, the operation is simple, and the accuracy of the measurement result is high. The method can be widely applied to the technical field of signal monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of signal monitoring, and in particular to a non-invasive blood sugar monitoring system and an implementation method thereof. Background Art

[0002] Among the related technologies, fingertip blood sampling is currently a widely used technology for blood glucose monitoring, with advantages such as high accuracy and instant results. However, frequent blood sampling may cause pain and discomfort to the patient's fingers, and the operation process is relatively complicated. In addition, this method can only provide blood glucose levels at a single time point each time it is measured, and cannot reflect the continuous change trend of blood glucose. The continuous glucose monitoring system (CGM) provides 24-hour uninterrupted blood glucose data, which helps to understand the trend of blood glucose changes. However, CGM has many disadvantages, including complex operation of equipment and sensors, limited sensor life and regular replacement, and some equipment requires daily calibration and wearing can easily affect daily activities. Since non-invasive blood glucose monitoring devices do not directly measure glucose in the blood, the measurement accuracy will be affected by external factors. Summary of the invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, the purpose of the present invention is to provide a high-precision non-invasive blood glucose monitoring system and implementation method.

[0005] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0006] In one aspect, an embodiment of the present invention provides a non-invasive blood glucose monitoring system, comprising:

[0007] The non-invasive blood glucose monitoring system of the embodiment of the present invention comprises: a metabolic heat non-invasive sensor, an analog front end, and a control module; the control module is used to receive the physiological index data measured by the metabolic heat non-invasive sensor, and perform blood glucose prediction based on the physiological index data through a blood glucose prediction model to obtain a blood glucose value; the analog front end is detachably connected to the control module; the analog front end is used to obtain an electrical signal through a minimally invasive sensor if the blood glucose value needs to be calibrated, and transmit the electrical signal to the control module connected to the analog front end; the electrical signal corresponds to the actual result of the blood glucose value of the measured object; the control module is used to receive the electrical signal of the analog front end, and construct or update the blood glucose prediction model based on the electrical signal. The embodiment of the present application uses the physiological index data measured by the metabolic heat non-invasive sensor, and determines the blood glucose value based on the blood glucose prediction model; at the same time, the blood glucose prediction model is updated by obtaining an electrical signal through a minimally invasive sensor to improve the accuracy of the blood glucose measurement result. The embodiment of the present application can realize real-time non-invasive measurement of blood glucose value, simple operation, and high accuracy of measurement results.

[0008] In addition, the non-invasive blood glucose monitoring system according to the above embodiment of the present invention may also have the following additional technical features:

[0009] Furthermore, in the non-invasive blood glucose monitoring system of the embodiment of the present invention, the analog front end includes an AD5941 chip or an AD5940 chip, the analog ground of the AD5941 chip is connected to the digital ground of the AD5941 chip through a first resistor, and the resistance of the first resistor is 0Ω; the universal interface of the AD5941 chip is connected to the minimally invasive sensor; and the analog front end communicates with the control module via SPI.

[0010] Furthermore, in one embodiment of the present invention, the metabolic heat non-invasive sensor includes a first photoelectric sensor, a second photoelectric sensor, a first temperature and humidity sensor, and a second temperature and humidity sensor; the first photoelectric sensor is used to detect the photoelectric signal at the wrist of the measured object, and the second photoelectric sensor is used to detect the photoelectric signal at the finger of the measured object; the first temperature and humidity sensor is installed between the bottom layer of the circuit board and the measured object, the first temperature and humidity sensor is used to detect the skin temperature and humidity signal of the measured object, the second temperature and humidity sensor is installed on the side of the circuit board away from the measured object, and the second temperature and humidity sensor is used to detect the ambient temperature signal; the metabolic heat non-invasive sensor communicates with the control module via IIC.

[0011] Furthermore, in one embodiment of the present invention, the analog front end is connected to the control module via a board-to-board connector.

[0012] Furthermore, in one embodiment of the present invention, the physiological indicator data measured by the metabolic heat non-invasive sensor is used as the characteristic value for training the blood glucose prediction model, and the electrical signal measured by the minimally invasive sensor is used as the true value for training the blood glucose prediction model, so as to train the blood glucose prediction model.

[0013] Furthermore, in one embodiment of the present invention, the monitoring system also includes a power supply module, the first power supply outputs the second power supply through a voltage regulator, the second power supply is grounded through a first capacitor, the second power supply is grounded through a second capacitor, the second power supply is grounded through a third capacitor, and the capacity of the first capacitor is greater than the capacity of the second capacitor and the third capacitor.

[0014] On the other hand, an embodiment of the present invention provides a method for implementing non-invasive blood glucose monitoring, which is applied to the above-mentioned non-invasive blood glucose monitoring system. The method includes:

[0015] Receiving physiological index data measured by a metabolic heat non-invasive sensor, and performing blood sugar prediction based on the physiological index data using a blood sugar prediction model to obtain a blood sugar value;

[0016] If the blood glucose value needs to be calibrated, an electrical signal obtained by a minimally invasive sensor is received, and based on the electrical signal, the blood glucose prediction model is constructed or updated.

[0017] Furthermore, in the implementation method of non-invasive blood glucose monitoring of the embodiment of the present invention, the blood glucose prediction model is trained by the following steps:

[0018] Inputting the physiological indicator data into the blood glucose prediction model to obtain a blood glucose prediction result;

[0019] According to the electrical signal, the actual result of blood sugar is determined, and the loss value is calculated using a loss function according to the blood sugar prediction result and the actual result, and the parameters of the blood sugar prediction model are updated according to the loss value to obtain the trained blood sugar prediction model.

