CN108937955A - The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence - Google Patents
The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence Download PDFInfo
- Publication number
- CN108937955A CN108937955A CN201710369650.7A CN201710369650A CN108937955A CN 108937955 A CN108937955 A CN 108937955A CN 201710369650 A CN201710369650 A CN 201710369650A CN 108937955 A CN108937955 A CN 108937955A
- Authority
- CN
- China
- Prior art keywords
- blood glucose
- artificial intelligence
- patient
- blood
- blood sugar
- 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.)
- Withdrawn
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, 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
- A61B5/145—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
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention belongs to blood glucose alignment technique fields, and in particular to the adaptive wearable blood glucose bearing calibration of personalization based on artificial intelligence comprises the concrete steps that: (1) collecting the accurate blood glucose value of the lasting variation of patient；(2) still uncorrected blood glucose value is recorded；(3) the numerical value diversity mode for after being collected into blood glucose numerical value by both modes, being corrected by artificial intelligence deep approach of learning, and this artificial intelligence approach being identified is as the distinctive blood glucose correction mode of the patient；(4) after artificial intelligence learning training finishes, which continues to use Woundless blood sugar monitoring, and is corrected using the obtained data calibration method of artificial intelligence study module training to the blood glucose value recorded.The present invention can be for each different patients, artificial intelligence training study can be adaptively carried out with different patients by the method, the blood glucose bearing calibration identified specifically for the patient is concluded, the blood glucose value of each diabetic for non-invasive is monitored.
Description
Technical field
The invention belongs to blood glucose alignment technique field, in particular to a kind of personalization based on artificial intelligence can adaptively be worn
Wear blood glucose bearing calibration and its means for correcting.
Background technique
In recent years, the disease incidence of diabetes causes great puzzlement to people's lives in trend is risen year by year, oneself passes through
As the chronic disease for seriously threatening human health the third-largest after tumour, cardiovascular pathological changes.China has become diabetes hair
" severely afflicated area " of disease, is global the second big country of diabetes, more allow people's worry is more and more children also at patient of diabetes
Person.
Diabetes are divided into four kinds of different types according to the mechanism of morbidity, wherein falling ill at most is 1 type and diabetes B.
Type 1 diabetes are a kind of autoimmune diseases, account for about the 10% of diabetic's sum, but be more common in children
And teenager, insulin secretion lack, it is necessary to rely on insulin therapy and sustain life.
Diabetes B accounts for about the 90% of diabetic's sum, is mainly in 40 years old or more adult or the elderly, has
Apparent Familial Occurrence, the secretory volume of insulin is not low or even also higher, and the cause of disease is mainly that body is unwise to insulin
Feel (i.e. insulin resistance), what it is in addition there are a few patients trouble is gestational diabetes mellitus or special patients with type Ⅰ DM.Clinically, diabetes
Classical symptom show as " three-many-one-little ", i.e. diuresis, more food, more drinks and thin.Stress when aggravation, occur
Dizziness, Nausea and vomiting, abdominal pain, diuresis aggravate, the serious symptoms such as hypertension, blurred vision, expiratory dyspnea, stupor.Therefore, sugared
Urine patient needs continually to carry out blood sugar test, injects appropriate insulin regulating and controlling blood sugar concentration according to blood sugar concentration.
Currently, clinically through frequently with method be venous blood samples measurement, quick blood sugar radiomete measurement and blood glucose try
Paper slip colorimetric method acquires blood, detects blood sugar concentration by blood sugar analyzer mainly by puncturing patients fingers.It is this
Traditional detection method brings many inconvenient and pain to patient, certain wound can be caused to skin, and refer to
Sharp blood drawing method can only read blood glucose value at a small number of time points, cannot go out in time as a result, bringing perhaps to the diagnosis of the glycosuria state of an illness
It is mostly inconvenient.
Therefore, continue the research field that blood Sugar Monitoring instrument enters diabetes, the companies such as MiniMed, Dexcom push away one after another
Go out a series of blood glucose meters that can be continuously monitored, but will test electrode implantation subcutaneously due to needing to insert broken skin skin with syringe needle,
It is the same with finger blood-taking, some inconvenient and pain can be brought to patient, and be implanted into scorching with the easy induction of subcutaneous electrode probe
Disease reaction, so that detection signal is affected, so it is generally necessary to additionally using the method for finger tip blood drawing, by lasting blood sugar monitoring
Signal be corrected.Therefore a kind of hurtless measure pain, real-time continuous, the rapid detection method of response are needed, this is just established
The basis of non-invasive blood glucose etection theory.
