Method and device for realizing cardiac function discrimination based on near infrared spectrum technology

Abstract

The invention discloses a method and a device for realizing cardiac function discrimination through a near infrared spectrum technology, and the method comprises the steps: obtaining a to-be-discriminated human face near infrared spectrogram, and carrying out the preprocessing of the near infrared spectrogram; inputting the preprocessed data and user age information corresponding to the near infrared spectrum into a pre-trained discrimination model, and outputting by the discrimination model to obtain a cardiac function discrimination level corresponding to the to-be-discriminated face near infrared spectrum; wherein the pre-trained discrimination model is constructed based on a partial least square method. The cardiac function level is judged based on the near infrared spectrogram, so that the detection complexity is reduced, and the detection efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of information intelligent processing technology, specifically to a method for cardiac function discrimination based on near-infrared spectroscopy. Background Technology

[0002] Currently, clinically common methods for evaluating cardiac function fall into two main categories: non-invasive and invasive. Non-invasive cardiac function testing methods mainly include echocardiography, mechanocardiography to measure the different phases of the cardiac cycle, radionuclide imaging, cardiovascular angiography, electrocardiogram stress testing, and combined cardiac tests via tube or atrial transfer. Invasive cardiac function testing methods mainly include left heart catheterization (left ventriculography to measure left ventricular ejection fraction) and right heart catheterization (insertion of a floating catheter to the right side of the heart, and thermodilution to measure cardiac output). These methods are cumbersome, time-consuming, and labor-intensive, and cannot be used for self-monitoring anytime, anywhere.

[0003] Therefore, there is an urgent need for a non-invasive, rapid, and accurate method for evaluating and assessing cardiac function. Summary of the Invention

[0004] The main objective of this invention is to provide a method for determining cardiac function based on near-infrared spectroscopy, thereby addressing the shortcomings of related technologies.

[0005] To achieve the above objectives, according to a first aspect of the present invention, a method for cardiac function discrimination based on near-infrared spectroscopy is provided, comprising: after acquiring a near-infrared spectral image of a face to be discriminated against, preprocessing the near-infrared spectral image; inputting the preprocessed data and the user's age information corresponding to the near-infrared spectral image into a pre-trained discrimination model, and outputting the cardiac function discrimination level corresponding to the near-infrared spectral image of the face to be discriminated against from the discrimination model; wherein the pre-trained discrimination model is constructed based on partial least squares method.

[0006] Optionally, preprocessing the near-infrared spectrum includes determining the detection index value of a specified substance based on the near-infrared spectrum.

[0007] Optionally, the method for training the discriminant model includes: acquiring training near-infrared spectral training samples and constructing an independent variable matrix based on the training samples; constructing a label matrix based on the labels corresponding to the near-infrared spectra, wherein the independent variable matrix is ​​determined based on the specified substance detection index value and user age information; decomposing the independent variable matrix and the label matrix, and maximizing the covariance of the independent variable matrix and the label matrix; extracting the combination with the strongest correlation between the spatial information of the independent variable matrix and the spatial information of the label matrix; optimizing the number of principal components based on a cross-validation strategy; and optimizing parameters based on the principal component data during the training process.

[0008] Optionally, parameter optimization based on principal component data during training includes: determining the optimal interval of principal components through parameter tuning; and searching within the optimal interval until the principal components improve the performance of the validation set to a set value.

[0009] Optionally, the specified substance detection indicators include aspartate aminotransferase (AST), troponin, creatine kinase isoenzyme, lipoprotein a, triglycerides, fasting blood glucose, C-reactive protein, and myoglobin.

[0010] Optionally, the discrimination level includes anomaly level, and / or the level range corresponding to the anomaly level, the number of anomaly scalars, and the decay factor.

[0011] According to a second aspect of the present invention, an apparatus for cardiac function discrimination based on near-infrared spectroscopy is provided, comprising a preprocessing unit for preprocessing the near-infrared spectral image of a face to be discriminated against after acquisition; and a cardiac function discrimination unit for inputting the preprocessed data and user age information corresponding to the near-infrared spectrum into a pre-trained discrimination model, and outputting the cardiac function discrimination level corresponding to the near-infrared spectral image of the face to be discriminated against from the discrimination model; wherein the pre-trained discrimination model is constructed based on partial least squares method.

