CN115624328A - Infrared emitter of noninvasive glucose meter and glucose meter - Google Patents
Infrared emitter of noninvasive glucose meter and glucose meter Download PDFInfo
- Publication number
- CN115624328A CN115624328A CN202211382976.0A CN202211382976A CN115624328A CN 115624328 A CN115624328 A CN 115624328A CN 202211382976 A CN202211382976 A CN 202211382976A CN 115624328 A CN115624328 A CN 115624328A
- Authority
- CN
- China
- Prior art keywords
- infrared
- blood glucose
- signal
- light
- module
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
- A61B5/7228—Signal modulation applied to the input signal sent to patient or subject; demodulation to recover the physiological signal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Optics & Photonics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Emergency Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an infrared emitter of a noninvasive glucometer and the glucometer, comprising: the system comprises a noninvasive sensor, a photoelectric conversion module, an intelligent management and control platform and a blood glucose detection terminal, wherein the noninvasive sensor, the photoelectric conversion module, the intelligent management and control platform and the blood glucose detection terminal are integrated; the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissues, the infrared light penetrates through the human skin tissues to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal. The infrared light is selected for blood sugar measurement, so that the human skin tissue can be measured without pretreatment, and the integrated noninvasive sensor directly measures the human skin tissue by virtue of the stronger penetrating power and scattering effect of the infrared light, so that the rapid and efficient analysis efficiency is realized, the test cost is low, and the change trend of the blood sugar can be better reflected.
Description
Technical Field
The invention relates to the technical field of noninvasive blood glucose detection, in particular to an infrared transmitter of a noninvasive blood glucose meter and the blood glucose meter.
Background
Diabetes mellitus is a chronic metabolic disorder that causes a series of serious effects on human organs with complications. Complications of this disease can be prevented by regular blood glucose concentration detection and control of blood glucose concentration by medication or other means. Most of the available blood glucose testing devices on the market are invasive or minimally invasive. Invasive blood glucose test devices are inconvenient and painful to use, and minimally invasive blood glucose test devices are limited in sustainability and stability of use. Therefore, there is a need for the development of an economical, simple, painless and portable non-invasive blood glucose monitoring device that combines infrared technology with non-invasive blood glucose monitoring with the rapid development of infrared analysis technology to more effectively predict blood glucose concentration.
Disclosure of Invention
The invention provides an infrared emitter of a noninvasive glucometer and the glucometer, aiming at solving the problem that diabetes in the prior art is a chronic metabolic disorder which causes a series of serious effects on human organs and is accompanied with complications. Complications of this disease can be prevented by regular blood glucose concentration detection and control of blood glucose concentration by medication or other means. Most of the available blood glucose testing devices on the market are invasive or minimally invasive. Invasive blood glucose test devices are inconvenient and painful to use, and minimally invasive blood glucose test devices are limited in sustainability and stability of use. Therefore, there is a need for the development of an economical, simple, painless and portable non-invasive blood glucose monitoring device, which combines infrared technology with non-invasive blood glucose monitoring with the rapid development of infrared analysis technology, thereby more effectively predicting blood glucose concentration.
In order to achieve the purpose, the invention provides the following technical scheme:
an atraumatic glucose meter, comprising: the system comprises a noninvasive sensor, a photoelectric conversion module, an intelligent management and control platform and a blood sugar detection terminal;
the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissues, the infrared light penetrates through the human skin tissues to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal.
Wherein the integrated non-invasive sensor comprises: a plurality of infrared transmitters, a plurality of infrared receivers and a plurality of human body physiological parameter detectors;
based on a double-light-path spectral measurement method, a plurality of infrared transmitters are divided into two paths, infrared light emitted by the first path of infrared transmitter is reference light which does not pass through human tissues, the second path of infrared transmitter is measuring light which is diffused and reflected through the human tissues, and the reference light and the measuring light are received by a plurality of infrared receivers in groups to obtain collected infrared spectrum signals;
the human body physiological parameter detectors collect physiological parameters related to human body metabolism by contacting human body skin, and the physiological parameters comprise environment temperature and humidity, human body surface temperature and humidity and pulse wave parameters.
Wherein, intelligence management and control platform includes: the system comprises a data processing module, a cloud database and a machine learning module;
the data processing module is used for converting the electric signals into digital signals and then performing feature extraction operation;
the cloud database is used for storing a large amount of blood sugar detection data and human body physiological parameter detection data in a grading manner;
the machine learning module is used for establishing a training set based on data of the cloud database, optimizing and training the training set and establishing a mapping relation between a blood glucose infrared absorption spectrum and blood glucose concentration.
Wherein the data processing module comprises: a signal conditioning submodule and a feature extraction submodule;
the signal conditioning submodule is used for preprocessing the electric signal and converting the electric signal into a digital signal;
the characteristic extraction submodule is used for extracting the characteristics of the data signals, extracting the blood glucose absorption spectrum under various wavelength spectrums, and filtering the influences of jitter and baseline drift in the characteristic extraction process.
Wherein the cloud database comprises: the system comprises a data intelligent layering module and a data calling module;
the data calling module calls a large amount of blood glucose concentration data based on traditional invasive measurement from a cloud server, calls digital signal data processed by the feature extraction submodule based on the same type of population of the blood glucose concentration data based on the traditional invasive measurement, and divides the blood glucose concentration data based on the traditional invasive measurement into a test set;
and the cloud database is graded through the data intelligent layering module according to the range of the blood glucose concentration value, the gender of the user and the age of the user, wherein the grading comprises a plurality of grades of storage layers.