Non-invasive monitoring blood glucose has become the hot spot competitively studied both at home and abroad, and the research of noninvasive dynamics monitoring technology is more at present
Concentrate on spectrum detection technique, comprising: near infrared spectroscopy, mid-infrared light dive method, far red light spectrometry, Raman spectroscopy,
Polarimetry etc., such method are typically all certain positions such as finger, ear, tongue, the abdomen for utilizing the light in the region to irradiate human body
Portion, thigh etc., then receive the optical signal of reflection or transmission by optical detector again, and are analyzed, to determine blood glucose
Concentration.Furthermore there are also the methods of spectroscopic methodology, optoacoustic method, impedance measurement, heat metabolism, the spectroscopic methodology is for Woundless blood sugar monitoring
Refer to through near infrared spectroscopy or mid-infrared light spectrometry or far red light spectrometry or Raman spectroscopy or polarimetry；Optoacoustic method is benefit
The ultrasound signal analyzing blood sugar concentration generated with optoacoustic effect, impedance measurement are hindered using electrolyte caused by glucose
Anti- changes to monitor the concentration of blood glucose；Hot metabolic method is humidity on the basis of spectrum monitoring technology and combination temperature, skin
The series of parameters such as thickness, thus it is speculated that blood sugar concentration.
But since human internal environment is extremely complex, and the physical difference in the different human world is also very big, and non-invasive blood glucose connects
Continuous monitoring cannot accurately detect subcutaneous blood sugar concentration, therefore its clinical application and market are all extremely restricted, and are not yet obtained at present
Obtain clinical approval.But the blood sugar concentration of patient can be monitored in real time in noninvasive dynamics monitoring, can allow doctor accurately and timely
The state of an illness for understanding patient, to reduce the other complication odds of diabetic, while can mitigate patient in blood glucose
In detection process, bring pain due to needing to puncture skin sampling subtracts so as to improve the treatment consciousness of patient for patient
Light spiritual burden.And the method and principle of noninvasive dynamics monitoring are also applied to the detection of human body other compositions such as blood oxygen
In, realize the systematic survey of human body, its hurtless measure, information are not necessarily to reagent, the sound conveniently and in principle comprehensively
Should be fast, precision is high the advantages that, become one of the most promising method detected at present.
Therefore, study a kind of combination set continue blood Sugar Monitoring instrument and noninvasive dynamics monitoring technology blood glucose bearing calibration and
Device is extremely urgent.
Summary of the invention
The purpose of the present invention is overcome the deficiencies in the prior art, discloses a kind of personalization based on artificial intelligence and adaptively may be used
Dress blood glucose bearing calibration, acquire accurate blood glucose value by minimally-invasive glucose monitoring techniques, to non-invasive blood glucose supervise method into
Row training study, the bearing calibration concluded the blood glucose bearing calibration identified specifically for the patient, and non-invasive blood glucose is enabled to supervise
The personalized situation of the patient is adapted to, other subsequent non-invasive blood sugar monitorings are used for, therefore, for each different patients,
Can by the method adaptively with different patients carry out artificial intelligence training study, conclusion identify specifically for
The blood glucose bearing calibration of the patient for non-invasive monitors the blood glucose value of each diabetic.