[0020] Furthermore, the method for implementing non-invasive blood glucose monitoring of the embodiment of the present invention further includes:

[0021] Communicating with the metabolic heat non-invasive sensor via IIC;

[0022] Communicate with the minimally invasive sensor via SPI.

[0023] On the other hand, an embodiment of the present invention provides a non-invasive blood glucose monitoring device, including the above-mentioned non-invasive blood glucose monitoring system.

[0024] On the other hand, an embodiment of the present invention provides a non-invasive blood glucose monitoring device, comprising:

[0025] at least one processor;

[0026] at least one memory for storing at least one program;

[0027] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for implementing non-invasive blood glucose monitoring.

[0028] On the other hand, an embodiment of the present invention provides a storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for implementing non-invasive blood glucose monitoring.

[0029] The monitoring system provided by the embodiment of the present invention includes: a metabolic heat non-invasive sensor, an analog front end, and a control module; the control module is used to receive the physiological index data measured by the metabolic heat non-invasive sensor, and perform blood sugar prediction based on the physiological index data through a blood sugar prediction model to obtain a blood sugar value; the analog front end is detachably connected to the control module; the analog front end is used to obtain an electrical signal through a minimally invasive sensor if the blood sugar value needs to be calibrated, and transmit the electrical signal to the control module connected to the analog front end; the electrical signal corresponds to the actual result of the blood sugar value of the measured object; the control module is used to receive the electrical signal of the analog front end, and based on the electrical signal, construct or update the blood sugar prediction model. The embodiment of the present application uses the physiological index data measured by the metabolic heat non-invasive sensor, and determines the blood sugar value based on the blood sugar prediction model; at the same time, the blood sugar prediction model is updated by obtaining an electrical signal through a minimally invasive sensor to improve the accuracy of the blood sugar measurement result. The embodiment of the present application can realize real-time non-invasive measurement of blood sugar value, simple operation, and high accuracy of measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1a A physical diagram of an embodiment of a non-invasive blood glucose monitoring system provided in an embodiment of the present application;

[0032] Figure 1b A physical diagram of an embodiment of a photoelectric sensor provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of the structure of an embodiment of a non-invasive blood glucose monitoring system provided in an embodiment of the present application;

[0034] Figure 3 An electrical schematic diagram of an embodiment of an analog front end provided in an embodiment of the present application;

[0035] Figure 4 An electrical schematic diagram of an embodiment of lithium battery power supply provided in the embodiment of the present application;

[0036] Figure 5 An electrical schematic diagram of an embodiment of a level conversion circuit provided in an embodiment of the present application;

[0037] Figure 6An electrical schematic diagram of an embodiment of a Bluetooth module provided in an embodiment of the present application;

[0038] Figure 7 An electrical schematic diagram of an embodiment of a control module provided in an embodiment of the present application;

[0039] Figure 8 An electrical schematic diagram of an embodiment of a photoelectric sensor provided in an embodiment of the present application;

[0040] Fig. 9 An electrical schematic diagram of another embodiment of the photoelectric sensor provided in the embodiment of the present application;

[0041] Fig.10 An electrical schematic diagram of an embodiment of a temperature and humidity sensor provided in an embodiment of the present application;

[0042] Fig.11 An electrical schematic diagram of an embodiment of a connector provided in an embodiment of the present application;

[0043] Fig.12 An electrical schematic diagram of an embodiment of an infrared sensor provided in an embodiment of the present application;

[0044] Fig.13 A PCB design layout of an embodiment of a system mainboard provided in an embodiment of the present application;

[0045] Fig.14 A PCB design layout of an embodiment of the analog front end provided in the embodiment of the present application;

[0046] Fig.15 A PCB design layout of an embodiment of a photoelectric sensor provided in an embodiment of the present application;

[0047] Fig.16 A PCB design layout of an embodiment of a thermal radiation sensor provided in an embodiment of the present application;

[0048] Fig.17 A photoelectric principle diagram of an embodiment of a minimally invasive sensor provided in an embodiment of the present application;

[0049] Fig.18 A schematic diagram of the structure of an embodiment of a blood glucose prediction model provided in an embodiment of the present application;

[0050] Fig.19a A front view of the upper portion of the system housing provided by an embodiment of the present application;

[0051] Fig.19b A top view of the upper portion of the system housing provided by an embodiment of the present application;

[0052] Fig.19cA side view of the upper portion of the system housing provided by an embodiment of the present application;

[0053] Fig.20a A front view of the lower portion of the system housing provided by an embodiment of the present application;

[0054] Fig.20b A top view of the lower portion of the system housing provided in an embodiment of the present application;

[0055] Fig.20c A side view of the lower portion of the system housing provided by an embodiment of the present application;

[0056] Fig.21a A front view of a physical diagram of a system provided in an embodiment of the present application;

[0057] Figure 21b A wearing view of a physical diagram of the system provided in an embodiment of the present application;

[0058] Fig.21c A back view of a physical diagram of a system provided in an embodiment of the present application;

[0059] Fig.21d A front view of a physical diagram of a board-to-board connector provided in an embodiment of the present application;

[0060] Fig. 22 A graph showing an embodiment of a sensitivity test of a microneedle in a simulated front end provided in an embodiment of the present application;

[0061] Fig.23 A curve diagram of another embodiment of the sensitivity test of the microneedle in the simulated front end provided in the embodiment of the present application;

[0062] Fig.24 A stability curve diagram of a photoelectric sensor signal acquisition based on a first object provided in an embodiment of the present application;