Wherein the machine learning module comprises: training an algorithm model;
inputting the called blood glucose concentration data and digital signal data of the traditional invasive measurement into a training algorithm model for training, and establishing a relation model between a spectrum signal and the blood glucose concentration through the training process;
inputting the collected spectral signals into a relation model after being used as a training set to obtain a predicted value of blood glucose concentration, measuring a corresponding accurate value based on the predicted value and a correlation coefficient and a relative standard deviation of an actually measured blood glucose value, and optimizing a training algorithm model based on the corresponding accurate value to obtain an optimized training model; and optimizing and training the optimized training model for multiple times to form a mapping relation between the blood glucose infrared absorption spectrum and the blood glucose concentration, and constructing a blood glucose concentration prediction model based on the mapping relation.
The electric signal is preprocessed through the signal conditioning submodule to remove environmental noise of the electric signal and reserve a useful signal frequency band, and then the electric signal is subjected to pre-amplification and low-pass filtering to obtain the preprocessed electric signal;
the method comprises the steps of accessing a preprocessed electric signal into a phase-locked amplifier, detecting the weak degree of the signal through the phase-locked amplifier, rejecting the current electric signal if the frequency of an output signal of the phase-locked amplifier is different from that of a set reference signal, outputting a direct current signal through the phase-locked amplifier if the frequency of the output signal of the phase-locked amplifier is the same as that of the set reference signal, and converting the amplitude of the output direct current signal into a digital signal through an AD converter.
An infrared emitter of noninvasive blood glucose appearance, infrared emitter connect the infrared receiver that corresponds, infrared emitter includes: the device comprises a light-emitting device, an infrared emission driving module, a pulse modulation module and a light path coupling module;
based on the spectroscopic characteristics of blood sugar, a light-emitting device with a spectrum band with blood sugar specificity absorption sensitivity is selected, an infrared emission driving module adjusts the spectrum broadening of the light-emitting device to be a set standard spectrum broadening and then drives the light-emitting device to send infrared light, the interference of background light, stray light and dark current of the infrared light is eliminated through a pulse modulation module, then the difference of optical path paths of different light sources in a light absorption medium is compensated through optical fiber coupling of the infrared light through an optical path coupling module, and finally the infrared light is received by an infrared receiver.
Wherein, infrared emission drive module includes: a sawtooth wave generator;
the light emitting device adopts light emitting diodes with strong center wavelengths of 700nm, 1350nm, 1450nm and 1550nm which penetrate through the dermis layer of a human body as radiation light sources of the infrared emitter;
the infrared emission driving module controls the voltage locking of the sawtooth wave generator to enable the voltage output by the sawtooth wave generator to be a constant value, and therefore the intensity of infrared light emitted by the infrared emitter is controlled to be unchanged.
Wherein, the pulse modulation module includes: a frequency selection sub-module;
based on the frequency selection submodule, reserving useful frequency signals of infrared light, simultaneously preventing interference of the frequency signals and acquiring a high-efficiency signal-to-noise ratio;
based on the blood sugar detection concentration and the signal-to-noise ratio, the relation between the signal-to-noise ratio and the blood sugar detection limit concentration is established through calculation, the controllable range of infrared light is determined based on the relation between the signal-to-noise ratio and the blood sugar detection limit concentration, and the infrared emission driving module is used for driving and controlling the light-emitting device.
Compared with the prior art, the invention has the following advantages:
an noninvasive glucometer comprising: the system comprises a noninvasive sensor, a photoelectric conversion module, an intelligent management and control platform and a blood sugar detection terminal; the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissues, the infrared light penetrates through the human skin tissues to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal. The infrared light is selected for blood sugar measurement, so that the human skin tissue can be measured without pretreatment, the integrated noninvasive sensor directly measures the human skin tissue by virtue of the stronger penetration capability and scattering effect of the infrared light, the high-efficiency analysis efficiency is realized, the test cost is low, and the change trend of the blood sugar can be better reflected.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an noninvasive glucometer according to an embodiment of the present invention;
FIG. 2 is a flow chart of a non-invasive glucose meter according to an embodiment of the present invention;
fig. 3 is a structural diagram of an intelligent management and control platform in the noninvasive glucose meter according to the embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides a noninvasive glucometer, which comprises: the system comprises a noninvasive sensor, a photoelectric conversion module, an intelligent management and control platform and a blood sugar detection terminal;
the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissue, the infrared light penetrates through the human skin tissue to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal.