In order to reach above-mentioned technical purpose, the present invention is realized by following technical scheme:
The adaptive wearable blood glucose bearing calibration of personalization of the present invention based on artificial intelligence, specific steps
It is:
(1) the accurate blood glucose value persistently changed in a period of time of patient is collected: first with minimally-invasive blood sugar monitoring skill
Art collects the accurate blood glucose value of consecutive variations in a period of time from single patient；
(2) it records still uncorrected blood glucose value: recording still uncorrected blood glucose value using Woundless blood sugar monitoring technology；
(3) after being collected into blood glucose numerical value by both modes, the consecutive variations that are collected into minimally-invasive blood sugar monitoring
Accurate blood glucose value on the basis of be worth, by blood glucose value acquired in Woundless blood sugar monitoring technology carry out artificial intelligence learning correction, make
It identifies the degree of blood glucose value acquired in the Woundless blood sugar monitoring technology and practical blood glucose value difference rule with only patient
Rule, and the numerical value diversity mode that this artificial intelligent depth learning method is identified is as the distinctive blood glucose straightening die of the patient
Formula；
(4) after artificial intelligence training finishes, which continues to use Woundless blood sugar monitoring, and is instructed using artificial intelligence
Practice obtained data calibration method to be corrected the blood glucose value recorded.
As the further improvement of above-mentioned technology, above-mentioned steps (1) collect the standard that persistently changes in a period of time of patient
The method of true blood glucose value is the detection method or Fingertip blood glucose monitoring method of dynamic continuous blood sugar monitor.
As the further improvement of above-mentioned technology, Woundless blood sugar monitoring technology described in above-mentioned steps (2) has as follows
It is several:
The first, passes through near infrared spectroscopy or mid-infrared light spectrometry or far red light spectrometry or Raman spectroscopy or optically-active
Then method is received using certain positions such as finger or tongue or abdomen or thigh of light irradiation human body by optical detector
It reflects or is projected back to the optical signal come, and analyzed, to determine that the concentration of blood glucose can be in conjunction with body temperature, metabolic heat, humidity, skin
Thickness, the parameter indexes such as palmic rate conversion blood glucose value.
Second, Woundless blood sugar monitoring technology described in above-mentioned steps (2) refers to: spectroscopic methodology, optoacoustic method, impedance measurement
Method, hot metabolic method.Wherein, the spectroscopic methodology refer to through near infrared spectroscopy or mid-infrared light spectrometry or far red light spectrometry or
Raman spectroscopy or polarimetry；The optoacoustic method is dense using the ultrasound signal analyzing blood glucose of optoacoustic effect generation；The resistance
Anti- mensuration is the concentration that blood glucose is monitored using the variation of electrolyte impedance caused by glucose；Or the Woundless blood sugar
Monitoring technology refers to hot metabolic approach, and the hot metabolic method is on the basis of spectrum monitoring technology and combination temperature or wet
Degree, skin thickness series of parameters, for speculating blood sugar concentration.
As the further improvement of above-mentioned technology, the minimally-invasive glucose monitoring techniques are to continue blood using minimally-invasive
Glucose monitor instrument repeatedly collects accurate data with same a patient, and as the data sample of deep learning, deep learning is obtained
Correction rule and mode applied with same a patient, each patient possesses a set of blood glucose straightening die for meeting itself sign
Formula.
As the further improvement of above-mentioned technology, deep learning is corrected in the method for blood glucose value in above-mentioned steps (2), deep
The data sample of degree study is that multiple test constantly obtains from same a patient, and the data sample of each patient is served together
A patient.
As the further improvement of above-mentioned technology, the artificial intelligence learning correction method includes autocoder skill
Art, deep learning, multilayer neural network method.
As the further improvement of above-mentioned technology, the minimally-invasive continues glucose monitoring techniques and carries out blood sugar test,
5-10000 dextrose equivalent of acquisition daily, and continue 0.5-10 days.
The adaptive wearable blood glucose means for correcting of the personalization that the invention also discloses above-mentioned based on artificial intelligence comprising
The minimally-invasive that realization minimally-invasive continues blood sugar monitoring methods continues blood sugar monitoring instrument, and it is noninvasive to realize that Woundless blood sugar monitoring technology passes through
Blood sugar monitoring instrument, and realize the artificial intelligence learning correction module of artificial intelligence learning correction method, the minimally-invasive continues blood
Three glucose monitor instrument, non-invasive glucose monitor and artificial intelligence learning correction module modules are to connect each other but be to be separated from each other
Or three in one Integrated design, can also establish between these modules data transmission, set in other words existing
The module of standby upper increase data receiver transmission, can make this method more Intelligent portable in this way, can also reduce this method
Cost of labor.
