CN117224120A - Blood oxygen saturation detection method based on skin data model assistance - Google Patents
Blood oxygen saturation detection method based on skin data model assistance Download PDFInfo
- Publication number
- CN117224120A CN117224120A CN202311172510.2A CN202311172510A CN117224120A CN 117224120 A CN117224120 A CN 117224120A CN 202311172510 A CN202311172510 A CN 202311172510A CN 117224120 A CN117224120 A CN 117224120A
- Authority
- CN
- China
- Prior art keywords
- blood oxygen
- oxygen saturation
- skin
- intelligent terminal
- model
- 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
- 239000008280 blood Substances 0.000 title claims abstract description 86
- 210000004369 blood Anatomy 0.000 title claims abstract description 86
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 78
- 239000001301 oxygen Substances 0.000 title claims abstract description 78
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 78
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 238000013499 data model Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000012937 correction Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 10
- 230000036564 melanin content Effects 0.000 claims description 10
- 238000004868 gas analysis Methods 0.000 claims description 7
- 238000002310 reflectometry Methods 0.000 claims description 7
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 claims description 6
- 230000001815 facial effect Effects 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000007954 hypoxia Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004768 organ dysfunction Effects 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, which relates to the technical field of blood oxygen detection and comprises the steps of detecting data, correcting skin color difference, establishing a correction model and outputting a result; by modeling and correcting a large amount of experimental data, the blood oxygen saturation can be measured only through one intelligent terminal program; the detection method makes up the defects of the current mainstream portable detection equipment and overcomes the interferences of skin color, environment and the like; by using the method for measuring the blood oxygen saturation, a more accurate blood oxygen saturation result can be obtained quickly, and the blood oxygen saturation measuring device is convenient to use at home, so that the remote medical treatment can be further facilitated.
Description
Technical Field
The invention relates to the technical field of blood oxygen detection, in particular to a blood oxygen saturation detection method based on the assistance of a skin data model.
Background
Currently, blood oxygen saturation has become an important index reflecting human health; blood oxygen saturation is an important physiological parameter of the respiratory cycle of a human body, and can directly reflect the oxygenation of the lung and the oxygen carrying capacity of hemoglobin in blood; furthermore, hypoxia can cause organ dysfunction and even failure; in severe cases, blood oxygen saturation may drop sharply due to infection with viruses in healthy people, which requires immediate medical attention; for ordinary residents, professional blood oxygen saturation detection equipment is generally difficult to acquire; even in emergency situations, timely blood oxygen saturation detection is often difficult to implement due to resource and environmental limitations; in recent years, the popularization of intelligent equipment lays a crucial foundation for remote electronic medical treatment; therefore, it is important to develop a convenient and rapid intelligent terminal blood oxygen saturation detection method.
Clinically, arterial blood gas detection (gold standard) is generally adopted to detect the blood oxygen saturation, and an accurate blood oxygen saturation result can be directly obtained; however, the test can only be performed in a professional institution (e.g., a hospital); another commonly used optical instrument for measuring blood oxygen saturation has been widely used; however, the accuracy of this method is reported to be often affected by human skin color, requiring correction by skin instruments (e.g., spectrophotometers); in addition, the method is difficult to apply to home monitoring, and it is urgent to construct a standardized accurate measurement method which is not affected by skin color and external environment.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for detecting blood oxygen saturation based on assistance of a skin data model, which is characterized by comprising:
step one: detecting blood oxygen saturation of a subject by using an oximeter, arterial blood gas analysis and an intelligent terminal app respectively;
step two: measuring standard skin color and skin reflectivity by using a portable spectrophotometer, and simultaneously shooting a skin image of the measurement part in the first step by using an intelligent terminal to obtain imaging skin color;
step three: respectively establishing an oximeter, a color and an intelligent terminal correction model to eliminate detection errors caused by different skin colors;
step four: by applying the auxiliary means, the corrected oximeter result is used to correct the measurement result of the intelligent terminal app, and the standardized detection result of the intelligent terminal is output.