[0063] Fig.25 A stability curve diagram of the photoelectric sensor signal acquisition based on the second object provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0065] There are many technologies for monitoring human blood glucose, including fingertip blood sampling, continuous glucose monitoring system (CGM) and non-invasive monitoring technology. Fingerprick blood sampling collects a small amount of blood sample for chemical analysis. Although it is highly accurate, it requires frequent blood sampling, which is inconvenient for patients. CGM continuously monitors blood glucose levels through sensors implanted or attached to the skin, reducing the need for frequent blood sampling. The sensor measures every few minutes and transmits the data wirelessly to the receiving device, but the sensor needs to be replaced regularly. Non-invasive blood glucose monitoring technology aims to measure blood glucose levels without blood sampling. There are currently many research attempts, such as using near-infrared or mid-infrared light to measure absorbance changes through the skin (spectroscopy), analyzing scattering spectra through the interaction of lasers with molecules in the skin (Raman spectroscopy), and inferring blood glucose concentrations through changes in skin surface current (electrochemical method). In addition, there are some embedded monitoring devices that can be implanted subcutaneously for long-term blood glucose monitoring, combined with CGM technology to transmit blood glucose data in real time, reducing patient maintenance requirements. Different technologies have their own advantages and disadvantages. Which method to choose depends on specific application requirements, patient acceptance, cost and technical maturity.

[0066] On the other hand, fingertip blood sampling is a widely used technology for blood glucose monitoring, with advantages such as high accuracy and instant results. However, frequent blood sampling may cause pain and discomfort to the patient's fingers, and the operation process is relatively complicated. In addition, this method can only provide blood glucose levels at a single time point each time it is measured, and cannot reflect the continuous change trend of blood glucose. The continuous glucose monitoring system (CGM) provides 24-hour uninterrupted blood glucose data, which helps to understand the trend of blood glucose changes. However, CGM has many disadvantages, including high equipment and sensor costs, limited sensor life and regular replacement, daily calibration of some devices, and wearing can easily affect daily activities. Since non-invasive blood glucose monitoring devices do not directly measure glucose in the blood, the measurement accuracy will be affected by external factors. At the same time, everyone's skin and body characteristics are different, and the default calibration of non-invasive blood glucose meters may not be suitable for everyone, and the accuracy is low. Therefore, blood glucose monitoring devices with long life, continuous monitoring, wearable and high accuracy can greatly improve the effectiveness of blood glucose monitoring in patients with hyperglycemia or diabetes. However, they face problems such as high development difficulty and complex technical routes.

[0067] In view of the high requirements of existing blood glucose monitoring equipment in application for long life, continuous monitoring, wearability and high accuracy, and the difficulties of existing non-invasive blood glucose equipment development, such as high difficulty and low accuracy, the present invention proposes a minimally invasive sensor fusion artificial intelligence correction metabolic heat non-invasive blood glucose monitoring solution. The circuit integrates an analog front end and a variety of sensors, collects data through electrochemical microneedles and a variety of sensors (photoelectric sensors, temperature and humidity sensors, and thermal radiation sensors), and combines the concept of deep learning to achieve calibration of metabolic heat non-invasive blood glucose equipment. The present invention can simultaneously solve the problems of low accuracy of non-invasive blood glucose equipment and the impact of implantable equipment on daily activities, and greatly reduce the overall pain and inconvenience of patients with hyperglycemia or diabetes.

[0068] The following describes in detail a non-invasive blood glucose monitoring system and implementation method according to an embodiment of the present invention with reference to the accompanying drawings. First, a non-invasive blood glucose monitoring system according to an embodiment of the present invention is described with reference to the accompanying drawings, specifically comprising:

[0069] Metabolic heat non-invasive sensor, analog front end, control module;

[0070] The control module is used to receive the physiological index data measured by the metabolic heat non-invasive sensor, and perform blood sugar prediction based on the physiological index data through a blood sugar prediction model to obtain a blood sugar value;

[0071] The analog front end is detachably connected to the control module; the analog front end is used to obtain an electrical signal through a minimally invasive sensor if the blood sugar value needs to be calibrated, and transmit the electrical signal to the control module connected to the analog front end; the electrical signal corresponds to the actual result of the blood sugar value of the measured object;

[0072] The control module is used to receive the electrical signal of the analog front end, and to construct or update the blood glucose prediction model based on the electrical signal.

[0073] Optionally, in the non-invasive blood glucose monitoring system in the embodiment of the present invention, the analog front end includes an AD5941 chip or an AD5940 chip, the analog ground of the AD5941 chip is connected to the digital ground of the AD5941 chip through a first resistor, and the resistance of the first resistor is 0Ω; the universal interface of the AD5941 chip is connected to the minimally invasive sensor; the analog front end communicates with the control module via SPI. The blood glucose prediction model can be constructed according to the artificial intelligence model, and this application does not limit the specific model architecture of the blood glucose prediction model. The minimally invasive sensor is used if the blood glucose value does not need to be calibrated and is not connected to the control module.

[0074] In some possible embodiments, the minimally invasive sensor includes an electrochemical microneedle sensor. The electrical signal may be a current signal. The physiological index data may be the blood flow velocity, systolic pressure, diastolic pressure, pulse rate, blood oxygen saturation, metabolic heat production and other data of the measured object, which can be achieved by arranging the corresponding sensors for data collection according to the required data. It is understandable that the optimization of the digital oscilloscope algorithm in the embodiment of the present application can further reduce the system noise.