Compared with prior art, the beneficial effects of the present invention are:
(1) personalized adaptive wearable blood glucose bearing calibration of the present invention, by traditional blood glucose meter and at present
Emerging technology artificial intelligence has carried out good combination, carries out blood sugar test using the method for the present invention, on the one hand alleviates and invade
Enter formula and survey blood glucose method to pain brought by diabetic and inconvenience, is on the other hand supervised again for current noninvasive blood glucose
The biggish defect of survey method measurement error is optimized；
(2) present invention improves accuracy rate by artificial intelligence variation autocoder technology, in the blood glucose for solving script
But also with personalized and adaptive advantage on the basis of measurement method, blood can be preferably monitored for different diabetics
Sugared situation.General non-invasive glucose monitor measurement error is greater than 15%, even more greatly, is used for using method proposed by the present invention
Blood glucose value error is measured in 5%-10%, substantially increases the accuracy of blood glucose value.
Detailed description of the invention
The present invention is described in detail in the following with reference to the drawings and specific embodiments:
Fig. 1 is the schematic diagram of blood glucose bearing calibration of the present invention.
Specific embodiment
The adaptive wearable blood glucose bearing calibration of personalization of the present invention based on artificial intelligence, as shown in Figure 1, its
It comprises the concrete steps that:
(1) collect the accurate blood glucose value that persistently changes in a period of time of patient: using minimally-invasive glucose monitoring techniques from
The accurate blood glucose value of consecutive variations in a period of time is collected with single patient；
(2) it records still uncorrected blood glucose value: recording the blood of still uncorrected inaccuracy using Woundless blood sugar monitoring technology
Sugar value；
(3) after being collected into blood glucose numerical value by both modes, the consecutive variations that are collected into minimally-invasive blood sugar monitoring
Accurate blood glucose value as a reference value, blood glucose value acquired in Woundless blood sugar monitoring technology is subjected to artificial intelligence learning correction,
Make the degree of its identification blood glucose value and practical blood glucose value difference acquired in Woundless blood sugar monitoring technology with only patient
Rule, and the numerical value diversity mode that this artificial intelligence approach is identified is as the distinctive blood glucose correction mode of the patient；
(4) after artificial intelligence training finishes, which continues to use Woundless blood sugar monitoring, and is instructed using artificial intelligence
Practice obtained data calibration method to be corrected the blood glucose value recorded.
In the present invention, the method for the accurate blood glucose value persistently changed in a period of time of above-mentioned steps (1) collection patient
The detection method or Fingertip blood glucose monitoring method of dynamic continuous blood sugar monitor, the minimally-invasive continue glucose monitoring techniques into
Promoting circulation of blood sugar detection acquires 5-10000 dextrose equivalent daily, and continues 0.5-10 days, to obtain more accurate blood glucose value.
In the present invention, Woundless blood sugar monitoring technology described in above-mentioned steps (2) there are several types of:
The first, the Woundless blood sugar monitoring technology refers to: by near infrared spectroscopy or mid-infrared light spectrometry or remote red
External spectrum method or Raman spectroscopy or polarimetry utilize certain positions such as finger or tongue or abdomen or big of light irradiation human body
Leg, then by optical detector receive reflection or be projected back to come optical signal, and analyzed, to determine the dense of blood glucose
Degree.
Second, the Woundless blood sugar monitoring technology refers to: optoacoustic method refers to impedance measurement or refers to hot generation
Thank to method, in which: the optoacoustic method is the ultrasound signal analyzing blood sugar concentration generated using optoacoustic effect, the impedance measurement
Method is that the concentration of blood glucose is monitored using the variation of electrolyte impedance caused by glucose, and the hot metabolic method is in spectrum
On the basis of monitoring technology and combination temperature or humidity, skin thickness series of parameters, for speculating blood sugar concentration.
In the present invention, the minimally-invasive glucose monitoring techniques are to continue blood sugar monitoring instrument in same a patient using minimally-invasive
Accurate data is repeatedly collected with it correction rule and mode that deep learning obtains exist as the data sample of deep learning
With applying with patient, each patient possesses a set of blood glucose correction mode for meeting itself sign.
In the present invention, in above-mentioned steps (2) in the method for deep learning correction blood glucose value, the data sample of deep learning is
Multiple test constantly obtains from same a patient, and the data sample of each patient is served with a patient.