The blood oxygen saturation detection method based on the skin data model is characterized by comprising the following steps of firstly, determining the standard skin color and reflectivity of the left and right upper inner walls of a subject; and average the obtained data.
The invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, which is characterized in that a skin melanin content calculation model is preferably as follows:
where M represents melanin content and red reflectance represents skin reflectance measured by a spectrophotometer.
According to the blood oxygen saturation detection method based on the skin data model assistance, preferably, the intelligent terminal app extracts facial images of a subject and calculates lips and facial color metadata around the lips to obtain a blood oxygen saturation value.
The invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, and preferably, the method for calculating and detecting the blood oxygen saturation value by an intelligent terminal app comprises the following steps:
s1, loading clinical sample images through a smart phone;
s2, extracting a sample color characteristic signal by an intelligent terminal app background;
s3, inputting terminal app model calculation, and outputting a final detection result on a screen.
The invention provides a blood oxygen saturation detection method based on skin data model assistance, preferably, a calculation model for calculating and detecting a blood oxygen saturation value by an intelligent terminal app is as follows:
y=W 1 P+w 2 C 1 +…+w m+1 C m +b
wherein y is the finalOutput blood oxygen saturation result, vector C 1 ...C m Representing color characteristic signals extracted by APP, b representing bias terms, and vector P being a self-designed characteristic term with the value:
the invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, and preferably, a calculation model comprises the following steps:
the calculation model of the oximeter correction model is:
aF+bS 1 +cS 2 +uS 3 +qM+β 1 =A
the calculation model of the skin color correction model is:
S P1 =dS 1 +eC p +fD p +gI(K)+β 2
S P2 =d 1 S 2 +e 1 C p +f 1 D p +g 1 I(K)+β 3
S P3 =d 2 S 3 +e 2 C p +f 2 D p +g 2 I(K)+β 4
the relationship model between melanin and skin color is:
S 1 =nM+β 5
the intelligent terminal blood oxygen saturation prediction model is as follows:
SpO 2 =θ 1 C 1 +θ 2 C 2 +…+θ n C n +θ n+1 P+β
wherein the letters in the formula describe: f represents an indication of the blood oxygen saturation measured by a pulse oximeter;
S 1 …S n represents skin color measured by standard instruments (spectrophotometers);
m represents skin melanin content;
a represents an arterial blood gas analysis result;
S P1 …S3 P3 ,C 1 …C P …C n ,D p representing the skin color of an arm and face image shot by the intelligent terminal;
i represents ISO parameters (which can be replaced by skin color parameters K) of images shot by the intelligent terminal;
β...β 5 representing a bias term;
the other parameter is the weight.
The invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, which comprises the steps of detecting data, correcting skin color difference, establishing a correction model and outputting a result; by modeling and correcting a large amount of experimental data, the blood oxygen saturation can be measured only through one intelligent terminal program; the detection method makes up the defects of the current mainstream portable detection equipment and overcomes the interferences of skin color, environment and the like; by using the method for measuring the blood oxygen saturation, a more accurate blood oxygen saturation result can be obtained quickly, and the blood oxygen saturation measuring device is convenient to use at home, so that the remote medical treatment can be further facilitated.
Drawings
FIG. 1 is a flow chart of a method for detecting blood oxygen saturation based on the assistance of a skin data model according to the present invention;
fig. 2 is a process and a result diagram of detecting blood oxygen saturation by using an intelligent terminal APP based on a skin data model-assisted blood oxygen saturation detection method of the present invention;
FIG. 3 is a graph showing the comparison of blood oxygen saturation measurements before and after modeling with skin data for an assisted blood oxygen saturation detection method based on skin data model according to the present invention;
FIG. 4 is a graph showing the comparison of the results before and after skin color correction based on the skin data model-assisted blood oxygen saturation detection method of the present invention;
FIG. 5 is a graph of blood oxygen saturation measurement error over multiple subject samples based on a skin data model-aided blood oxygen saturation detection method of the present invention;
FIG. 6 is a comparison of blood oxygen saturation measurement errors over multiple subject samples based on a skin data model-aided blood oxygen saturation detection method of the present invention.
