Method for evaluating postprandial blood glucose response of human body based on continuous blood glucose data and application

Abstract

The invention discloses a method for evaluating postprandial blood glucose response of a human body based on continuous blood glucose data and application. The method comprises the following steps: acquiring a continuous blood glucose detection value and meal starting time; matching a first blood glucose recording point after eating according to the dining time, intercepting blood glucose data of 2 hours after meal, and preprocessing the data; constructing four postprandial blood glucose response modes by applying the continuous blood glucose data of FPCA and based on a characteristic function of which the interpretation degree ranks top two obtained by the FPCA; through comparison of postprandial blood glucose response mean value curves of the four blood glucose response modes, the four response modes can evaluate postprandial blood glucose by integrating the blood glucose concentration range and whether the fasting homeostasis can be rapidly recovered or not.

Description

Technical Field

[0001] The present invention belongs to the technical field of nutritional intervention, and particularly relates to a method and application for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data. Background Art

[0002] In recent years, the importance of postprandial blood glucose management in metabolic health and diabetes control has received extensive attention. Research has shown that a significant increase in postprandial blood glucose is an important risk factor for metabolic disorders such as prediabetes, type 2 diabetes, and cardiovascular diseases. Effectively controlling postprandial blood glucose fluctuations can not only improve insulin resistance and overall pancreatic islet function but also help prevent diabetes complications. With the progress of science, many drugs and therapies have been designed to reduce postprandial blood glucose fluctuations.

[0003] The blood glucose level fluctuations caused by the body after eating have significant individual differences and are affected by multiple factors, including genes, gut microbiota, lifestyle, metabolic status, and the composition and combination of foods. Traditional standardized blood glucose management methods often ignore these individual differences, resulting in limited effectiveness in controlling postprandial blood glucose fluctuations. In response to this challenge, researchers have gradually turned to personalized intervention strategies, developing personalized diet plans, nutritional interventions, and treatment plans by combining multi-dimensional biological data to more effectively manage postprandial blood glucose. This precision intervention strategy based on individual characteristics shows great potential in improving metabolic health, reducing the risk of diabetes and its complications, and has broad application prospects.

[0004] The current methods for evaluating postprandial blood glucose response mainly rely on single-point blood glucose values such as peak value and the area under the curve of postprandial blood glucose increment to characterize an individual's postprandial blood glucose response to different nutritional interventions and make dietary choices accordingly. However, the use of these two indicators in clinical practice has certain limitations. On the one hand, there is no clear reference range for the area under the curve of postprandial blood glucose increment in clinical practice, making it difficult to apply to clinical blood glucose management for different populations. In addition, insulin is the key to postprandial blood glucose regulation, and the first-phase and second-phase releases of insulin have different physiological meanings, and whether their releases are normal will directly affect an individual's glucose metabolism ability. However, the area under the curve of postprandial blood glucose increment cannot identify the characteristics of insulin dynamically regulating postprandial blood glucose. On the other hand, although a large amount of research evidence has proven that single-point blood glucose values are of great significance for the occurrence and development of diabetes, such as peak value, blood glucose value at one hour after a meal, blood glucose value at two hours after a meal, etc., single-point blood glucose values cannot fully reflect the characteristics of postprandial blood glucose response in terms of shape and development trend. When evaluating postprandial blood glucose response, these values can only provide limited information. Given the complexity and dynamics of the human body's physiology, further identifying postprandial blood glucose characteristics from the time dimension can better reflect the ability of the human body to regulate glucose metabolism compared to the blood glucose value at a certain time point or the overall measurement index.

[0005] Therefore, how to solve the problems that the single-point blood glucose value cannot evaluate the change characteristics of continuous blood glucose data, and the area of blood glucose increment commonly used in continuous blood glucose data cannot evaluate the postprandial blood glucose control range and quickly obtain the fasting steady state, so as to provide a more accurate evaluation of the postprandial blood glucose response pattern for individuals and open up a new path for realizing personalized postprandial blood glucose response evaluation, is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0006] The first object of the present invention is to comprehensively evaluate and classify the postprandial blood glucose response pattern from the time dimension, and in view of the problem that the prior art cannot comprehensively describe the postprandial blood glucose response from the time dimension, a postprandial blood glucose evaluation and classification model based on time series algorithm is provided.