The working principle of the technical scheme is as follows: the method comprises the steps that an infrared emitter and a corresponding infrared receiver in an integrated noninvasive sensor are placed on two sides of a human tissue to be detected to be used as a transmission mode for detection, the infrared emitter and the corresponding infrared receiver are placed on the same side of the human tissue to be detected to be used as a diffuse reflection mode for detection, and the detection is carried out in combination with the transmission mode and the diffuse reflection mode, wherein the detection mode of blood glucose concentration can be set through a blood glucose detection terminal; establishing a relation model of near-infrared luminosity data and blood sugar through an intelligent control platform, processing the collected infrared light through the intelligent control platform, analyzing the data through the relation model of the near-infrared luminosity data and the blood sugar to obtain blood sugar concentration, and checking the blood sugar concentration through a blood sugar detection terminal by a user;
the blood sugar detection terminal comprises a mobile phone APP terminal, account information of a user can be managed through the mobile phone APP terminal, relevant data of the user can be processed, and collected various detection data can be sorted to derive Excel files forming a training set and a testing set of the blood sugar concentration prediction model. The result obtained by the blood glucose concentration prediction model can be made into a corresponding relation table of blood glucose and detection parameters and uploaded to the intelligent control platform, so that the blood glucose concentration prediction model is beneficial to quickly obtaining a blood glucose prediction result and is convenient for daily use of a user. Meanwhile, the relation table can be updated in time according to the change of the detection conditions by the mobile phone APP terminal correction approval function, so that the blood sugar prediction result can keep accuracy.
And entering a correction approval interface of the APP end of the mobile phone, seeing an unprocessed correction information list, selecting a row where data to be processed are located, exporting corrected data, generating a new relation table through a model, recording and storing the new relation table, adding the new relation table into a relation table of a user, and clearing the row on the correction approval interface after correction approval processing. Due to the change of the body and the environment of the individual, the blood sugar relation table is also updated in time. Therefore, a correction module is further designed, the actually measured blood glucose value of a certain day can be recorded into the system through correction data of the APP terminal of the mobile phone, a table containing detection indexes such as a predicted value, an actually measured value and photometric data is formed, an Excel table named by a user is formed after the table is exported, the Excel table can serve as a test set of a new prediction model and can expand the number of samples of a training set, and the accuracy rate of the blood glucose concentration prediction model can be further improved.
The beneficial effects of the above technical scheme are: the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissues, the infrared light penetrates through the human skin tissues to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal. The infrared light is selected for blood sugar measurement, so that the human skin tissue can be measured without pretreatment, and the integrated noninvasive sensor directly measures the human skin tissue by virtue of the stronger penetrating power and scattering effect of the infrared light, so that the rapid and efficient analysis efficiency is realized, the test cost is low, and the change trend of the blood sugar can be better reflected.
In another embodiment, the integrated non-invasive sensor comprises: a plurality of infrared transmitters, a plurality of infrared receivers and a plurality of human body physiological parameter detectors;
based on a double-light-path spectral measurement method, a plurality of infrared transmitters are divided into two paths, infrared light emitted by the first path of infrared transmitter is reference light which does not pass through human tissues, the second path of infrared transmitter is measuring light which is diffused and reflected through the human tissues, and the reference light and the measuring light are received by a plurality of infrared receivers in groups to obtain collected infrared spectrum signals;
the human body physiological parameter detectors collect physiological parameters related to human body metabolism by contacting human body skin, and the physiological parameters comprise environment temperature and humidity, human body surface temperature and humidity and pulse wave parameters.
The working principle of the technical scheme is as follows: gather two way infrared light, can carry out contrastive analysis with two way infrared light, acquire the influence of environment to infrared receipt through the reference light, environmental impact includes: measuring the influence of variables such as ambient temperature, humidity and the like, and then processing the measuring light to eliminate the influence of the ambient on infrared light reception;
in actual measurement, the infrared light is also influenced by the body temperature, the heart rate (pulse), the diastolic pressure, the systolic pressure and other human physiological parameter variables of a person to be measured, so that the human physiological parameters are collected through a plurality of human physiological parameter detectors.
The beneficial effects of the above technical scheme are: based on a double-light-path spectral measurement method, a plurality of infrared transmitters are divided into two paths, infrared light emitted by the first path of infrared transmitter is reference light which does not pass through human tissues, the second path of infrared transmitter is measuring light which is diffused and reflected through the human tissues, and the reference light and the measuring light are received by a plurality of infrared receivers in groups to obtain collected infrared spectrum signals; the human body physiological parameter detectors collect physiological parameters related to human body metabolism by contacting human body skin, and the physiological parameters comprise environment temperature and humidity, human body surface temperature and humidity and pulse wave parameters. Interference factors are eliminated by measuring data for detecting infrared light, so that the accuracy of the blood glucose concentration prediction model is further improved.
In another embodiment, the intelligent management and control platform comprises: the system comprises a data processing module, a cloud database and a machine learning module;
the data processing module is used for converting the electric signals into digital signals and then performing feature extraction operation;
the cloud database is used for storing a large amount of blood sugar detection data and human body physiological parameter detection data in a grading manner;
the machine learning module is used for establishing a training set based on data of the cloud database, optimizing and training the training set and establishing a mapping relation between a blood glucose infrared absorption spectrum and blood glucose concentration.
The working principle of the technical scheme is as follows: the detection data are stored in a grading mode, so that the data can be called and the blood sugar detection terminal can check the data conveniently, the measured body temperature, the heart rate (pulse), the diastolic pressure and the systolic pressure, the measurement environment temperature, the humidity and other parameters are used for building the mapping relation between the blood sugar infrared absorption spectrum and the blood sugar concentration, an accurate prediction model is obtained, and the prediction model can be updated according to the updated data of the cloud database. The cloud database makes the hierarchically stored data into a table, the table is input into the prediction model through the intelligent control platform, the predicted blood glucose value can be obtained through training, and the table is stored in the cloud database.