[0012] According to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing the computer to perform the method described in any one of the first aspects.

[0013] According to a fourth aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the method described in any implementation of the first aspect.

[0014] This embodiment presents a method and apparatus for determining cardiac function using near-infrared spectroscopy. The method includes: acquiring a near-infrared spectral image of a face to be determined; preprocessing the near-infrared spectral image; inputting the preprocessed data and the user's age information corresponding to the near-infrared spectrum into a pre-trained discrimination model; and outputting the cardiac function level corresponding to the near-infrared spectral image of the face to be determined from the discrimination model. The pre-trained discrimination model is constructed based on partial least squares (PLS) method. Determining cardiac function level based on near-infrared spectroscopy reduces detection complexity and improves detection efficiency. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a method for determining cardiac function based on near-infrared spectroscopy according to an embodiment of the present invention;

[0017] Figure 2 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] Predicting heart function using substances in the blood is a cutting-edge field of medical research. Chemicals and biomarkers in the blood reflect the body's internal health, including heart function. Currently, there is limited publicly available data supporting the establishment of blood substance index datasets for different heart function levels and the application of mature machine learning and other classification algorithms to predict heart function levels based on given blood substance levels.

[0022] According to embodiments of the present invention, a method for determining cardiac function based on near-infrared spectroscopy is provided, such as... Figure 1 As shown, steps 101 to 103 are included below:

[0023] Step 101: After obtaining the near-infrared spectrum of the face to be identified, the near-infrared spectrum is preprocessed.

[0024] In this step, near-infrared spectral imaging technology is used to deeply capture the spectral characteristics of different trace substances in the core area of ​​the human face, observing their absorption of energy at specific wavelengths. Based on these spectral characteristics, the corresponding detection index value for a specified substance can be obtained. During the extraction of spectral features, several original feature variables are extracted; these original feature variables are then corrected using a standard normal variable transformation method.

[0025] As an optional implementation of this embodiment, preprocessing the near-infrared spectrum includes determining the detection index value of a specified substance based on the near-infrared spectrum.

[0026] In this optional implementation, the near-infrared spectrum is processed to obtain indicators of substances related to cardiac function, namely, aspartate aminotransferase (AST), troponin, creatine kinase isoenzyme, lipoprotein a, triglycerides, fasting blood glucose, C-reactive protein, and myoglobin, thus laying the foundation for evaluating and judging cardiac function. That is, any abnormality in one or more indicators, combined with relevant age and other indicators, may indicate a potential functional problem. For example: 1) AST: In some patients with chronic heart disease and heart failure, AST levels may be slightly elevated, especially in cases of severe cardiac failure. This is because long-term cardiac overload or ischemia can lead to myocardial cell damage; 2) Troponin: A protein specific to myocardial cells, released into the bloodstream when the heart is damaged. Elevated troponin levels are usually associated with myocardial injury (such as myocardial infarction) and are an important biomarker for diagnosing acute cardiac events; 3) Creatine kinase isoenzyme: CK-MB levels rise during myocardial injury. Although troponin is more sensitive, CK-MB can still serve as an auxiliary diagnostic tool for cardiac injury; 4) Lipoprotein a: It is associated with the progression of chronic heart failure (CHF), especially in patients with coronary heart disease or myocardial infarction. In addition, lipoprotein a affects the blood supply and myocardial function of the heart by promoting atherosclerosis and exacerbating thrombus formation. Lp(a) may hinder the repair process after cardiac injury by inhibiting thrombolysis and promoting inflammation of the blood vessel wall, leading to a further decline in cardiac function; 5) Triglycerides: They are usually associated with increased cardiovascular risk, especially with heart diseases such as atherosclerosis, coronary heart disease (including myocardial infarction), and heart failure. Although triglycerides themselves do not directly reflect cardiac function, changes in their blood levels can serve as an early indication of heart failure and cardiovascular risk. By regularly monitoring triglyceride levels and combining them with other cardiac markers (such as troponin, BNP, etc.) for comprehensive assessment, doctors can help determine the patient's cardiac health status and potential cardiovascular risk; 6) Blood glucose levels: Diabetes and hyperglycemia are important risk factors for heart disease. Long-term high blood sugar can lead to vascular damage and heart attacks; 7) C-reactive protein (CRP): CRP is an acute-phase protein secreted by the liver and is an indicator of inflammatory responses in the body. Long-term high CRP levels are associated with cardiovascular diseases (such as arteriosclerosis and heart disease). Myoglobin's role is closely related to heart function, especially during heart damage, when myoglobin is released into the bloodstream. Therefore, it can serve as a marker of heart damage, helping to assess heart health.