Detailed Description
The invention will be described in further detail with reference to the accompanying drawings and specific preferred embodiments.
In the description of the present invention, it should be understood that the terms "left", "right", "upper", "lower", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and "first", "second", etc. do not indicate the importance of the components, and thus are not to be construed as limiting the present invention. The specific dimensions adopted in the present embodiment are only for illustrating the technical solution, and do not limit the protection scope of the present invention.
Example 1:
as shown in fig. 1 to 6, the present invention provides a blood oxygen saturation detection method based on skin data model assistance, which is characterized by comprising:
step one: detecting blood oxygen saturation of a subject by using an oximeter, arterial blood gas analysis and an intelligent terminal app respectively;
step two: measuring standard skin color and skin reflectivity by using a portable spectrophotometer, and simultaneously shooting a skin image of the measurement part in the first step by using an intelligent terminal to obtain imaging skin color;
step three: respectively establishing an oximeter, a color and an intelligent terminal correction model to eliminate detection errors caused by different skin colors;
step four: by applying the auxiliary means, the corrected oximeter result is used to correct the measurement result of the intelligent terminal app, and the standardized detection result of the intelligent terminal is output.
More specifically, removing standard skin colors and reflectivity of the left and right upper inner walls of the subject in the second step; and average the obtained data.
More specifically, the skin melanin content calculation model is:
where M represents melanin content and red reflectance represents skin reflectance measured by a spectrophotometer.
More specifically, the smart terminal app extracts a subject's facial image and calculates lips and facial color metadata around the lips to obtain a blood oxygen saturation value.
More specifically, the method for calculating and detecting the blood oxygen saturation value by the intelligent terminal app comprises the following steps:
s1, loading clinical sample images through a smart phone;
s2, extracting a sample color characteristic signal by an intelligent terminal app background;
s3, inputting terminal app model calculation, and outputting a final detection result on a screen.
More specifically, the calculation model of the intelligent terminal app calculates the detected blood oxygen saturation value is:
y=w 1 P+w 2 C 1 +…+w m+1 C m +b
where y is the final output blood oxygen saturation result, vector C 1 ...C m Representing color characteristic signals extracted by APP, b representing bias terms, and vector P being a self-designed characteristic term with the value:
more specifically, the calculation model includes:
the calculation model of the oximeter correction model is:
aF+bS 1 +cS 2 +uS 3 +qM+β 1 =A
the calculation model of the skin color correction model is:
S P1 =dS 1 +eC p +fD p +gI(K)+β 2
S P2 =d 1 S 2 +e 1 C p +f 1 D p +g 1 I(K)+β 3
S P3 =d 2 S 3 +e 2 C p +f 2 D p +g 2 I(K)+β 4
the relationship model between melanin and skin color is:
S 1 =nM+β 5
the intelligent terminal blood oxygen saturation prediction model is as follows:
SpO 2 =θ 1 C 1 +θ 2 C 2 +…+θ n C n +θ n+1 P+β
wherein the letters in the formula describe: f represents an indication of the blood oxygen saturation measured by a pulse oximeter;
S 1 …S n represents skin color measured by standard instruments (spectrophotometers);
m represents skin melanin content;
a represents an arterial blood gas analysis result;
S P1 …S3 P3 ,C 1 …C P …C n ,D p representing the skin color of an arm and face image shot by the intelligent terminal;
i represents ISO parameters (which can be replaced by skin color parameters K) of images shot by the intelligent terminal;
β … β 5 representing a bias term;
the other parameter is the weight.
Working principle:
firstly, respectively detecting blood oxygen saturation of a subject by using an oximeter, arterial blood gas analysis and an intelligent terminal app, wherein the blood oxygen saturation comprises an oximeter count and melanin content;
measuring standard skin color and skin reflectivity by using a portable spectrophotometer, and simultaneously shooting a skin image of the measuring part in the first step by using an intelligent terminal to obtain imaging skin color;
thirdly, respectively establishing an oximeter, a color and an intelligent terminal correction model to eliminate detection errors caused by different skin colors;
and finally, correcting the measurement result of the intelligent terminal app by using the corrected oximeter result by using the auxiliary means, and outputting the detection result of the intelligent terminal after standardized correction.