The beneficial effects of the above technical scheme are: the data processing module is used for converting the electric signals into digital signals and then performing feature extraction operation; the cloud database is used for storing a large amount of blood sugar detection data and human body physiological parameter detection data in a grading manner; the machine learning module is used for establishing a training set based on data of the cloud database, optimizing and training the training set and establishing a mapping relation between a blood glucose infrared absorption spectrum and blood glucose concentration. Thereby further improving the accuracy of the blood glucose concentration prediction model.
In another embodiment, the data processing module comprises: a signal conditioning submodule and a feature extraction submodule;
the signal conditioning submodule is used for preprocessing the electric signal and converting the electric signal into a digital signal;
the characteristic extraction submodule is used for extracting the characteristics of the data signals, extracting the blood glucose absorption spectrum under various wavelength spectrums, and filtering the influences of jitter and baseline drift in the characteristic extraction process.
The working principle of the technical scheme is as follows: infrared light intensity signals are very weak, and even if the amplitude of high-frequency interference is not large, the influence of the infrared light intensity signals on the signals is very serious, so that filtering must be considered; because the near-infrared light intensity signal belongs to a low-frequency signal, and the frequency components are mainly concentrated within 100Hz, a low-pass filter with the cut-off frequency of 100Hz is adopted to filter the infrared light, then the infrared light is subjected to AD conversion by conditioning the amplitude of the signal, the conditioned light intensity signal is converted into a digital signal by a photoelectric conversion module, the data signal is subjected to feature extraction, and in the process of feature extraction, the influences of jitter and baseline drift are filtered.
The beneficial effects of the above technical scheme are: the signal conditioning submodule is used for preprocessing the electric signal and converting the electric signal into a digital signal; the characteristic extraction submodule is used for extracting the characteristics of the data signals, extracting the blood glucose absorption spectrum under various wavelength spectrums, and filtering the influences of jitter and baseline drift in the characteristic extraction process. Thereby further improving the accuracy of the blood glucose concentration prediction model.
In another embodiment, the cloud database comprises: the system comprises a data intelligent layering module and a data calling module;
the data calling module calls a large amount of blood glucose concentration data based on traditional invasive measurement from a cloud server, calls digital signal data processed by the feature extraction submodule based on the same type of population of the blood glucose concentration data based on the traditional invasive measurement, and divides the blood glucose concentration data based on the traditional invasive measurement into a test set;
and the cloud database is graded through the data intelligent layering module according to the range of the blood glucose concentration value, the gender of the user and the age of the user, and the grading comprises a plurality of grades of storage layers.
The working principle of the technical scheme is as follows: the data calling module calls a large amount of blood glucose concentration data based on traditional invasive measurement from a cloud server, calls digital signal data processed by the feature extraction submodule for the same type of people based on the blood glucose concentration data based on the traditional invasive measurement, and divides the blood glucose concentration data based on the traditional invasive measurement into a test set; the cloud database is graded according to the range of the blood glucose concentration value, the gender of the user and the age of the user through the data intelligent layering module, the grading comprises a plurality of grades of storage layers, and the range of the blood glucose concentration value comprises: higher than normal, lower than normal, user gender is: male, female, user age segmentation includes: the young, the middle-aged and the old have 18 storage layers in total, and the retrieval and the checking of data are quickened through layering, so that the interference of external factors such as gender, age, physical condition and the like is more effectively eliminated.
The beneficial effects of the above technical scheme are: the data calling module calls a large amount of blood glucose concentration data based on traditional invasive measurement from a cloud server, calls digital signal data processed by the feature extraction submodule for the same type of people based on the blood glucose concentration data based on the traditional invasive measurement, and divides the blood glucose concentration data based on the traditional invasive measurement into a test set; and the cloud database is graded through the data intelligent layering module according to the range of the blood glucose concentration value, the gender of the user and the age of the user, and the grading comprises a plurality of grades of storage layers. Thereby further improving the accuracy of the blood glucose concentration prediction model.
In another embodiment, the machine learning module comprises: training an algorithm model;
inputting the called blood glucose concentration data and digital signal data of the traditional invasive measurement into a training algorithm model for training, and establishing a relation model between a spectrum signal and the blood glucose concentration through the training process;
inputting the collected spectral signals into a relation model after being used as a training set to obtain a predicted value of blood glucose concentration, measuring a corresponding accurate value based on the predicted value and a correlation coefficient and a relative standard deviation of an actually measured blood glucose value, and optimizing a training algorithm model based on the corresponding accurate value to obtain an optimized training model; and optimizing and training the optimized training model for multiple times to form a mapping relation between the blood glucose infrared absorption spectrum and the blood glucose concentration, and constructing a blood glucose concentration prediction model based on the mapping relation.
The working principle of the technical scheme is as follows: inputting the called blood glucose concentration data and digital signal data of the traditional invasive measurement into a training algorithm model for training, and establishing a relation model between a spectrum signal and the blood glucose concentration through the training process; inputting the collected spectral signals into a relation model after being used as a training set to obtain a predicted value of blood glucose concentration, measuring a corresponding accurate value based on the predicted value and a correlation coefficient and a relative standard deviation of an actually measured blood glucose value, and optimizing a training algorithm model based on the corresponding accurate value to obtain an optimized training model; and optimizing and training the optimized training model for multiple times to form a mapping relation between the blood glucose infrared absorption spectrum and the blood glucose concentration, and constructing a blood glucose concentration prediction model based on the mapping relation.