In the present invention, the artificial intelligence learning correction method includes autocoder technology, deep learning, multilayer nerve
Network method.
In the present invention, the minimally-invasive continues glucose monitoring techniques and carries out blood sugar test, acquires 5-10000 Portugal daily
Grape sugar value, and continue 0.5-10 days.
The invention also discloses the adaptive wearable blood glucose means for correctings of personalization based on artificial intelligence comprising realizes
The minimally-invasive that minimally-invasive continues blood sugar monitoring methods continues blood sugar monitoring instrument, realizes that Woundless blood sugar monitoring technology passes through Woundless blood sugar
Monitor and and realize the artificial intelligence learning correction module of artificial intelligence learning correction method, the minimally-invasive continues blood glucose
Three monitor, non-invasive glucose monitor and artificial intelligence learning correction module modules are to connect each other but be to be separated from each other
Or three in one Integrated design.The data transmission between these modules can also be established, is set in other words existing
The module of standby upper increase data receiver transmission, can make this method more Intelligent portable in this way, can also reduce this method
Cost of labor.
It is explained below by way of specific several embodiments:
Embodiment 1: non-invasive glucose monitor being worn on the body of healthy aglycosuria patient, in certain particular time as after meal
Detect blood glucose value, for examine this non-invasive glucose monitor for change of blood sugar reflection trend correctness, if variation tendency with
Normal expected value is not obviously inconsistent, then the meaning that this blood glucose meter does not correct, if variation tendency is consistent with desired value, this blood glucose meter
The data of detection can be used as reference data in subsequent artefacts' intelligence timing.
Embodiment 2: after non-invasive glucose monitor correction, this blood glucose meter being worn on diabetic, at the same time,
The minimally invasive blood sugar monitoring instrument of sustainable detection blood glucose is also worn with patient herein 3-4 days, and from this blood glucose meter daily
This and glucose value (i.e. measured value and exact value) are read in timing, are recorded in in a table.
Training of enough exact values for artificial intelligence is read in embodiment 3:3-4 days, remove minimally invasive blood glucose later
Monitor because with the growth of time, measure data can increasingly be not allowed, therefore manually intelligence correction Woundless blood sugar prison
It surveys instrument and detects the data obtained.
Embodiment 4: artificial intelligence using autocoder be used as calibration model, variation autocoder conduct in recent years without
The new hot spot of deep learning is supervised, main be characterized by is introduced into the probability distribution that probability interpretation is come in learning data.
Aiming at the problem that blood glucose level data correction, since the data of Different Individual have a certain difference, it is assumed that it meets certain probability
Distribution is rationally, such as normal distribution.Therefore fitting is corrected to blood glucose level data using variation autocoder, compared to tradition
Autocoder model, output result can be advanced optimized.
The present invention acquires accurate blood glucose value by minimally-invasive glucose monitoring techniques, instructs to non-invasive blood glucose prison method
Practice study, the bearing calibration concluded the blood glucose bearing calibration identified specifically for the patient, and non-invasive blood glucose is enabled to supervise adapts to
The personalized situation of the patient is used for other subsequent non-invasive blood sugar monitorings, therefore, can be with for each different patients
Artificial intelligence training study is adaptively carried out with different patients by the method, conclusion is identified specifically for the trouble
The blood glucose bearing calibration of person for non-invasive monitors the blood glucose value of each diabetic.
It is all that the present invention is not departed to various changes or modifications of the invention the invention is not limited to above embodiment
Spirit and scope, if these modification and variations belong within the scope of claim and equivalent technologies of the invention, then this hair
It is bright to also imply that comprising these modification and variations.
