Method and system for detecting low-density lipoprotein in blood based on near infrared spectrum
Through near-infrared spectroscopy, convenient, automated and highly accurate LDL detection without blood drawing is achieved, solving the problems of cumbersome operation of traditional detection methods and discomfort to the human body, and real-time monitoring of changes in LDL is achieved and control.
Patent Information
- Application Number
- CN202411184050.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
AI Technical Summary
Traditional blood LDL detection methods are cumbersome, have low automation, and are uncomfortable to the human body. They cannot achieve fast, convenient, accurate and non-destructive detection, and cannot observe the changes in LDL in real time.
Using a detection method based on near-infrared spectrum, face video samples are collected through video, blood component spectroscopy samples are obtained using a near-infrared camera, and pre-processing and discriminant model construction is carried out to achieve rapid detection of low-density lipoprotein content, and ideal values are established. Critical value and excessive value database, output judgment results.
It realizes convenient, automated and highly accurate LDL detection without blood drawing, reduces detection costs, can observe and control LDL changes in real time, and improves the sensitivity and safety of detection.
Smart Images

Figure CN119064309A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of blood component detection, and in particular, to a method and system for detecting low-density lipoprotein in blood based on near-infrared spectroscopy. Background Art
[0002] Traditional methods for detecting low-density lipoprotein cholesterol in blood include: 1) Heparin precipitation method: Heparin can precipitate LDL in a pH 5.12 citrate buffer, separate LDL from other lipoproteins, and then perform cholesterol determination; 2) Iso-density and density gradient ultracentrifugation method: This method is to add serum to a separation solution with different density gradients, and after ultracentrifugation, the various components of lipoproteins in the serum can be transferred to equal areas of equal density. This method can separate various components in lipoproteins at one time; 3) Immuno-binding separation method: This method prepares antibodies related to apolipoproteins based on the differences in the types and quantities of apolipoproteins contained in serum lipoproteins, and achieves precipitation of the corresponding substances through immuno-binding to obtain the desired results.
[0003] These traditional detection methods require first drawing blood to obtain human serum or plasma, and then using the above method to detect the low-density lipoprotein (LDL) index. The equipment operation is cumbersome, the degree of automation is low, it is easy to cause discomfort to the human body, and it is time-consuming and laborious. In order to control the high low-density lipoprotein and improve their own quality of life, users are not satisfied with traditional detection methods. Therefore, there is an urgent need for a fast, convenient, sensitive, highly accurate, non-destructive, and relatively low-cost detection method and equipment to complete daily testing, so as to observe the changes in low-density lipoprotein at any time and achieve the purpose of effectively controlling low-density lipoprotein. Summary of the invention
[0004] The main purpose of the present application is to provide a method and system for detecting low-density lipoprotein in blood based on near-infrared spectroscopy, so as to realize the observation of changes in low-density lipoprotein at any time through video acquisition, so as to achieve the purpose of effectively controlling low-density lipoprotein.
[0005] In order to achieve the above object, the present application provides a method for detecting blood low-density lipoprotein based on near-infrared spectroscopy, the method comprising:
[0006] Collect the user's face video sample and obtain the blood component spectrum sample;
[0007] Preprocessing the spectrum sample to obtain a blood component spectrum graph;
[0008] A discrimination model is constructed using known blood component content data and its corresponding blood spectrogram;
[0009] The blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
[0010] Furthermore, the method of collecting a user's face video sample and obtaining a spectrum sample of blood components includes:
[0011] Use a near-infrared camera to illuminate the user's face;
[0012] The spectrometer receives the photoelectric pulse wave corresponding to the outgoing light of each wavelength;
[0013] The photoelectric converter and the analog-to-digital converter perform signal conversion on the photoelectric pulse wave to obtain data of the changing output light intensity;
[0014] Calculating absorbance data of each component in the blood according to the data of the changed emitted light intensity, wherein the absorbance data includes the absorbance data of low-density lipoprotein;
[0015] A spectrum sample of the blood component is obtained based on the absorbance data.