Theoretically, the blood glucose concentration and the acquired infrared spectrum information should be linearly related, but because of the influence of objective factors, a nonlinear relation is often presented between the two parameters, so that modeling needs to be carried out through an improved nonlinear modeling mode, a mathematical model between the spectral absorbances of 700nm, 1350nm, 1450nm and 1550nm and the blood glucose concentration is firstly established, the spectral absorbances of 4 different wave bands are used as input layers, the blood glucose concentration of a human body is used as an output layer, wherein the number of nodes of the input layer of the nonlinear relation model is 4, the number of nodes of the output layer is 1, and then a three-layer nonlinear relation model with the number of hidden layer layers being 1 is established. The formula of the model is as follows:
wherein Y represents the output value of the nonlinear relation model, H represents the unit step function (when the argument value of the function is positive, the function output is 1, otherwise it is 0), X i Spectral absorbance value, K, representing the i-th dimension input i Connection weight, K, representing the ith dimension 0 Representing an initial connection weight;
when the sum of the received information exceeds a certain threshold value, the nonlinear relation model is activated and transmits the information to the next data layer through connection conversion, and the processing of the data information are completed by obtaining the output value of the nonlinear relation model, so that a more accurate prediction model is obtained.
The beneficial effects of the above technical scheme are: inputting the called blood glucose concentration data and the called digital signal data of the traditional invasive measurement into a training algorithm model for training, and establishing a relation model between the spectrum signal and the blood glucose concentration through the training process; inputting the collected spectrum signals serving as a training set into a relation model to obtain a predicted value of blood glucose concentration, measuring a corresponding accurate value based on the predicted value and a correlation coefficient and a relative standard deviation of an actually measured blood glucose value, and optimizing a training algorithm model based on the corresponding accurate value to obtain an optimized training model; and optimizing and training the optimized training model for multiple times to form a mapping relation between the blood glucose infrared absorption spectrum and the blood glucose concentration, and constructing a blood glucose concentration prediction model based on the mapping relation. Thereby obtaining a more accurate prediction model.
In another embodiment, the electrical signal is preprocessed through the signal conditioning submodule to remove the environmental noise of the electrical signal and reserve a useful signal frequency band, and then the electrical signal is subjected to pre-amplification and low-pass filtering processing to obtain a preprocessed electrical signal;
the method comprises the steps of accessing a preprocessed electric signal into a phase-locked amplifier, detecting the weak degree of the signal through the phase-locked amplifier, rejecting the current electric signal if the frequency of an output signal of the phase-locked amplifier is different from that of a set reference signal, outputting a direct current signal through the phase-locked amplifier if the frequency of the output signal of the phase-locked amplifier is the same as that of the set reference signal, and converting the amplitude of the output direct current signal into a digital signal through an AD converter.
The working principle of the technical scheme is as follows: the electric signal is preprocessed through the signal conditioning submodule to remove the environmental noise of the electric signal and reserve a useful signal frequency band, and then the electric signal is subjected to pre-amplification and low-pass filtering processing to obtain the preprocessed electric signal; the method comprises the steps of accessing a preprocessed electric signal into a phase-locked amplifier, detecting the weak degree of the signal through the phase-locked amplifier, rejecting the current electric signal if the frequency of an output signal of the phase-locked amplifier is different from that of a set reference signal, outputting a direct current signal through the phase-locked amplifier if the frequency of the output signal of the phase-locked amplifier is the same as that of the set reference signal, and converting the amplitude of the output direct current signal into a digital signal through an AD converter. Thereby obtaining a more accurate prediction model.
The beneficial effects of the above technical scheme are: the electric signal is preprocessed through the signal conditioning submodule to remove environmental noise of the electric signal and reserve a useful signal frequency band, and then the electric signal is subjected to pre-amplification and low-pass filtering processing to obtain the preprocessed electric signal; the method comprises the steps of accessing a preprocessed electric signal into a phase-locked amplifier, detecting the weak degree of the signal through the phase-locked amplifier, rejecting the current electric signal if the frequency of an output signal of the phase-locked amplifier is different from that of a set reference signal, outputting a direct current signal through the phase-locked amplifier if the frequency of the output signal of the phase-locked amplifier is the same as that of the set reference signal, and converting the amplitude of the output direct current signal into a digital signal through an AD converter. Thereby obtaining a more accurate prediction model.
In another embodiment, an infrared transmitter of a noninvasive glucometer is connected with a corresponding infrared receiver, and the infrared transmitter comprises: the device comprises a light-emitting device, an infrared emission driving module, a pulse modulation module and a light path coupling module;
based on the spectroscopic characteristics of blood sugar, a light-emitting device with a spectrum band with blood sugar specificity absorption sensitivity is selected, an infrared emission driving module adjusts the spectrum broadening of the light-emitting device to be a set standard spectrum broadening and then drives the light-emitting device to send infrared light, the interference of background light, stray light and dark current of the infrared light is eliminated through a pulse modulation module, then the difference of optical path paths of different light sources in a light absorption medium is compensated through optical fiber coupling of the infrared light through an optical path coupling module, and finally the infrared light is received by an infrared receiver.