Claims (9)
1. a kind of adaptive wearable blood glucose bearing calibration of personalization based on artificial intelligence, comprises the concrete steps that:
(1) collect the accurate blood glucose value that persistently changes in a period of time of patient: first with minimally-invasive glucose monitoring techniques from
The accurate blood glucose value of consecutive variations in a period of time is collected with single patient；(2) it records still uncorrected blood glucose value: utilizing
Woundless blood sugar monitoring technology records still uncorrected blood glucose value；
(3) after being collected into blood glucose numerical value by both modes, with the standard for the consecutive variations that minimally-invasive blood sugar monitoring is collected into
It is worth on the basis of true blood glucose value, blood glucose value acquired in Woundless blood sugar monitoring technology is subjected to the correction of artificial intelligence learning method, makes it
Identify that the degree of blood glucose value acquired in Woundless blood sugar monitoring technology and practical blood glucose value difference is regular with only patient,
And the numerical value diversity mode for being identified this artificial intelligence approach is as the distinctive blood glucose correction mode of the patient；
(4) after artificial intelligence learning training finishes, which continues to use Woundless blood sugar monitoring, and utilizes artificial intelligence
The obtained data calibration method of module training is practised to be corrected the blood glucose value recorded.
2. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
It is: the minimally-invasive glucose monitoring techniques of the accurate blood glucose value persistently changed in a period of time of above-mentioned steps (1) collection patient
It is the detection method or Fingertip blood glucose monitoring method of dynamic continuous blood sugar monitor.
3. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: minimally-invasive continuous blood sugar monitoring technology described in above-mentioned steps (1) refers to: can using subcutaneous or implanted can be inserted
Continue blood sugar monitoring instrument, or utilize finger tip blood-sampling method, continuous blood sugar value is collected with patient；In above-mentioned steps (2)
The Woundless blood sugar monitoring technology refers to: passing through near infrared spectroscopy or mid-infrared light spectrometry or far red light spectrometry or Raman
Spectroscopic methodology or polarimetry, using light irradiation human body certain positions such as finger or or ear or tongue or abdomen or thigh, so
The optical signal of reflection or projection is received by optical detector afterwards, and is analyzed, to determine the concentration of blood glucose, can be combined
Body temperature, metabolic heat, humidity, skin depth, the parameter indexes such as palmic rate conversion blood glucose value.
4. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: Woundless blood sugar monitoring technology described in above-mentioned steps (2) includes: spectroscopic methodology, optoacoustic method, metabolic heat mensuration, or resistance
Anti- mensuration: the spectroscopic methodology refers to through near infrared spectroscopy or mid-infrared light spectrometry or far red light spectrometry or Raman spectrum
Method or polarimetry；The optoacoustic method is the ultrasound signal analyzing blood sugar concentration generated using optoacoustic effect；The metabolic heat is surveyed
Amount method, which refers to, infers blood glucose value by measurement body metabolism heat conversion；The impedance measurement is to utilize electricity caused by glucose
Solution matter impedance changes to monitor the concentration of blood glucose.
5. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: the minimally-invasive glucose monitoring techniques are to continue blood sugar monitoring instrument using minimally-invasive repeatedly to collect with same a patient
Accurate data, as the data sample of deep learning, the correction rule and mode that deep learning is obtained are with same a patient
Using each patient possesses a set of blood glucose correction mode for meeting itself sign.
6. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: in above-mentioned steps (2) in the method for deep learning correction blood glucose value, the data sample of deep learning is from same a patient's body
What upper multiple test constantly obtained, the data sample of each patient is served with a patient.
7. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: pedestrian's work intelligence learning bearing calibration includes autocoder technology, deep learning, multilayer neural network method.
8. the adaptive wearable blood glucose bearing calibration of the personalization according to claim 1 based on artificial intelligence, feature
Be: the minimally-invasive continues glucose monitoring techniques and carries out blood sugar test, acquires 5-10000 dextrose equivalent daily, and hold
It is 0.5-10 days continuous.