[0016] Furthermore, the method of preprocessing the spectral sample to obtain a blood component spectrum includes:
[0017] Using Euclidean distance to determine the discrete points of the spectral samples, and eliminating invalid spectral samples;
[0018] The wavelet transform denoising method is used to remove the interference noise of the spectral samples;
[0019] One or more of the peak-valley point leveling, bias subtraction, differential processing and baseline tilting methods are used to remove the spectrum baseline of the spectrum sample;
[0020] The preprocessed spectral samples are normalized to obtain a preprocessed blood component spectrum.
[0021] Furthermore, after preprocessing the spectrum sample to obtain a blood component spectrum graph, the method further includes:
[0022] constructing a spectrum database according to the blood component spectrum diagram;
[0023] The spectrum database is constructed with an ideal value sub-database, a critical value sub-database and an excessive value sub-database according to the control standard of low-density lipoprotein content.
[0024] Furthermore, the method of constructing a discrimination model using known blood component content data and its corresponding blood spectrogram includes:
[0025] Obtaining blood component content data and its corresponding blood spectrogram;
[0026] Selecting a chemometric algorithm to pre-process the blood spectrogram;
[0027] The principal component analysis method was used to construct a discriminant model based on the blood component content data and the preprocessed blood spectra.
[0028] Furthermore, after inputting the blood component spectrum into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood, the method further includes:
[0029] Compare the low-density lipoprotein content value with the control standard, and output the judgment result as an ideal value, a critical value, or an excessive value;
[0030] The blood spectra corresponding to different low-density lipoproteins are stored in an ideal value sub-database, a critical value sub-database, or an excessive value sub-database according to the judgment result.
[0031] The present invention further discloses a blood low-density lipoprotein detection system based on near-infrared spectroscopy, comprising:
[0032] The video acquisition module is used to collect the user's face video samples and obtain the spectrum samples of blood components;
[0033] A spectrum processing module, used for preprocessing the spectrum sample to obtain a blood component spectrum;
[0034] The model processing module is used to construct a discrimination model using known blood component content data and its corresponding blood spectrogram; and is also used to:
[0035] The blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
[0036] Furthermore, the spectrum processing module is also used to:
[0037] constructing a spectrum database according to the blood component spectrum diagram;
[0038] The spectrum database is constructed with an ideal value sub-database, a critical value sub-database and an excessive value sub-database according to the control standard of low-density lipoprotein content.
[0039] Furthermore, the spectrum processing module is also used to:
[0040] Compare the low-density lipoprotein content value with the control standard, and output the judgment result as an ideal value, a critical value, or an excessive value;
[0041] The blood spectra corresponding to different low-density lipoproteins are stored in an ideal value sub-database, a critical value sub-database, or an excessive value sub-database according to the judgment result.
[0042] The present invention further discloses an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the program.
[0043] Compared with the prior art, the method and system for detecting low-density lipoprotein in blood based on near-infrared spectroscopy provided by the present invention have the following beneficial effects: by collecting a user's face video sample, a spectral sample of blood components can be obtained, and after preprocessing the spectral sample, a blood component spectrum can be obtained, and a discrimination model is constructed using known blood component content data and its corresponding blood spectrum, and then the blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood. There is no need to draw blood to obtain human serum or plasma, the operation is more convenient, the degree of automation is higher, and the human body will not feel uncomfortable, and finally a fast, convenient, sensitive, high-accuracy, non-destructive, and relatively low-cost detection and observation of low-density lipoprotein changes can be achieved, so as to achieve the purpose of effectively controlling low-density lipoprotein. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:
[0045] Figure 1 Schematic diagram of the process of the method for detecting low-density lipoprotein in blood based on near-infrared spectroscopy in this embodiment;
[0046] Figure 2 This is a schematic diagram of the structure of the blood low-density lipoprotein detection system based on near-infrared spectroscopy in this embodiment;
[0047] Figure 3 It is a schematic diagram of the structure of the electronic device disclosed in this embodiment. DETAILED DESCRIPTION
[0048] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0049] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0050] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.
[0051] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.
[0052] In addition, the term "plurality" shall mean two or more.