[0027] Step 102: Input the preprocessed data and the user age information corresponding to the near-infrared spectrum into the pre-trained discrimination model, and output the cardiac function discrimination level corresponding to the near-infrared spectrum of the face to be judged by the discrimination model. The pre-trained discrimination model is constructed based on the partial least squares method.

[0028] In this step, a PLS-DA discriminant model is constructed based on partial least squares regression. The preprocessed data is input into the PLS-DA evaluation and discriminant model for training to obtain the optimal PLS-DA evaluation and discriminant model. Here, cardiac function level prediction is actually a classification process, which can be achieved using a mature classification algorithm. PLS-DA (Partial Least Squares Discriminant Analysis) is a statistical method mainly used for classification and discriminant analysis of high-dimensional data. This method is particularly useful in fields such as bioinformatics, chemometrics, and metabolomics for extracting and identifying patterns from complex datasets. PLS-DA is based on partial least squares regression (PLS), but unlike PLS, PLS-DA focuses on classification problems.

[0029] The near-infrared spectra to be evaluated and discriminated are input into the optimal PLS-DA evaluation and discriminant model to obtain the cardiac function evaluation and discriminant results corresponding to the near-infrared spectra to be evaluated and discriminated. The discriminant results include no abnormality, mild abnormality, moderate abnormality, and severe abnormality.

[0030] As an optional implementation of this embodiment, the method for training the discriminant model includes: acquiring training near-infrared spectral training samples and constructing an independent variable matrix based on the training samples; constructing a label matrix based on the labels corresponding to the near-infrared spectra, wherein the independent variable matrix is ​​determined based on the specified substance detection index value and user age information; decomposing the independent variable matrix and the label matrix, and maximizing the covariance of the independent variable matrix and the label matrix; extracting the combination with the strongest correlation between the spatial information of the independent variable matrix and the spatial information of the label matrix; optimizing the number of principal components based on a cross-validation strategy; and optimizing parameters based on the principal component data during the training process.

[0031] In this optional implementation, when potential multicollinearity exists and the number of observed values ​​is less than the number of variables, a threshold is set after selecting latent variables based on the cross-validation results. If the predicted value is greater than the threshold, the variable belongs to the current category; if the predicted value is less than the threshold, the variable does not belong to the current category. The optimal number of latent variables is selected to construct the PLS-DA evaluation and discrimination model.

[0032] Specifically, the independent variable matrix X and the label matrix Y are decomposed simultaneously; the weight vector is iteratively solved to maximize the covariance of X and Y; the latent variable scores are calculated to extract the combination with the strongest correlation between the spatial information of X and the spatial information of Y, thereby completing the spatial projection of the latent variables. Further, principal component optimization is performed. For example, a 10-fold cross-validation strategy can be used, randomly dividing the data into 10 equal parts, with 9 parts as the training set and 1 part as the validation set, looping 10 times to ensure that each part of the data is validated. The search range is to test 1 to 20 principal components (n_components), and the evaluation metrics are validation set accuracy and AUC value.

[0033] As an optional implementation method in this embodiment, parameter optimization based on principal component data during training includes: determining the optimal interval of principal components through parameter tuning; and searching within the optimal interval, terminating when the principal components improve the performance of the validation set to a set value.

[0034] The parameter optimization process includes the following steps: First, coarse tuning, recording the performance curves for different numbers of principal components; determining the optimal interval, selecting the range of principal components with an accuracy ≥ 95% and an AUC ≥ 0.98; Second, fine tuning, performing a fine search within the optimal interval at 0.5 intervals; The convergence condition is that the process terminates when adding new principal components improves the validation set performance by < 0.5%.