[0075] The present invention proposes a method for non-invasive blood glucose monitoring by fusion of minimally invasive sensors and artificial intelligence. The AD5941 analog front-end chip is developed to collect the current signal of the minimally invasive microneedle sensor, and the concept of artificial intelligence is integrated to realize the calibration of the metabolic heat non-invasive blood glucose device. The advantages are mainly: the minimally invasive sensor can collect the current signal corresponding to different concentrations of glucose, realize the calibration of the non-invasive blood glucose monitoring device, and can simultaneously solve the problems of low accuracy of the non-invasive blood glucose device and the impact of implantable devices on daily activities; the design is very flexible, and the minimally invasive sensor can be installed through the male and female vertical board-to-board connector with a spacing of 0.5mm and a PIN of 10P during calibration. It can be disassembled when calibration is not required and does not affect the operation of the metabolic heat non-invasive blood glucose monitoring device; the device is highly integrated, and the area is equivalent to the size of a watch dial, which meets the wearable requirements; it can realize multi-sensor continuous monitoring of human blood flow velocity, systolic pressure, diastolic pressure, pulse rate, blood oxygen saturation, metabolic heat production and other physiological indicators. The sensitivity of the analog front end to collect electrochemical minimally invasive microneedle sensor signals was tested in the solution, and the stability of metabolic heat sensor data acquisition was tested on humans and rabbits. The present invention constructs a blood sugar monitoring system, promotes the development of blood sugar monitoring technology, and can greatly alleviate the inconvenience of blood sugar monitoring for patients with hyperglycemia or diabetes.

[0076] Optionally, in the non-invasive blood glucose monitoring system in the embodiment of the present invention, the metabolic heat non-invasive sensor includes a first photoelectric sensor, a second photoelectric sensor, a first temperature and humidity sensor, and a second temperature and humidity sensor; the first photoelectric sensor is used to detect the photoelectric signal at the wrist of the measured object, and the second photoelectric sensor is used to detect the photoelectric signal at the finger of the measured object; the first temperature and humidity sensor is installed between the bottom layer of the circuit board and the measured object, the first temperature and humidity sensor is used to detect the skin temperature and humidity signal of the measured object, the second temperature and humidity sensor is installed on the side of the circuit board away from the measured object, and the second temperature and humidity sensor is used to detect the ambient temperature signal; the metabolic heat non-invasive sensor communicates with the control module via IIC.

[0077] In the embodiment of the present application, the photoelectric sensor is electrically connected to the control module via a Dupont line, and the photoelectric sensor is in direct contact with the skin of the object being measured when in use. In some embodiments, the metabolic heat non-invasive sensor also includes a thermal radiation sensor, which is installed above the main device circuit board and does not directly contact the skin of the object being measured. The thermal radiation sensor is used to detect the thermal radiation infrared signal of the object being measured.

[0078] In some embodiments, the electrical principle of the photoelectric sensor is as follows: the second power supply is connected to the source of the first transistor, the drain of the first transistor is connected to the SCL terminal of the photoelectric sensor chip, and the gate of the first transistor is connected to the third power supply; the second power supply is connected to the source of the second transistor, the drain of the second transistor is connected to the SDA terminal of the photoelectric sensor chip, and the gate of the second transistor is connected to the third power supply; the third power supply is connected to the gate of the third transistor, the third power supply is connected to the INT terminal of the photoelectric sensor chip through the second resistor, the INT terminal of the photoelectric sensor chip is connected to the drain of the third transistor, and the source of the third transistor is connected to the second power supply.

[0079] Optionally, in the non-invasive blood glucose monitoring system in the embodiment of the present invention, the analog front end is connected to the control module via a board-to-board connector.

[0080] In some possible implementations, the number and spacing of PINs of the board-to-board connector can be set as needed.

[0081] Optionally, in the non-invasive blood glucose monitoring system in the embodiment of the present invention, the physiological indicator data measured by the metabolic heat non-invasive sensor is used as the characteristic value for training the blood glucose prediction model, and the electrical signal measured by the minimally invasive sensor is used as the true value for training the blood glucose prediction model, so as to train the blood glucose prediction model.

[0082] Optionally, in the non-invasive blood glucose monitoring system in the embodiment of the present invention, the monitoring system also includes a power supply module, the first power supply outputs the second power supply through a voltage stabilizer, the second power supply is grounded through a first capacitor, the second power supply is grounded through a second capacitor, the second power supply is grounded through a third capacitor, and the capacity of the first capacitor is greater than the capacity of the second capacitor and the third capacitor.

[0083] In some possible implementations, the first power supply may be a 3.7V power supply, and the second power supply may be a 3.3V power supply.

[0084] The non-invasive blood glucose monitoring system proposed in this application is described in detail below with a specific embodiment.

[0085] FIG1 is a system schematic diagram of a minimally invasive sensor calibration metabolic heat non-invasive blood glucose monitoring device provided in an embodiment of the present application.

[0086] in Figure 1aWorn on the wrist, the left protrusion is a detachable minimally invasive sensor / analog front end. Figure 1b It is a photoelectric sensor in the metabolic heat non-invasive blood glucose monitoring system, which needs to be worn on the finger and should be connected to the main device / control module (i.e. Figure 1a The devices shown in the figure are electrically connected via Dupont wires. Figure 2 A schematic diagram of the connection of a multi-sensor integrated acquisition system provided in an embodiment of the present application. The analog front end collects current signals corresponding to different glucose concentrations in body fluids or solutions through an electrochemical microneedle sensor (i.e., a minimally invasive sensor). When in use, a detachable analog front end needs to be installed, and the microneedle sensor probe is implanted subcutaneously or inserted below the surface of the glucose solution to collect current signals. The metabolic thermal sensor includes three major categories of sensors, and the specific information is as follows: two photoelectric sensors (PPG), one PPG is placed on the wrist (i.e., the first photoelectric sensor) when in use, and the other PPG is placed on the finger and directly in contact with the skin (i.e., the second photoelectric sensor), respectively collecting photoelectric signals of changes in diameter of human blood vessels during cardiac contraction or diastole. Two temperature and humidity sensors (si7021), one temperature and humidity sensor is installed on the bottom layer of the main device circuit board to contact the human wrist skin to collect skin temperature signals (i.e., the first temperature and humidity sensor), and the other temperature and humidity sensor is installed on the top layer of the main device circuit board to collect environmental temperature and humidity signals (i.e., the second temperature and humidity sensor). The thermal radiation sensor (MLX90614) is installed above the main device circuit board without direct contact with the skin to detect infrared signals of thermal radiation from human skin. The embodiment of the present application further includes a power module, Figure 4 This is the schematic diagram of the 3.7V lithium battery power supply circuit, including a 3.7V to 1.8V level conversion circuit. Figure 5 This is the schematic diagram of the 3.3V to 1.8V level conversion circuit. The 3.7V lithium battery powers the entire system, and is converted into the working voltage required by various sensors through the 1.8V and 3.3V level conversion circuits. After the data is collected, it is transmitted to the microcontroller through SPI, IIC and other communication protocols, and then transmitted to the host computer through Bluetooth wireless for data display and storage.