[0053] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0054] refer to Figure 1 This embodiment discloses a method for detecting low-density lipoprotein in blood based on near-infrared spectroscopy, so as to realize rapid analysis of low-density lipoprotein in the blood of the tested population, and has the advantages of non-invasive and non-contact detection, and the method comprises:
[0055] S100: Collect a user's face video sample and obtain a blood component spectrum sample.
[0056] Specifically, since the human face has abundant blood flow and is easy to sample, this embodiment uses a portable near-infrared spectrometer as a collection device. Other collection devices with both spectral and imaging functions may also be used, and this embodiment does not limit this. Taking a portable near-infrared camera as an example, before face collection, the camera is calibrated and the faces of the tested people are uniformly scanned at least once. During the scan, the spectrometer excites several near-infrared lights of different wavelengths to illuminate the face of the person being tested. In this embodiment, the cheek and forehead areas of the face are framed to effectively avoid motion noise at the eyes and mouth.
[0057] The spectrometer receives the photoelectric pulse wave corresponding to the outgoing light of each wavelength, and the photoelectric conversion device and the analog-to-digital converter realize the conversion of light-to-electricity-to-digital signals to obtain the data of the changing outgoing light intensity. The absorbance data of each component in the blood is calculated based on the data of the changing outgoing light intensity, and the absorbance data includes the absorbance data of low-density lipoprotein; the spectral samples of different components of the blood are obtained based on the absorbance data.
[0058] S200: Preprocessing the spectrum sample to obtain a blood component spectrum graph.
[0059] Specifically include:
[0060] S210: using Euclidean distance to determine the discrete points of the spectral sample and eliminating invalid spectral samples; that is, by calculating the coordinates of the data points of each spectral sample, and then calculating the Euclidean distance between the data point of each spectral sample and all other spectral data points, after obtaining the Euclidean distance, the current spectral sample discrete points are determined according to the thresholds set for different blood components, and the spectral samples corresponding to the above discrete points are eliminated.
[0061] S220: using wavelet transform denoising method to remove interference noise of spectral samples;
[0062] S230: removing the spectrum baseline of the spectrum sample by using one or more of peak-valley point leveling, offset subtraction, differential processing and baseline tilting methods;
[0063] Among them, when the peak-valley point equalization method is adopted, each new spectrum is subtracted from the average value of the absorbance at the peak and valley of the spectrum to achieve the goal.
[0064] S240: performing normalization processing on the preprocessed spectrum sample to obtain a preprocessed blood component spectrum graph.
[0065] After obtaining the pre-processed blood component spectrogram, a spectral database is constructed for unified management and call. According to the existing blood low-density lipoprotein control standard, an ideal value sub-database, a critical value sub-database and an excessive value sub-database are constructed in the spectral database to store blood component spectral samples after obtaining accurate low-density lipoprotein content. In this embodiment, the division criteria of the above sub-databases are exemplified as follows: the ideal value should be <130mg / dL; the critical value is 130-159mg / dL; the excessive value refers to low-density lipoprotein cholesterol>160mg / dL.
[0066] S300: Constructing a discrimination model using known blood component content data and its corresponding blood spectrogram.
[0067] Specific:
[0068] S310: Obtain blood component content data and its corresponding blood spectrogram;
[0069] S320: using a chemometrics algorithm to pre-process the blood spectrogram;
[0070] S330: Construct a discrimination model based on the blood component content data and the preprocessed blood spectrogram using principal component analysis.
[0071] Since blood is an opaque turbid medium with strong absorption and scattering characteristics, it is impossible to detect the material components using the Lambert-Beer law. Therefore, this embodiment uses a chemometric algorithm to establish a functional relationship between the spectral sample and the content of its components, that is, by one-to-one correspondence between the known sample spectrum and the content data, a chemometric algorithm is selected to pre-process and optimize the spectral sample, and a blood spectrum graph with a high correlation between the spectral sample and the component content is established to construct a discrimination model, and then the discrimination model is used to achieve rapid prediction of relevant data such as the content or properties of the unknown sample components.
[0072] For the method of constructing the above-mentioned discriminant model, the options include principal component analysis (PCA), MLR principle regression analysis, partial least squares regression analysis, and BP artificial neural network (BP-ANN). This embodiment takes principal component analysis (PCA) as an example for explanation.