[0035] Furthermore, the performance of the trained PLS-DA evaluation and discrimination model is evaluated based on the validation set to obtain a PLS-DA evaluation and discrimination model that meets the performance conditions; the prediction results of the PLS-DA evaluation and discrimination model that meets the performance conditions are evaluated based on the test set to obtain the evaluation index corresponding to the PLS-DA evaluation and discrimination model.

[0036] Through formula Y pre =T pre BQ calculates the categorical variable value Ypre for the test set; Tpre is the score of the spectral matrix Xpre for the test set; Q is the loading matrix of the spectral matrix in the optimal spectral range of the validation set; and T is the score matrix of the spectral matrix in the optimal spectral range of the validation set.

[0037] In addition to the results including classifications of no abnormality, mild abnormality, moderate abnormality, and severe abnormality, the results also include the information shown in Table 1:

[0038] Table 1

[0039]

[0040]

[0041] Under the assumed conditions, when the age is >45 years, the decline in cardiac function is significant when the levels of related substances are abnormal.

[0042] Based on empirical knowledge, indicators such as aspartate aminotransferase (AST), troponin, creatine kinase isoenzyme, lipoprotein a, triglycerides, fasting blood glucose, C-reactive protein, and myoglobin are screened and divided according to age groups to achieve the probability distribution of certain specific indicators within different age groups, simulating the mode mechanism.

[0043] For example:

[0044] When testing, users enter their own attribute information (such as age). Taking a user aged 65 as an example, their abnormal detection indicators may include four items: triglycerides, lipoproteins, troponin, and creatine kinase isoenzymes. The total number of abnormal indicators directly determines the assessed cardiac function level (if one or two abnormal indicators are present, the level is rated as mildly abnormal). At the same time, there is a corresponding decline factor under the function level, which is used to describe the degree of cardiac decline under the current cardiac function level (based on the normal degree of decline). If two abnormal indicators are present, the cardiac function level is mildly abnormal, the decline factor is 3.5, and the estimated cardiac age is 65 + 3.5 = 68.5.

[0045] This invention discloses a method and system for evaluating and discriminating cardiac function based on near-infrared spectroscopy. The method includes: collecting near-infrared spectra of a certain number of human blood samples; performing spectral processing on the near-infrared spectra to obtain preprocessed data; constructing a PLS-DA evaluation and discrimination model based on partial least squares (PLS-DA); inputting the preprocessed data into the PLS-DA evaluation and discrimination model for training to obtain an optimal PLS-DA evaluation and discrimination model; and inputting the near-infrared spectra to be evaluated and discriminating into the optimal PLS-DA model to obtain the cardiac function evaluation and discrimination results corresponding to the near-infrared spectra. The evaluation and discrimination results include four levels: no abnormality, mild abnormality, moderate abnormality, and severe abnormality. This invention utilizes near-infrared spectroscopy combined with the PLS-DA method to rapidly detect the elemental content in human blood and accurately predict and evaluate cardiac function.

[0046] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0047] According to an embodiment of the present invention, a device for cardiac function discrimination based on near-infrared spectroscopy is also provided, comprising: a preprocessing unit, configured to preprocess the near-infrared spectral image of a face to be discriminated after acquiring the near-infrared spectral image of the face to be discriminated; and a cardiac function discrimination unit, configured to input the preprocessed data and the user's age information corresponding to the near-infrared spectrum into a pre-trained discrimination model, and to output the cardiac function discrimination level corresponding to the near-infrared spectral image of the face to be discriminated from the discrimination model; wherein the pre-trained discrimination model is constructed based on partial least squares method.

[0048] As an optional implementation of this embodiment, the preprocessing of the near-infrared spectrum includes determining the detection index value of a specified substance based on the near-infrared spectrum.

[0049] As an optional implementation of this embodiment, the device includes a training unit for acquiring training samples of near-infrared spectra and constructing an independent variable matrix based on the training samples; constructing a tag matrix based on the tags corresponding to the near-infrared spectra, wherein the independent variable matrix is ​​determined based on the specified substance detection index value and user age information; decomposing the independent variable matrix and the tag matrix and maximizing the covariance of the independent variable matrix and the tag matrix; extracting the combination with the strongest correlation between the spatial information of the independent variable matrix and the spatial information of the tag matrix; optimizing the number of principal components based on a cross-validation strategy; and optimizing parameters based on the principal component data during the training process.