[0087] For the design of the analog front-end circuit of the embodiment of the present application, in order to achieve a reliable connection between the minimally invasive sensor and the metabolic heat mainboard, a 0.5mm board-to-board connector can be used (as shown in Figure 1, the right side of the main device is a board-to-board connector, and the circuit at the analog front end realizes a detachable function). This connector can not only reduce the layout area as much as possible, but also provide a stable connection. It is worth mentioning that this connector design makes it possible to easily remove the sensor part without calibration without affecting the normal operation of the entire metabolic heat system. This flexible design greatly improves the convenience of wearing and user experience.

[0088] In order to ensure that the data collected by the analog front end is more stable and accurate, the digital ground and analog ground are distinguished in the schematic design. Figure 3 This is the schematic diagram of the analog front end. This part is independent of the main board and communicates with the microcontroller via SPI. The board-to-board connector is electrically connected to the main board. Connect the two through a single-point 0Ω resistor (such as Figure 3 R5 connects the digital ground and analog ground of the analog front-end circuit, thereby reducing the interference of digital signals on analog signals and ensuring the integrity and reliability of data.

[0089] In the design of the power supply system, large and small capacitors are connected in parallel (such as Figure 4 The 3.7V voltage input is stepped down by LDO, and then the low-frequency noise is filtered out by a 10μF large capacitor for energy storage and decoupling, and then the high-frequency noise is filtered out by a 100nF small capacitor. The filtering function of noise in different frequency bands is achieved by setting appropriate parameters. Specifically, the large capacitor is used for energy storage and filtering low-frequency noise, while the small capacitor is used for filtering high-frequency noise. This combination can significantly improve the stability of the power supply system, ensure the purity of the power supply, and thus improve the performance of the entire system. We also specially selected capacitors with smaller packages to further improve the stability and integration of the system.

[0090] Specifically, the power supply system of the present invention adopts a 3.7V to 3.3V lithium battery voltage conversion circuit, and realizes a stable voltage output through a low voltage difference linear regulator (LDO). The use of LDO can not only effectively reduce the layout area of ​​the power supply system, but also provide a smaller power supply ripple, thereby preventing the power supply noise from interfering with the signal acquisition of the analog front end, and ensuring the accuracy and stability of the data. In order to make the operation of the power supply system more convenient, a paddle switch circuit is designed, and the user can easily switch the circuit at any time. This design improves the flexibility of the device, and is particularly suitable for application scenarios that require frequent start and stop. In addition, in order to monitor the power supply situation in real time, we integrate an LED indicator light in the circuit. The LED indicator light can clearly display the current power supply status. For example, when the battery is fully charged, the indicator light will remain bright; when the battery is low, the LED indicator light will obviously dim or flash intermittently, reminding the user to replace the battery in time. This design not only improves the user experience, but also ensures that the device can be maintained in time when the battery is low, avoiding device failure or data loss caused by low power.

[0091] In addition, in order to achieve bidirectional conversion of logic levels between sensors with different power supply voltages, a 3.3V and 1.8V level conversion circuit is designed. An NMOS tube with a turn-on voltage lower than 1.8V is used, and its source is connected to the low power supply terminal. When the bus is idle, both signal terminals remain at a high level. When the low power supply terminal becomes a low level, the NMOS tube is turned on, and the high power supply terminal is pulled down to the same level. Vice versa, the high power supply terminal signal is pulled down through the body diode. In this way, the normal IIC communication and bidirectional level conversion are realized, preventing the high voltage burr from damaging the low voltage device.

[0092] On the other hand, refer to Figure 6 The embodiment of the present application realizes data transmission through a Bluetooth module. Figure 7 It is a microcontroller schematic, which communicates with the analog front end through the SPI protocol, is electrically connected through a male and female vertical board-to-board connector with a spacing of 0.5mm and a PIN of 10P, and communicates with the temperature and humidity sensor, thermal radiation sensor and photoelectric sensor through the IIC protocol. The module also contains a resistor-capacitor reset circuit, a crystal oscillator circuit and a main control filter circuit. Figure 8 This is the schematic diagram of the photoelectric sensor at the wrist, where Q1 is the first transistor, Q4 is the second transistor, Q2 is the third transistor, and U1 is the photoelectric sensor chip. Fig. 9 This is the schematic diagram of the photoelectric sensor at the finger. The components of this part are independent of the main board and will be electrically connected to the main board through a connector. Fig.10 It is the schematic diagram of the temperature and humidity sensor, which detects skin temperature and ambient temperature and humidity respectively. Fig.11 is a schematic diagram of the connector used to make the electrical connection to the infrared sensor. Fig.12 This is the schematic diagram of the infrared sensor. The components of this part are independent of the main board and will be electrically connected to the main board through the connector. Fig.13 It is the PCB design layout of the front and back sides of the system motherboard. Fig.14 It is the front and back PCB design layout of the system analog front end, which is electrically connected to the main board through the board-to-board connector. Fig.15 It is the front and back PCB design layout of the photoelectric sensor at the system finger, which is electrically connected to the main board through DuPont wire. Fig.16 It is the front and back PCB design layout of the system thermal radiation sensor, which is electrically connected to the mainboard through pin headers. Fig.17 This is an optical picture of the minimally invasive electrochemical microneedle used in this system, connected to the analog front end via three electrodes for data acquisition.