9. the adaptive wearable blood glucose means for correcting of the personalization according to claim 1 based on artificial intelligence, feature
Be: the minimally-invasive for continuing blood sugar monitoring methods including realization minimally-invasive continues blood sugar monitoring instrument, realizes that Woundless blood sugar monitors skill
Art is by non-invasive glucose monitor, and realizes the artificial intelligence learning correction module of artificial intelligence learning correction method, described micro-
Wound formula continues blood sugar monitoring instrument, three modules of non-invasive glucose monitor and artificial intelligence learning correction module be connect each other but
It is separated or three in one Integrated design.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710369650.7A CN108937955A (en) | 2017-05-23 | 2017-05-23 | The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710369650.7A CN108937955A (en) | 2017-05-23 | 2017-05-23 | The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108937955A true CN108937955A (en) | 2018-12-07 |
Family
ID=64493724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710369650.7A Withdrawn CN108937955A (en) | 2017-05-23 | 2017-05-23 | The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108937955A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110575181A (en) * | 2019-09-10 | 2019-12-17 | 重庆大学 | Near infrared spectrum noninvasive blood glucose detection network model training method |
| CN111326255A (en) * | 2020-01-19 | 2020-06-23 | 湖南盈赛缇思人工智能公共数据平台有限公司 | Blood glucose concentration correction method based on big data, storage medium and system |
| CN111317473A (en) * | 2020-03-12 | 2020-06-23 | 桂林电子科技大学 | Blood glucose detection method based on hybrid measurement technology |
| CN112438704A (en) * | 2019-08-31 | 2021-03-05 | 深圳硅基传感科技有限公司 | Calibration system of physiological parameter monitor |
| CN113063753A (en) * | 2021-03-16 | 2021-07-02 | 重庆大学 | Blood glucose prediction model self-correction method based on near-infrared light |
| CN113317783A (en) * | 2021-04-20 | 2021-08-31 | 港湾之星健康生物(深圳)有限公司 | Multimode personalized longitudinal and transverse calibration method |
| WO2021238810A1 (en) * | 2020-05-27 | 2021-12-02 | 京东方科技集团股份有限公司 | Method, apparatus and device for obtaining blood glucose measurement result |
| WO2022032218A1 (en) * | 2020-08-07 | 2022-02-10 | Endectra, Llc | Wearable spectrometer for biomolecule interrogation in biological tissue |
| WO2022222197A1 (en) * | 2021-04-20 | 2022-10-27 | 港湾之星健康生物(深圳)有限公司 | Multi-mode personalized monitoring method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365374A (en) * | 2005-08-31 | 2009-02-11 | 弗吉尼亚大学专利基金委员会 | Accuracy of continuous glucose sensors |
| CN101915744A (en) * | 2010-07-05 | 2010-12-15 | 北京航空航天大学 | Near infrared spectrum nondestructive testing method and device for material component content |
| US20130287631A1 (en) * | 2010-03-11 | 2013-10-31 | Glumetrics, Inc. | Measurement devices and methods for measuring analyte concentration incorporating temperature and ph correction |
| CN104048939A (en) * | 2014-06-05 | 2014-09-17 | 中国肉类食品综合研究中心 | Near infrared rapid detection method for blood sugar content in live pig blood |
| CN106551700A (en) * | 2015-09-28 | 2017-04-05 | 戴文招 | A kind of survey blood glucose method for measuring in several ways and demarcating elimination systematic error |
-
2017
- 2017-05-23 CN CN201710369650.7A patent/CN108937955A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101365374A (en) * | 2005-08-31 | 2009-02-11 | 弗吉尼亚大学专利基金委员会 | Accuracy of continuous glucose sensors |
| US20130287631A1 (en) * | 2010-03-11 | 2013-10-31 | Glumetrics, Inc. | Measurement devices and methods for measuring analyte concentration incorporating temperature and ph correction |
| CN101915744A (en) * | 2010-07-05 | 2010-12-15 | 北京航空航天大学 | Near infrared spectrum nondestructive testing method and device for material component content |
| CN104048939A (en) * | 2014-06-05 | 2014-09-17 | 中国肉类食品综合研究中心 | Near infrared rapid detection method for blood sugar content in live pig blood |
| CN106551700A (en) * | 2015-09-28 | 2017-04-05 | 戴文招 | A kind of survey blood glucose method for measuring in several ways and demarcating elimination systematic error |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112438704A (en) * | 2019-08-31 | 2021-03-05 | 深圳硅基传感科技有限公司 | Calibration system of physiological parameter monitor |