The working principle of the technical scheme is as follows: based on the spectroscopic characteristics of blood sugar, a light emitting device with a spectrum waveband with specific absorption sensitivity of blood sugar is selected, the infrared emission driving module adjusts the spectrum broadening of the light emitting device to a set standard spectrum broadening and then drives the light emitting device to send infrared light, the interference of background light, stray light and dark current is eliminated by the infrared light through the pulse modulation module, then the difference of optical path paths of different light sources in a light absorption medium is compensated by the optical path coupling module through optical fiber coupling of the infrared light, and finally the infrared light is received by the infrared receiver.
The spectral bands sensitive to specific absorption of blood glucose are selected, and those spectral bands insensitive to blood glucose absorption are also selected as references. The light source spectrum band formed by combining the two spectrum bands with different characteristics can reduce the measurement error of the system when a correction model is established at the later stage.
The beneficial effects of the above technical scheme are: based on the spectroscopic characteristics of blood sugar, a light emitting device with a spectrum waveband with specific absorption sensitivity of blood sugar is selected, the infrared emission driving module adjusts the spectrum broadening of the light emitting device to a set standard spectrum broadening and then drives the light emitting device to send infrared light, the interference of background light, stray light and dark current is eliminated by the infrared light through the pulse modulation module, then the difference of optical path paths of different light sources in a light absorption medium is compensated by the optical path coupling module through optical fiber coupling of the infrared light, and finally the infrared light is received by the infrared receiver.
In another embodiment, an infrared emission driving module includes: a sawtooth wave generator;
the light emitting device adopts light emitting diodes with strong center wavelengths of 700nm, 1350nm, 1450nm and 1550nm which penetrate through the dermis layer of a human body as radiation light sources of the infrared emitter;
the infrared emission driving module controls the voltage locking of the sawtooth generator to make the voltage output by the sawtooth generator be a constant value, thereby controlling the intensity of the infrared light emitted by the infrared emitter to be unchanged.
The working principle of the technical scheme is as follows: the light emitting device selects the light emitting diodes with the strong central wavelengths of 700nm, 1350nm, 1450nm and 1550nm which penetrate through the dermis layer of a human body as radiation light sources of the infrared emitter, the selected light emitting diodes have 4 different wave bands, the positions of the central wavelengths of the light emitting diodes are accurate, and although the light emitting diodes have different degrees of spectrum broadening, the light emitting diodes are used as the radiation light sources of the near infrared spectrum non-invasive blood sugar detection system, and the broadening range of the degrees can be accepted;
the infrared emission driving module controls the voltage locking of the sawtooth wave generator to make the voltage output by the sawtooth wave generator constant, thereby controlling the intensity of the infrared light emitted by the infrared emitter to be unchanged
The beneficial effects of the above technical scheme are: the light emitting device adopts light emitting diodes with strong center wavelengths of 700nm, 1350nm, 1450nm and 1550nm which penetrate through the dermis of a human body as radiation light sources of the infrared emitter; the infrared emission driving module controls the voltage locking of the sawtooth wave generator to enable the voltage output by the sawtooth wave generator to be a constant value, and therefore the intensity of infrared light emitted by the infrared emitter is controlled to be unchanged. The blood glucose absorption spectrum under various wavelength spectrums is extracted, so that the detection precision is improved.
In another embodiment, the pulse modulation module comprises: a frequency selection sub-module;
based on the frequency selection submodule, useful frequency signals of infrared light are reserved, meanwhile, the frequency signals are prevented from being interfered, and a high-efficiency signal-to-noise ratio is obtained;
based on the blood sugar detection concentration and the signal-to-noise ratio, the relation between the signal-to-noise ratio and the blood sugar detection limit concentration is established through calculation, the controllable range of infrared light is determined based on the relation between the signal-to-noise ratio and the blood sugar detection limit concentration, and the infrared emission driving module is used for driving and controlling the light-emitting device.
The working principle of the technical scheme is as follows: the interference signal is superposed on the detected useful signal, so that filtering is required to be introduced to improve the signal-to-noise ratio, the useful frequency signal of the infrared light is reserved based on the frequency selection submodule, the interference frequency signal is prevented, and the high-efficiency signal-to-noise ratio is obtained; based on the blood sugar detection concentration and the signal-to-noise ratio, the relation between the signal-to-noise ratio and the blood sugar detection limit concentration is established through calculation, the controllable range of infrared light is determined based on the relation between the signal-to-noise ratio and the blood sugar detection limit concentration, and the infrared emission driving module is used for driving and controlling the light-emitting device.