In summary, the invention provides a blood oxygen saturation detection method based on the assistance of a skin data model, which comprises the steps of detecting data, correcting skin color difference, establishing a correction model and outputting a result; by modeling and correcting a large amount of experimental data, the blood oxygen saturation can be measured only through one intelligent terminal program; the detection method makes up the defects of the current mainstream portable detection equipment and overcomes the interferences of skin color, environment and the like; by using the method for measuring the blood oxygen saturation, a more accurate blood oxygen saturation result can be obtained quickly, and the blood oxygen saturation measuring device is convenient to use at home, so that the remote medical treatment can be further facilitated.
While the present invention has been described in detail through the foregoing description of the preferred embodiment, it should be understood that the foregoing description is not to be considered as limiting the invention. Many modifications and substitutions of the present invention will become apparent to those of ordinary skill in the art upon reading the foregoing. Within the technical conception scope of the invention, a plurality of equivalent changes can be carried out on the technical proposal of the invention, and the equivalent changes belong to the protection scope of the invention.
Claims (7)
1. The blood oxygen saturation detection method based on the assistance of the skin data model is characterized by comprising the following steps of:
step one: detecting blood oxygen saturation of a subject by using an oximeter, arterial blood gas analysis and an intelligent terminal app respectively;
step two: measuring standard skin color and skin reflectivity by using a portable spectrophotometer, and simultaneously shooting a skin image of the measurement part in the first step by using an intelligent terminal to obtain imaging skin color;
step three: respectively establishing an oximeter, a color and an intelligent terminal correction model to eliminate detection errors caused by different skin colors;
step four: by applying the auxiliary means, the corrected oximeter result is used to correct the measurement result of the intelligent terminal app, and the standardized detection result of the intelligent terminal is output.
2. The method for detecting blood oxygen saturation based on the assistance of a skin data model according to claim 1, wherein in the second step, the standard skin color and reflectivity of the upper and lower inner walls of the subject are removed; and average the obtained data.
3. The method for detecting blood oxygen saturation based on the assistance of a skin data model as claimed in claim 1, wherein the skin melanin content calculation model is as follows:
where M represents melanin content and red reflectance represents skin reflectance measured by a spectrophotometer.
4. The method for detecting blood oxygen saturation based on the assistance of a skin data model as claimed in claim 1, wherein the intelligent terminal app extracts facial images of the subject and calculates lips and facial color metadata around the lips to obtain the blood oxygen saturation value.
5. The method for detecting blood oxygen saturation based on the assistance of a skin data model as claimed in claim 4, wherein the method for calculating and detecting the blood oxygen saturation value by the intelligent terminal app comprises the following steps:
s1, loading clinical sample images through a smart phone;
s2, extracting a sample color characteristic signal by an intelligent terminal app background;
s3, inputting terminal app model calculation, and outputting a final detection result on a screen.