| CN112438704B (en) * | 2019-08-31 | 2024-02-23 | 深圳硅基传感科技有限公司 | Calibration system of physiological parameter monitor |
| CN110575181A (en) * | 2019-09-10 | 2019-12-17 | 重庆大学 | Near infrared spectrum noninvasive blood glucose detection network model training method |
| CN111326255A (en) * | 2020-01-19 | 2020-06-23 | 湖南盈赛缇思人工智能公共数据平台有限公司 | Blood glucose concentration correction method based on big data, storage medium and system |
| CN111317473A (en) * | 2020-03-12 | 2020-06-23 | 桂林电子科技大学 | Blood glucose detection method based on hybrid measurement technology |
| WO2021238810A1 (en) * | 2020-05-27 | 2021-12-02 | 京东方科技集团股份有限公司 | Method, apparatus and device for obtaining blood glucose measurement result |
| WO2022032218A1 (en) * | 2020-08-07 | 2022-02-10 | Endectra, Llc | Wearable spectrometer for biomolecule interrogation in biological tissue |
| CN113063753B (en) * | 2021-03-16 | 2022-11-08 | 重庆大学 | Blood glucose prediction model self-correction method based on near-infrared light |
| CN113063753A (en) * | 2021-03-16 | 2021-07-02 | 重庆大学 | Blood glucose prediction model self-correction method based on near-infrared light |
| CN113317783A (en) * | 2021-04-20 | 2021-08-31 | 港湾之星健康生物(深圳)有限公司 | Multimode personalized longitudinal and transverse calibration method |
| CN113317783B (en) * | 2021-04-20 | 2022-02-01 | 港湾之星健康生物(深圳)有限公司 | Multimode personalized longitudinal and transverse calibration method |
| WO2022222198A1 (en) * | 2021-04-20 | 2022-10-27 | 港湾之星健康生物(深圳)有限公司 | Multi-mode individualised aspect calibration method |
| WO2022222197A1 (en) * | 2021-04-20 | 2022-10-27 | 港湾之星健康生物(深圳)有限公司 | Multi-mode personalized monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108937955A (en) | The adaptive wearable blood glucose bearing calibration of personalization and its means for correcting based on artificial intelligence | |
| CN102058400B (en) | Method and device for quickly detecting human body basic vital sign data | |
| WO2018107915A1 (en) | General noninvasive blood glucose prediction method based on timing analysis | |
| US20090240440A1 (en) | Non-Invasive Glucose Monitoring | |
| CN110575181A (en) | Near infrared spectrum noninvasive blood glucose detection network model training method | |
| US6949070B2 (en) | Non-invasive blood glucose monitoring system | |
| CN111599470B (en) | Method for improving near-infrared noninvasive blood glucose detection precision | |
| US10542919B2 (en) | Method and system for non-invasive blood glucose detection utilizing spectral data of one or more components other than glucose | |
| CN101138500A (en) | Non-invasive blood-sugar detecting instrument based on conservation of energy | |
| CN108937954A (en) | Artificial intelligence deep learning method corrects the monitoring method for continuing blood glucose | |
| CN111466921A (en) | Noninvasive blood glucose detector based on multi-source information sensing and fusion and detection method | |
| CN103230273B (en) | The non-invasive detection system of early stage subclinical asymptomatic diabetes and method thereof | |
| CN113063753B (en) | Blood glucose prediction model self-correction method based on near-infrared light | |
| CN112568902A (en) | Noninvasive blood glucose calibration method based on blood glucose value | |
| Batdorf et al. | The effect of signal averaging on the reproducibility and reliability of measures of T-wave morphology | |
| CN104188662A (en) | Blood-sampling-free type blood sugar monitoring device and use method thereof | |
| Wei et al. | Noninvasive glucose evaluation by human skin oxygen saturation level | |
| CN114403866B (en) | Noninvasive blood sugar prediction device based on near-infrared light wavelength conversion | |
| CN116035571A (en) | Intelligent noninvasive glucometer | |
| CN110575182A (en) | Method and device for detecting blood sugar | |
| Burma et al. | The validity and reliability of an open source biosensing board to quantify heart rate variability | |
| TWI516247B (en) | Method for analyzing emotional physiological signals of depressive tendency for home care | |
| CN202288267U (en) | A human body physiology parameter rapid detection apparatus | |
| KR102392948B1 (en) | Blood Glucose Index Calculation Method of Non-invasive Type and Non-invasive Blood Glucose Index Measurement System Thereof | |
| DeCaro | Beyond catecholamines: Measuring autonomic responses to psychosocial context |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181207 |
|
| WW01 | Invention patent application withdrawn after publication |