[0073] The principal component analysis method is used to perform data dimension reduction on the above preprocessed blood spectrogram and blood component content data:
[0074] At the data level, the blood component content data and the blood spectrogram data are linearly related variables. In this embodiment, the orthogonal transformation method is used to make the above variables independent of each other, and the independent variables are used to represent the original data matrix, so as to retain the key information of the original data. Specifically: the principal component regression process is divided into principal component analysis and multivariate linear regression. The blood component content data and the blood spectrogram data are represented by independent variables X and dependent variables Y, as shown in the following example:
[0075]
[0076] Use principal component analysis to calculate the X matrix to obtain the load matrix P and the score matrix T: T = XP, where the dimension of the T matrix can be the same as that of the matrix X. For the matrix T, its first principal component reflects the maximum variance change of the original variable, the second principal component is second, the third principal component is third, and so on. That is, the principal components with higher rankings contain most of the useful information of the X matrix, while the principal components at the back are often related to noise and interference factors. Therefore, T involved in the regression in the principal component analysis is a matrix composed of the first few principal components, which is much smaller than X in dimension. As shown below:
[0077]
[0078] Use the reduced-dimensional T matrix and dependent variable Y matrix for multiple linear regression as follows:
[0079]
[0080] Then the least squares solution of Y is: B = (T'T) -1 T'Y, the details are as follows:
[0081]
[0082] In summary, the principal component analysis method adopted in this embodiment, after reducing the dimensionality of the data, only selects the factors with the highest scores to form the principal components to participate in the modeling, which solves the multicollinearity problem in the spectral matrix, removes the redundant components in the spectral data, and greatly improves the speed and efficiency of the operation.
[0083] S400: Inputting the blood component spectrum into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
[0084] The above-mentioned judgment model is used to identify the input blood component spectrum and obtain the corresponding low-density lipoprotein content in the blood, the low-density lipoprotein content value is compared with the control standard, and the judgment result is output as an ideal value, a critical value, or an excessive value. According to the judgment result, the blood spectra corresponding to different low-density lipoproteins are stored in the ideal value sub-database, the critical value sub-database, or the excessive value sub-database.
[0085] In summary, the technical solution disclosed in this embodiment uses a chemometric algorithm to construct a discriminant model in conjunction with the principal component analysis method for known blood component content data and its corresponding blood spectra, and establishes a functional relationship between the spectral sample and the blood component content data, namely, the discriminant model. The collected blood component spectral samples are input into the discriminant model to obtain the detection of low-density lipoprotein in the current blood. Since it uses non-invasive and non-contact detection methods, real-time detection of the population can be achieved, and the analysis speed is fast and the signal-to-noise ratio is high. It is particularly suitable for scenarios that require rapid detection, such as online detection and analysis.
[0086] refer to Figure 2 This embodiment further discloses a blood low-density lipoprotein detection system based on near-infrared spectroscopy, comprising:
[0087] The video acquisition module 21 is used to acquire a user's face video sample and obtain a blood component spectrum sample.
[0088] The spectrum processing module 22 is used to pre-process the spectrum sample to obtain a blood component spectrum; and is also used to:
[0089] constructing a spectrum database according to the blood component spectrum diagram;
[0090] The spectrum database is constructed with an ideal value sub-database, a critical value sub-database and an excessive value sub-database according to the control standard of low-density lipoprotein content; and is also used for:
[0091] Compare the low-density lipoprotein content value with the control standard, and output the judgment result as an ideal value, a critical value, or an excessive value;
[0092] The blood spectra corresponding to different low-density lipoproteins are stored in an ideal value sub-database, a critical value sub-database, or an excessive value sub-database according to the judgment result.
[0093] The model processing module 23 is used to construct a discrimination model using known blood component content data and its corresponding blood spectrogram; and is also used to:
[0094] The blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
[0095] refer to Figure 3 , this embodiment further discloses an electronic device, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503;
[0096] The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method embodiments.
[0097] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above method embodiments.
[0098] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.
[0099] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.