[0093] Fig.18A logical schematic diagram of a complete blood glucose monitoring system provided for an embodiment of the present application. Among them, the calibration of the model is mainly divided into two usage scenarios: in the early stage, the metabolic heat non-invasive sensor collects various signals as characteristic values ​​for training the machine learning model, and the analog front end collects the subcutaneous current signal of the human body through the electrochemical microneedle sensor to obtain the real blood glucose value, and the data is used as a training set to train the model for supervised learning; in the later stage, if the model predicts that the blood glucose value is biased, the real blood glucose data can be collected again with a minimally invasive sensor to train the model for a second time, so that the machine learning model predicting blood glucose is more accurate. In other embodiments, the model can be updated periodically to improve the accuracy of the blood glucose monitoring results. The period / time between the two updates can be set according to the actual situation, and this application does not make specific limitations.

[0094] Figure 19 is a three-view diagram of the upper half of the system housing. Fig.19a It is a front view; Fig.19b It is a top view; Fig.19c In some embodiments, the material is 8001SLA photosensitive resin, material color: transparent; surface treatment: spray painting; size: 1.82*4.6*4.6cm; volume: 6.5cm3; surface area: 70.87cm2.

[0095] Figure 20 Three views of the lower half of the system housing. Fig.20a It is a front view; Fig.20b It is a top view; Fig.20c It is a side view. Material: Imagine Black SLA photosensitive resin; Material color: black; Surface treatment: grinding-rough grinding; Size: 0.45*4.6*4.6cm; Volume: 2.03cm3; Surface area: 42.73cm2.

[0096] Figure 21 shows how to wear the device and its details. Fig.21a This is the front view of the object; Figure 21b For wearing actual pictures; Fig.21c This is the actual picture on the back; Fig.21d This is a physical picture of the detachable board-to-board connector.

[0097] Example 1: The analog front end collects the current signal in the glucose solution.

[0098] Step S11, preparation of solution experiment: prepare 50ml of 1mM glucose solution with PBS as solvent for use, prepare a 10ml beaker filled with PBS solution, add a magnetic rotor into the beaker, place the beaker in a metal shielding box, and then place the entire device on a magnetic stirrer.

[0099] Step S12, place the microneedle tip under the liquid surface of the beaker, and be careful not to let the liquid touch the PCB board to avoid affecting the analog front-end data reading. After the acquisition circuit equipment is placed, close the metal shielding box cover, start the magnetic stirrer for 30 seconds, let the solution stand for 30 seconds, start detecting the current signal, and count the detection time for 3 minutes.

[0100] Step S13, use a 20μL rubber-tipped dropper to draw up 50ml of 1mM glucose solution, and drop it into a 10ml beaker filled with PBS solution. After dropping, close the lid of the metal shielding box, start the magnetic stirrer for 30s, let the solution stand for 30s, start detecting the current signal, and count the detection time for 3min (at this time, the concentration of the glucose solution in the 10ml beaker changes from 0mM to 2mM, and its volume change is negligible).

[0101] Step S14, repeat the above experimental operation, each time adding glucose solution to increase the concentration by 2 mM, and respectively collect the current signal responses of glucose solution concentrations of 0, 2, 4, 6, and 8 mM.

[0102] Step S15, experimental analysis and verification, by finding the current stability value after each addition of glucose solution and drawing the microneedle current sensitivity curve, the effectiveness and stability of the circuit function are verified. Fig. 22 As shown, the sensitivity of the microneedle was tested in the solution using the analog front end using the chronoamperometry method. The glucose concentration was increased by 2 mM each time, and the current data was collected after stirring for 30 seconds using a magnetic stirring bar and then standing for 30 seconds. The sensitivity of the microneedle reached 0.83 nA / mM. Fig.23 As shown, the microneedle sensitivity was tested using the same experimental method using the Chenhua electrochemical workstation. It can be seen that the sensitivity is within an acceptable range.

[0103] Example 2: Detection of physiological signals in living animals.

[0104] Step S21, preparation of the experimental New Zealand rabbit: purchase a healthy New Zealand rabbit of appropriate age and stable weight, check for obvious abnormalities, and perform adaptive breeding.

[0105] Step S22, anesthesia method: After the New Zealand rabbit is securely fixed, general anesthesia is performed by intramuscular injection of Lumianning.

[0106] Step S23, using surgical scissors and depilatory cream to first depilate the chest to obtain an area of ​​4×4 cm 2 The device was fixed to the exposed skin of the rabbit with medical tape to collect the rabbit's skin temperature, thermal radiation temperature, and ambient temperature and humidity signals. The rabbit's front and back legs were depilated to obtain an area of ​​2×2cm 2The device is fixed to the front and back legs with medical tape to collect photoelectric signals (the photoelectric sensor signal at the front and back legs will be better). The minimally invasive electrochemical microneedle sensor collects subcutaneous signals from New Zealand rabbits as the real blood sugar value.