The beneficial effects of the above technical scheme are: based on the frequency selection submodule, reserving useful frequency signals of infrared light, simultaneously preventing interference of the frequency signals and acquiring a high-efficiency signal-to-noise ratio; based on the blood sugar detection concentration and the signal-to-noise ratio, the relation between the signal-to-noise ratio and the blood sugar detection limit concentration is established through calculation, the controllable range of infrared light is determined based on the relation between the signal-to-noise ratio and the blood sugar detection limit concentration, and the infrared emission driving module is used for driving and controlling the light-emitting device.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A noninvasive glucometer, comprising: the system comprises a noninvasive sensor, a photoelectric conversion module, an intelligent management and control platform and a blood sugar detection terminal;
the intelligent control platform controls the integrated noninvasive sensor to emit infrared light to human skin tissue, the infrared light penetrates through the human skin tissue to diffuse and reflect spectral signals, the photoelectric conversion module converts the received spectral signals into electric signals, the intelligent control platform converts the electric signals into digital signals and then performs feature extraction and parameter analysis on the digital signals to obtain blood glucose concentration, and a user checks the blood glucose concentration through the blood glucose detection terminal.
2. The noninvasive glucometer of claim 1, wherein the integrated noninvasive sensor comprises: a plurality of infrared transmitters, a plurality of infrared receivers and a plurality of human body physiological parameter detectors;
based on a double-light-path spectral measurement method, a plurality of infrared transmitters are divided into two paths, infrared light emitted by the first path of infrared transmitter is reference light which does not pass through human tissues, the second path of infrared transmitter is measuring light which is diffused and reflected through the human tissues, and the reference light and the measuring light are received by a plurality of infrared receivers in groups to obtain collected infrared spectrum signals;
the human body physiological parameter detectors collect physiological parameters related to human body metabolism by contacting human body skin, wherein the physiological parameters comprise environment temperature and humidity, human body surface temperature and humidity and pulse wave parameters.
3. The noninvasive glucometer according to claim 1, wherein the intelligent management and control platform comprises: the system comprises a data processing module, a cloud database and a machine learning module;
the data processing module is used for converting the electric signals into digital signals and then performing feature extraction operation;
the cloud database is used for storing a large amount of blood sugar detection data and human body physiological parameter detection data in a grading manner;
the machine learning module is used for establishing a training set based on data of the cloud database, optimizing and training the training set and establishing a mapping relation between a blood glucose infrared absorption spectrum and blood glucose concentration.
4. The noninvasive glucometer of claim 3, wherein the data processing module comprises: a signal conditioning submodule and a feature extraction submodule;
the signal conditioning submodule is used for preprocessing the electric signal and converting the electric signal into a digital signal;
the characteristic extraction submodule is used for extracting the characteristics of the data signals, extracting the blood glucose absorption spectrum under various wavelength spectrums, and filtering the influences of jitter and baseline drift in the characteristic extraction process.
5. The noninvasive glucometer of claim 3, wherein the cloud database comprises: the system comprises a data intelligent layering module and a data calling module;
the data calling module calls a large amount of blood glucose concentration data based on traditional invasive measurement from a cloud server, calls digital signal data processed by the feature extraction submodule based on the same type of population of the blood glucose concentration data based on the traditional invasive measurement, and divides the blood glucose concentration data based on the traditional invasive measurement into a test set;
and the cloud database is graded through the data intelligent layering module according to the range of the blood glucose concentration value, the gender of the user and the age of the user, and the grading comprises a plurality of grades of storage layers.
6. The noninvasive glucometer of claim 3, wherein the machine learning module comprises: training an algorithm model;
inputting the called blood glucose concentration data and digital signal data of the traditional invasive measurement into a training algorithm model for training, and establishing a relation model between a spectrum signal and the blood glucose concentration through the training process;
inputting the collected spectrum signals serving as a training set into a relation model to obtain a predicted value of blood glucose concentration, measuring a corresponding accurate value based on the predicted value and a correlation coefficient and a relative standard deviation of an actually measured blood glucose value, and optimizing a training algorithm model based on the corresponding accurate value to obtain an optimized training model; and optimizing and training the optimized training model for multiple times to form a mapping relation between the blood glucose infrared absorption spectrum and the blood glucose concentration, and constructing a blood glucose concentration prediction model based on the mapping relation.
7. The noninvasive glucometer according to claim 4, wherein the electrical signal is preprocessed by the signal conditioning submodule to remove the environmental noise of the electrical signal and reserve the useful signal frequency band, and then the electrical signal is pre-amplified and low-pass filtered to obtain the preprocessed electrical signal;
the method comprises the steps of accessing a preprocessed electric signal into a phase-locked amplifier, detecting the weak degree of the signal through the phase-locked amplifier, rejecting the current electric signal if the frequency of an output signal of the phase-locked amplifier is different from that of a set reference signal, outputting a direct current signal through the phase-locked amplifier if the frequency of the output signal of the phase-locked amplifier is the same as that of the set reference signal, and converting the amplitude of the output direct current signal into a digital signal through an AD converter.
8. The utility model provides an infrared emitter of noninvasive blood glucose meter which characterized in that, infrared emitter connects corresponding infrared receiver, and infrared emitter includes: the device comprises a light-emitting device, an infrared emission driving module, a pulse modulation module and a light path coupling module;
based on the spectroscopic characteristics of blood sugar, a light emitting device with a spectrum waveband with specific absorption sensitivity of blood sugar is selected, the infrared emission driving module adjusts the spectrum broadening of the light emitting device to a set standard spectrum broadening and then drives the light emitting device to send infrared light, the interference of background light, stray light and dark current is eliminated by the infrared light through the pulse modulation module, then the difference of optical path paths of different light sources in a light absorption medium is compensated by the optical path coupling module through optical fiber coupling of the infrared light, and finally the infrared light is received by the infrared receiver.