[0100] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A method for detecting low-density lipoprotein in blood based on near-infrared spectroscopy, characterized in that: The method comprises: Collect user's face video samples and obtain blood component spectrum samples; Preprocessing the spectrum sample to obtain a blood component spectrum; A discrimination model is constructed using known blood component content data and its corresponding blood spectra; The blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
2. The method for detecting blood low-density lipoprotein based on near-infrared spectroscopy according to claim 1, wherein: The method of collecting a user's face video sample and obtaining a blood component spectrum sample includes: Use a near-infrared camera to illuminate the user's face; The optical splitter receives the photoelectric pulse wave corresponding to the outgoing light of each wavelength; The photoelectric converter and the analog-to-digital converter perform signal conversion on the photoelectric pulse wave to obtain data of the changing output light intensity; Calculating absorbance data of various components in the blood based on the data of the changing output light intensity, wherein the absorbance data includes the absorbance data of low-density lipoprotein; Spectral samples of different blood components are obtained according to the absorbance data.
3. The method for detecting blood low-density lipoprotein based on near-infrared spectroscopy according to claim 2, wherein: The method of preprocessing the spectral sample to obtain a blood component spectrum includes: Using Euclidean distance to determine the discrete points of the spectral samples and eliminating invalid spectral samples; The wavelet transform denoising method is used to remove the interference noise of the spectral sample; De-baselining the spectrum of the spectrum sample by using one or more of peak-valley point leveling, bias subtraction, differential processing, and baseline tilting methods; The preprocessed spectral samples are normalized to obtain a preprocessed blood component spectrum.
4. The method for detecting blood low-density lipoprotein based on near-infrared spectroscopy according to claim 2, wherein: After preprocessing the spectral sample to obtain a blood component spectrum, the method further includes: constructing a spectrum database according to the blood component spectrum; The spectrum database is constructed with an ideal value sub-database, a critical value sub-database and an excessive value sub-database according to the control standard of low-density lipoprotein content.
5. The method for detecting blood low-density lipoprotein based on near-infrared spectroscopy according to claim 1, wherein: The method of constructing a discrimination model using known blood component content data and its corresponding blood spectrogram includes: Obtaining blood component content data and its corresponding blood spectrogram; Selecting a chemometric algorithm to pre-process the blood spectrogram; The principal component analysis method was used to construct a discriminant model based on the blood component content data and the preprocessed blood spectra.
6. The method for detecting blood low-density lipoprotein based on near-infrared spectroscopy according to claim 4, wherein: After inputting the blood component spectrum into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood, the method further includes: Compare the low-density lipoprotein content value with the control standard and output the judgment result as an ideal value, a critical value or an excessive value; According to the judgment result, the blood spectra corresponding to different low-density lipoproteins are stored in the ideal value sub-database, the critical value sub-database or the excessive value sub-database.
7. A blood low-density lipoprotein detection system based on near-infrared spectroscopy, characterized in that: include: The video acquisition module is used to collect user face video samples and obtain blood component spectrum samples; A spectrum processing module, used for pre-processing the spectrum sample to obtain a blood component spectrum; The model processing module is used to construct a discrimination model using known blood component content data and its corresponding blood spectra; and is also used to: The blood component spectrum is input into the discrimination model to obtain the corresponding low-density lipoprotein content in the blood.
8. The blood low-density lipoprotein detection system based on near-infrared spectroscopy according to claim 7, characterized in that: The spectrum processing module is further used to: constructing a spectrum database according to the blood component spectrum; The spectrum database is constructed with an ideal value sub-database, a critical value sub-database and an excessive value sub-database according to the control standard of low-density lipoprotein content.
9. The blood low-density lipoprotein detection system based on near-infrared spectroscopy according to claim 8, characterized in that: The spectrum processing module is further used to: Compare the low-density lipoprotein content value with the control standard and output the judgment result as an ideal value, a critical value or an excessive value; According to the judgment result, the blood spectra corresponding to different low-density lipoproteins are stored in the ideal value sub-database, the critical value sub-database or the excessive value sub-database.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.
Citation Information
Cited By
Method and device for detecting creatinine content information of blood
CN119770037A