[0107] Step S24, end of experiment and animal treatment: After recording the effective signal, we removed the sensor and cultured the experimental animals for another 24 hours, and finally killed the New Zealand rabbits by intramuscular injection of an overdose of anesthetic. Fig.24 As shown in the figure, the stability of the photoelectric sensor signal acquisition is tested on the front and back legs of the rabbit. PPG_1 and PPG_2 are the signals of the front and back legs of the rabbit respectively.

[0108] Embodiment 3: Detection of multiple physiological parameters of human body.

[0109] Step S31, subject recruitment: We recruited 3 adults as subjects. Each subject had a detailed understanding of the purpose and process of the experiment before participating in the experiment, and had clearly understood and agreed to participate in this experiment.

[0110] Step S32: To ensure data stability and accuracy during the measurement process, we use medical tape to securely fix the sensor on the subject's wrist and fingertips. This fixation method can ensure that the sensor is in close contact with the skin without causing excessive interference to the subject's daily activities.

[0111] Step S33, measure once every 20 minutes. In order to reduce the error in the measurement process, the measurement interval of each subject is set to 1 hour. During the measurement process, we ask the subjects to keep their bodies as still as possible and avoid large movements to reduce the impact of movement on the measurement results.

[0112] Step S34, in order to ensure the reliability of the experimental results and the diversity of the data, we repeated the above experimental steps on different dates within two weeks. During each experiment, we strictly followed the same operating procedures and measurement conditions to ensure the comparability of the data. Fig.25 As shown in the figure, the stability of the signal collected by the photoelectric sensor of the human body test, PPG_1 and PPG_2 are the signals at the wrist and fingers of the human body respectively.

[0113] Comparative Example 1:

[0114] Under the same experimental conditions, we compared the performance of the analog front end in collecting the current signal in the glucose solution. In order to test the sensitivity of the microneedle used in the present invention, we used the Chenhua electrochemical workstation and used the same experimental method as in Example 1 to draw the IT curves of different gradient changes in glucose solution concentration. Fig. 22 and Fig.23After saving the data, we captured the stable current value after adding glucose solution and plotted the microneedle current sensitivity curve to verify the effectiveness and stability of the data acquisition function of our analog front-end circuit.

[0115] The specific operations are as follows:

[0116] Step S41, experimental preparation:

[0117] Prepare glucose solutions of different concentrations and make sure to perform the experiment under the same conditions to ensure comparability of the results. Install the microneedle sensor on the electrochemical workstation in a shielded box and ensure that all equipment is working properly.

[0118] Step S42, data collection:

[0119] Start the electrochemical workstation and gradually increase the concentration of the glucose solution according to the predetermined experimental steps. After each concentration change, record the corresponding current signal by chronoamperometry and draw a real-time it curve (current-time curve). After each increase in glucose solution, when the current signal stabilizes, save the data point as the stable current value at that concentration.

[0120] Step S43, data analysis:

[0121] After the experiment, all the collected data were sorted and analyzed. The stable value of the current signal after each addition of glucose solution was intercepted and used to draw the microneedle current sensitivity curve. By comparing the current changes under different concentration gradients, the effectiveness and stability of the analog front-end circuit in the data acquisition process were verified.

[0122] In summary, the monitoring system provided by the embodiment of the present application includes: a metabolic heat non-invasive sensor, an analog front end, and a control module; the control module is used to receive the physiological index data measured by the metabolic heat non-invasive sensor, and perform blood sugar prediction based on the physiological index data through a blood sugar prediction model to obtain a blood sugar value; the analog front end is detachably connected to the control module; the analog front end is used to obtain an electrical signal through a minimally invasive sensor if the blood sugar value needs to be calibrated, and transmit the electrical signal to the control module connected to the analog front end; the electrical signal corresponds to the actual result of the blood sugar value of the measured object; the control module is used to receive the electrical signal of the analog front end, and based on the electrical signal, construct or update the blood sugar prediction model. The embodiment of the present application uses the physiological index data measured by the metabolic heat non-invasive sensor, and determines the blood sugar value based on the blood sugar prediction model; at the same time, the blood sugar prediction model is updated by obtaining an electrical signal through a minimally invasive sensor to improve the accuracy of the blood sugar measurement result. The embodiment of the present application can realize real-time non-invasive measurement of blood sugar value, simple operation, and high accuracy of measurement results.

[0123] Next, a method for implementing non-invasive blood glucose monitoring according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0124] An implementation method for non-invasive blood glucose monitoring is provided in an embodiment of the present invention. The implementation method for non-invasive blood glucose monitoring in the embodiment of the present invention can be applied to a terminal, a server, or software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The implementation method for non-invasive blood glucose monitoring in the embodiment of the present invention is applied to the non-invasive blood glucose monitoring system described above, and mainly includes the following steps:

[0125] Receiving physiological index data measured by a metabolic heat non-invasive sensor, and performing blood sugar prediction based on the physiological index data using a blood sugar prediction model to obtain a blood sugar value;

[0126] If the blood glucose value needs to be calibrated, an electrical signal obtained by a minimally invasive sensor is received, and based on the electrical signal, the blood glucose prediction model is constructed or updated.

[0127] Optionally, in the implementation method of non-invasive blood glucose monitoring in the embodiment of the present invention, the blood glucose prediction model is trained by the following steps:

[0128] Inputting the physiological indicator data into the blood glucose prediction model to obtain a blood glucose prediction result;

[0129] According to the electrical signal, the actual result of blood sugar is determined, and the loss value is calculated using a loss function according to the blood sugar prediction result and the actual result, and the parameters of the blood sugar prediction model are updated according to the loss value to obtain the trained blood sugar prediction model.