[0050] As an optional implementation method in this embodiment, parameter optimization based on principal component data during training includes: determining the optimal interval of principal components through parameter tuning; and searching within the optimal interval, terminating when the principal components improve the performance of the validation set to a set value.

[0051] As an optional implementation of this embodiment, the specified substance detection indicators include aspartate aminotransferase (AST), troponin, creatine kinase isoenzyme, lipoprotein a, triglycerides, fasting blood glucose, C-reactive protein, and myoglobin.

[0052] As an optional implementation of this embodiment, the discrimination level includes anomaly level, and / or the level range corresponding to the anomaly level, the number of anomaly scalars, and the decay factor.

[0053] According to embodiments of the present invention, the present invention also provides an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the methods described in any of the above embodiments.

[0054] According to embodiments of the present invention, the present invention also provides a readable storage medium storing computer instructions that enable a computer to perform the methods described in any of the above embodiments when executed.

[0055] According to embodiments of the present invention, the present invention also provides a computer program product that, when executed by a processor, can implement the methods described in any of the above embodiments.

[0056] Figure 2 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0057] like Figure 2 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0058] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0059] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the methods described above may be performed.

[0060] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0061] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0062] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

Claims

1. A method for determining cardiac function based on near-infrared spectroscopy, characterized in that, include: After obtaining the near-infrared spectral image of the face to be identified, the near-infrared spectral image is preprocessed. The preprocessed data and the user's age information corresponding to the near-infrared spectrum are input into the pre-trained discrimination model, and the discrimination model outputs the cardiac function discrimination level corresponding to the near-infrared spectrum of the face to be judged. The pre-trained discriminant model is constructed based on partial least squares.

2. The method for determining cardiac function based on near-infrared spectroscopy according to claim 1, characterized in that, Preprocessing the near-infrared spectrum includes determining the detection index value of a specified substance based on the near-infrared spectrum.

3. The method for determining cardiac function based on near-infrared spectroscopy according to claim 1, characterized in that, The method for training the discriminant model includes: Acquire training samples of near-infrared spectra and construct an independent variable matrix based on the training samples; construct a tag matrix based on the tags corresponding to the near-infrared spectra, wherein the independent variable matrix is ​​determined based on the specified substance detection index values ​​and user age information; Decompose the independent variable matrix and the label matrix, and maximize the covariance of the independent variable matrix and the label matrix; extract the combination with the strongest correlation between the spatial information of the independent variable matrix and the spatial information of the label matrix; optimize the principal component count based on the cross-validation strategy; Parameter optimization is performed based on principal component data during training.

4. The method for determining cardiac function based on near-infrared spectroscopy according to claim 3, characterized in that, Parameter optimization based on principal component data during training includes: The optimal interval of the principal components is determined by parameter tuning; and the search is performed within the optimal interval until the performance of the validation set is improved to a set value by the principal components.

5. The method for determining cardiac function based on near-infrared spectroscopy according to claim 2, characterized in that, The specified substance detection indicators include aspartate aminotransferase, troponin, creatine kinase isoenzyme, lipoprotein a, triglycerides, fasting blood glucose, C-reactive protein, and myoglobin.

6. The method for determining cardiac function based on near-infrared spectroscopy according to claim 1 is characterized in that, The discrimination level includes the anomaly level, and / or the level range corresponding to the anomaly level, the number of anomaly scalars, and the decay factor.

7. A device for determining cardiac function based on near-infrared spectroscopy, characterized in that, include: The preprocessing unit is used to preprocess the near-infrared spectrum of the face to be identified after acquiring the near-infrared spectrum. The cardiac function discrimination unit is used to input the preprocessed data and the user's age information corresponding to the near-infrared spectrum into the pre-trained discrimination model, and the discrimination model outputs the cardiac function discrimination level corresponding to the near-infrared spectrum of the face to be judged. The pre-trained discriminant model is constructed based on partial least squares.

8. The device for determining cardiac function based on near-infrared spectroscopy technology according to claim 7, characterized in that, The preprocessing of the near-infrared spectrum includes determining the detection index value of a specified substance based on the near-infrared spectrum.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method according to any one of claims 1-6.

10. An electronic device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the method according to any one of claims 1-6.

Images