9. The infrared transmitter of the noninvasive glucometer according to claim 8, wherein the infrared transmission driving module comprises: a sawtooth wave generator;
the light emitting device adopts light emitting diodes with strong center wavelengths of 700nm, 1350nm, 1450nm and 1550nm which penetrate through the dermis layer of a human body as radiation light sources of the infrared emitter;
the infrared emission driving module controls the voltage locking of the sawtooth wave generator to enable the voltage output by the sawtooth wave generator to be a constant value, and therefore the intensity of infrared light emitted by the infrared emitter is controlled to be unchanged.
10. The infrared transmitter of claim 8, wherein the pulse modulation module comprises: a frequency selection sub-module;
based on the frequency selection submodule, useful frequency signals of infrared light are reserved, meanwhile, the frequency signals are prevented from being interfered, and a high-efficiency signal-to-noise ratio is obtained;
based on the blood sugar detection concentration and the signal-to-noise ratio, the relation between the signal-to-noise ratio and the blood sugar detection limit concentration is established through calculation, the controllable range of infrared light is determined based on the relation between the signal-to-noise ratio and the blood sugar detection limit concentration, and the infrared emission driving module is used for driving and controlling the light-emitting device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211382976.0A CN115624328A (en) | 2022-11-07 | 2022-11-07 | Infrared emitter of noninvasive glucose meter and glucose meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211382976.0A CN115624328A (en) | 2022-11-07 | 2022-11-07 | Infrared emitter of noninvasive glucose meter and glucose meter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115624328A true CN115624328A (en) | 2023-01-20 |
Family
ID=84908659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211382976.0A Pending CN115624328A (en) | 2022-11-07 | 2022-11-07 | Infrared emitter of noninvasive glucose meter and glucose meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115624328A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115969366A (en) * | 2023-03-05 | 2023-04-18 | 北京大学第三医院（北京大学第三临床医学院） | Blood glucose measurement method based on near-infrared absorption spectrum-impedance spectrum analysis combination |
| CN116138771A (en) * | 2023-04-18 | 2023-05-23 | 江西科技师范大学 | Energy correction method for multispectral blood glucose photoacoustic detection |
-
2022
- 2022-11-07 CN CN202211382976.0A patent/CN115624328A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115969366A (en) * | 2023-03-05 | 2023-04-18 | 北京大学第三医院（北京大学第三临床医学院） | Blood glucose measurement method based on near-infrared absorption spectrum-impedance spectrum analysis combination |
| CN116138771A (en) * | 2023-04-18 | 2023-05-23 | 江西科技师范大学 | Energy correction method for multispectral blood glucose photoacoustic detection |
| CN116138771B (en) * | 2023-04-18 | 2023-06-30 | 江西科技师范大学 | Energy correction method for multispectral blood glucose photoacoustic detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115624328A (en) | Infrared emitter of noninvasive glucose meter and glucose meter | |
| CN100335001C (en) | Diagnostic method and device using light | |
| US10085656B2 (en) | Measurement device, measurement method, program and recording medium | |
| Habbu et al. | Estimation of blood glucose by non-invasive method using photoplethysmography | |
| WO2017024457A1 (en) | Blood-pressure continuous-measurement device, measurement model establishment method, and system | |
| KR102033914B1 (en) | method for measuring blood glucose and wearable type apparatus for the same | |
| CN105193423A (en) | Non-invasive blood glucose detection method, device and system | |
| WO2003071939A1 (en) | Active pulse spectraphotometry | |
| CN102245103A (en) | System and apparatus for non-invasive measurement of glucose levels in blood | |
| CN100482154C (en) | Portable near-infrared detection apparatus for human body local plasma volume variation parameter | |
| CN1314368C (en) | Method and apparatus for measuring a concentration of a component in a subject | |
| CN107296616A (en) | Portable non-invasive blood sugar test device and method | |
| WO2017112753A1 (en) | Devices and methods for predicting hemoglobin levels using electronic devices such as mobile phones | |
| CN112130663B (en) | EEG-NIRS-based target recognition training system and method | |
| KR101919229B1 (en) | Apparatus and method for measuring a biometrics information | |
| Prabha et al. | Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters | |
| CN105249974A (en) | Pressure-modulation-spectrum-technology-based noninvasive glucose detection system and method | |
| CN108324286A (en) | A kind of infrared light noninvasive dynamics monitoring device based on PCA-NARX correcting algorithms | |
| US20200093409A1 (en) | Method and device for detecting concentration of total hemoglobin in blood | |
| CN112674739B (en) | Detection device and detection method for biological characteristic information and electronic equipment | |
| Shulei et al. | Non-invasive blood glucose measurement scheme based on near-infrared spectroscopy | |
| WO1997036540A1 (en) | Determination of concentrations of biological substances using raman spectroscopy and artificial neural network discriminator | |
| US20140187884A1 (en) | Systems and methods for ensemble averaging in pulse oximetry | |
| KR20210101895A (en) | PPG system with multi-wavelength LEDs for unrestrained non-invasive continuous blood glucose monitoring and Method for controlling the same | |
| CN102727219B (en) | The calibration steps of the blood characteristics of non-intrusion measurement person under inspection and setting and sensor |
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 |