[0130] Optionally, the method for implementing non-invasive blood glucose monitoring in the embodiment of the present invention further includes:

[0131] Communicating with the metabolic heat non-invasive sensor via IIC;

[0132] Communicate with the minimally invasive sensor via SPI.

[0133] It can be seen that the contents of the above system embodiments are all applicable to the present method embodiments, the functions specifically implemented by the present method embodiments are the same as those of the above system embodiments, and the beneficial effects achieved are also the same as those achieved by the above system embodiments.

[0134] On the other hand, an embodiment of the present invention provides a non-invasive blood glucose monitoring device, including the above-mentioned non-invasive blood glucose monitoring system.

[0135] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0136] The embodiment of the present invention provides a non-invasive blood glucose monitoring device, comprising:

[0137] at least one processor;

[0138] at least one memory for storing at least one program;

[0139] When the at least one program is executed by the at least one processor, the at least one processor implements the method for implementing non-invasive blood glucose monitoring.

[0140] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0141] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned method for implementing non-invasive blood glucose monitoring.

[0142] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0143] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0144] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0145] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0146] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0147] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0148] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0149] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0150] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0151] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A non-invasive blood glucose monitoring system, characterized in that: The monitoring system includes: a metabolic heat non-invasive sensor, an analog front end, and a control module; The control module is used to receive the physiological index data measured by the metabolic heat non-invasive sensor, and perform blood sugar prediction based on the physiological index data through a blood sugar prediction model to obtain a blood sugar value; The analog front end is detachably connected to the control module; the analog front end is used to obtain an electrical signal through a minimally invasive sensor if the blood sugar value needs to be calibrated, and transmit the electrical signal to the control module connected to the analog front end; the electrical signal corresponds to the actual result of the blood sugar value of the measured object; The control module is used to receive the electrical signal of the analog front end, and to construct or update the blood glucose prediction model based on the electrical signal.

2. The non-invasive blood glucose monitoring system according to claim 1, characterized in that: The analog front end includes an AD5941 chip or an AD5940 chip, the analog ground of the AD5941 chip is connected to the digital ground of the AD5941 chip through a first resistor, and the resistance of the first resistor is 0Ω; the universal interface of the AD5941 chip is connected to the minimally invasive sensor; the analog front end communicates with the control module via SPI.

3. The non-invasive blood glucose monitoring system according to claim 1, characterized in that: The metabolic heat non-invasive sensor includes a first photoelectric sensor, a second photoelectric sensor, a first temperature and humidity sensor, and a second temperature and humidity sensor; the first photoelectric sensor is used to detect the photoelectric signal at the wrist of the measured object, and the second photoelectric sensor is used to detect the photoelectric signal at the finger of the measured object; the first temperature and humidity sensor is installed between the bottom layer of the circuit board and the measured object, the first temperature and humidity sensor is used to detect the skin temperature and humidity signal of the measured object, the second temperature and humidity sensor is installed on the side of the circuit board away from the measured object, and the second temperature and humidity sensor is used to detect the ambient temperature signal; the metabolic heat non-invasive sensor communicates with the control module via IIC.

4. The non-invasive blood glucose monitoring system according to claim 1, characterized in that: The analog front end is connected to the control module via a board-to-board connector.

5. The non-invasive blood glucose monitoring system according to claim 1, characterized in that: The physiological index data measured by the metabolic heat non-invasive sensor is used as the characteristic value of the blood glucose prediction model training, and the electrical signal measured by the minimally invasive sensor is used as the true value of the blood glucose prediction model training, so as to train the blood glucose prediction model.

6. The non-invasive blood glucose monitoring system according to claim 1, characterized in that: The monitoring system also includes a power supply module, the first power supply outputs the second power supply through a voltage regulator, the second power supply is grounded through a first capacitor, the second power supply is grounded through a second capacitor, and the second power supply is grounded through a third capacitor, and the capacity of the first capacitor is greater than the capacity of the second capacitor and the third capacitor.

7. A method for implementing non-invasive blood glucose monitoring, characterized in that: Applied to the non-invasive blood glucose monitoring system according to any one of claims 1 to 6, the method comprising: Receiving physiological index data measured by a metabolic heat non-invasive sensor, and performing blood sugar prediction based on the physiological index data using a blood sugar prediction model to obtain a blood sugar value; If the blood glucose value needs to be calibrated, an electrical signal obtained by a minimally invasive sensor is received, and based on the electrical signal, the blood glucose prediction model is constructed or updated.

8. The method for implementing non-invasive blood glucose monitoring according to claim 7, characterized in that: The blood sugar prediction model is trained by the following steps: Inputting the physiological indicator data into the blood glucose prediction model to obtain a blood glucose prediction result; According to the electrical signal, the actual result of blood sugar is determined, and the loss value is calculated using a loss function according to the blood sugar prediction result and the actual result, and the parameters of the blood sugar prediction model are updated according to the loss value to obtain the trained blood sugar prediction model.

9. The method for implementing non-invasive blood glucose monitoring according to claim 7, characterized in that: The method further comprises: Communicating with the metabolic heat non-invasive sensor via IIC; Communicate with the minimally invasive sensor via SPI.

10. A non-invasive blood glucose monitoring device, characterized in that: A non-invasive blood glucose monitoring system comprising any one of claims 1 to 6.

Citation Information

Patent Citations

  • Noninvasive blood glucose measurement device and method

    CN110123339A

  • Blood glucose detection system

    CN116965810A

  • Human body blood sugar noninvasive detector and detection method

    CN117838114A

  • Noninvasive blood glucose dynamic monitoring equipment, determination method and system

    CN118319298A

  • Blood sugar measuring instrument and blood sugar measuring system

    JP1999056823A