6. The method for detecting blood oxygen saturation based on the assistance of a skin data model as claimed in claim 4, wherein the calculation model for calculating and detecting the blood oxygen saturation value by the intelligent terminal app is as follows:
y=w 1 P+w 2 C 1 +…+w m+1 C m +b
where y is the final output blood oxygen saturation result, vector C 1.. Cm represents the color feature signal extracted by APP, b represents the bias term, and vector P is the self-designed feature term, and the value is:
7. a method for detecting blood oxygen saturation based on assistance of a skin data model as claimed in claim 1, wherein the calculation model comprises:
the calculation model of the oximeter correction model is:
aF+bS 1 +cS 2 +uS 3 +qM+β 1 =A
the calculation model of the skin color correction model is:
S P1 =dS 1 +eC p +fD p +gI(K)+β 2
S P2 =d 1 S 2 +e 1 C p +f 1 D p +g 1 I(K)+β 3
S P3 =d 2 S 3 +e 2 C p +f 2 D p +g 2 I(K)+β 4
the relationship model between melanin and skin color is:
S 1 =nM+β 5
the intelligent terminal blood oxygen saturation prediction model is as follows:
SpO 2 =θ 1 C 1 +θ 2 C 2 +…+θ n C n +θ n+1 P+β
wherein the letters in the formula describe: f represents an indication of the blood oxygen saturation measured by a pulse oximeter;
S 1 …S n represents skin color measured by standard instruments (spectrophotometers);
m represents skin melanin content;
a represents an arterial blood gas analysis result;
S P1 …S3 P3 ,C 1 …C P …C n ,D p representing the skin color of an arm and face image shot by the intelligent terminal;
i represents ISO parameters (which can be replaced by skin color parameters K) of images shot by the intelligent terminal;
β … β 5 representing a bias term;
the other parameter is the weight.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311172510.2A CN117224120A (en) | 2023-09-12 | 2023-09-12 | Blood oxygen saturation detection method based on skin data model assistance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311172510.2A CN117224120A (en) | 2023-09-12 | 2023-09-12 | Blood oxygen saturation detection method based on skin data model assistance |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117224120A true CN117224120A (en) | 2023-12-15 |
Family
ID=89087276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311172510.2A Pending CN117224120A (en) | 2023-09-12 | 2023-09-12 | Blood oxygen saturation detection method based on skin data model assistance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117224120A (en) |
-
2023
- 2023-09-12 CN CN202311172510.2A patent/CN117224120A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105943005B (en) | The non-invasive blood pressure detection device mixed based on photoelectricity green light pulse with electrocardiogram | |
US10080510B2 (en) | Breath analysing and training assembly | |
Takla et al. | The problem of artifacts in patient monitor data during surgery: a clinical and methodological review | |
KR101716663B1 (en) | Method and Apparatus for Correction of Non-Invasive Blood Glucose Measurement | |
CN108601527B (en) | Calibration method of blood pressure measuring equipment and blood pressure measuring equipment | |
CN107320089A (en) | Self-alignment human blood-pressure measuring method | |
WO2022262221A1 (en) | Method for measuring hematocrit, apparatus, terminal, and readable storage medium | |
TWI576093B (en) | Hemoglobin and hematocrit analyzer and analyzing method thereof | |
CN117224120A (en) | Blood oxygen saturation detection method based on skin data model assistance | |
US20170055891A1 (en) | Method, device and system for non-invasive measurement of blood glucose content | |
KR102119578B1 (en) | Color correction apparatus for colorimetric method and method thereof | |
CN117064382A (en) | Blood biochemical parameter intelligent analysis and abnormality early warning system based on artificial intelligence | |
CN106970074A (en) | The Urine test paper image-recognizing method of ability is corrected with color | |
CN115381444A (en) | Rapid detection method for blood oxygen saturation | |
KR102503149B1 (en) | Apparatus and method for measuring biometric information | |
CN210990300U (en) | Automatic correction system for lung function measurement zero drift | |
CN115752800A (en) | Medical wireless body temperature monitoring system based on internet | |
CN113727648B (en) | Identification and quantification of ventilation disorders resulting in incorrect measurement of arterial acid-base status | |
Abbas et al. | Haemoglobin detection in blood by signal to image scanning using Photo-Plethysmo-Graphic-Technique (PPG) | |
CN113616189A (en) | Method, device, equipment and storage medium for detecting amount of blepharoconjunctival hemoglobin | |
CN112683826A (en) | Correction method and device of calibration color plate for percutaneous jaundice tester | |
CN209499730U (en) | Partial pressure of carbon dioxide in endexpiratory gas measuring device and system | |
CN117292821B (en) | Auxiliary diagnosis and treatment system based on knowledge graph | |
Bhagat et al. | Development of jaundice detection approaches in neonates | |
Karlen et al. | Automated validation of capillary refill time measurements using photo-plethysmogram from a portable device for effective triage in children |
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 |