[0007] To this end, the above object of the present invention is achieved by the following technical solutions: A method for evaluating the postprandial blood glucose response of a human body based on continuous blood glucose data, characterized by comprising the following steps: S1, data collection: Each sample data collected includes the meal time point, continuous blood glucose concentration and its corresponding time point; S2, data preprocessing: Matching the meal time point, intercepting the blood glucose data, processing the missing values so that the number of single-postprandial response blood glucose data points is not less than 9, and standardization processing: calculating the mean μ and standard deviation σ of the postprandial blood glucose data set, and through the formula Converting the collected data into a standardized data set with a mean of 0 and a standard deviation of 1 to eliminate the dimension difference and obtain the postprandial blood glucose data set; S3, performing FPCA processing on the postprandial blood glucose data set in step S2: Using a Gaussian kernel function to smooth the postprandial blood glucose data set, processing the boundary points through mirror filling and calculating the weighted average value of each data point to reduce noise interference and retain the data trend; then, constructing a covariance matrix according to the smoothed postprandial blood glucose data set, and calculating the eigenvalues and eigenvectors; finally, sorting according to the eigenvalue size, and selecting the eigenvectors corresponding to the first two largest eigenvalues (the top two in contribution degree ranking) as eigenfunction Ⅰ and eigenfunction Ⅱ; S4, calculating the projection values of the postprandial blood glucose curve on eigenfunction Ⅰ and eigenfunction Ⅱ through inner product: Based on step S3, according to eigenfunction Ⅰ and eigenfunction Ⅱ of the postprandial blood glucose data set, calculate the projection values of the postprandial blood glucose curve of each meal on eigenfunction Ⅰ and eigenfunction Ⅱ.

[0008] S5, respectively calculating the median value of the projection values of eigenfunction Ⅰ in the postprandial blood glucose data set and the median value of the projection values on eigenfunction Ⅱ; S6, Postprandial blood glucose response assessment: By calculating the projection values of the single-meal blood glucose response on eigenfunction Ⅰ and eigenfunction Ⅱ respectively, and comparing them with the median values of the projection values of eigenfunction Ⅰ and eigenfunction Ⅱ of the postprandial blood glucose dataset, it is used to evaluate the postprandial blood glucose response.

[0009] While adopting the above technical solutions, the present invention can also adopt or combine the following technical solutions: As a preferred technical solution of the present invention: In step S1, the collected data includes recording the meal time of each meal, and obtaining the continuous blood glucose concentration and its corresponding time points after the meal through CGM or venous blood samples. Among them, the blood glucose monitoring time after each meal is greater than or equal to 2 hours, and the monitoring intervals are the same, and the interval between two time points does not exceed 15 minutes.

[0010] As a preferred technical solution of the present invention: In step S2, according to each meal time point of the sample, the first blood glucose concentration value recording point after the meal is matched and the blood glucose data for 2 hours after the meal is intercepted. And each blood glucose data point after the meal is used as a list and stored in the postprandial blood glucose dataset.

[0011] As a preferred technical solution of the present invention: Step S3 includes the following steps: S3.1 Data smoothing processing: Use the Gaussian kernel function parameter to smooth the postprandial blood glucose dataset, perform mirror filling processing on the boundary points, traverse each data point, calculate its weighted average value, and finally output the smoothed postprandial blood glucose dataset to reduce noise interference and retain the data trend; S3.2 Calculate the covariance matrix: Calculate the mean value of all samples for each time point. Two time points i and j form a pair of time points. Use a double loop to traverse each pair of time points (i,j) to calculate the covariance. For each pair of time points, calculate the covariance of all samples, and fill the calculated covariance value into the covariance matrix to obtain the covariance matrix of the postprandial blood glucose dataset; S3.3 Eigenfunction decomposition: Decompose the covariance matrix to obtain eigenvalues and eigenvectors, and the obtained eigenvectors represent eigenfunctions; S3.4 Eigenfunction selection: Sort the eigenvalues according to the magnitude of the eigenvalues, and select the eigenvectors corresponding to the first two largest eigenvalues (the top two in terms of contribution degree) as eigenfunction Ⅰ and eigenfunction Ⅱ.

[0012] As a preferred technical solution of the present invention: In step S3.1, the smoothing parameter is selected as 0.1.

[0013] As a preferred technical solution of the present invention: in the step S3.2, the smoothed postprandial blood glucose data set is X, which contains n samples and m time points. The covariance matrix C is an m×m matrix, and the element in the i-th row and j-th column represents the covariance between the i-th time point and the j-th time point. The calculation formula of the covariance is

[0014] where refers to the blood glucose concentration value of the k-th sample at the i-th time point, refers to the blood glucose concentration value of the k-th sample at the j-th time point, is the mean value of the i-th time point, is the mean value of the j-th time point, and n is the number of samples.

[0015] As a preferred technical solution of the present invention: in the step S3.4, the cumulative explained variance of the eigenfunction Ⅰ and the eigenfunction Ⅱ is greater than 80%, and it is determined that the top two eigenfunctions obtained by FPCA can fully represent the variability of the postprandial blood glucose response, while reducing the dimension of the features; The explained variance of each eigenvalue λi is calculated by the following formula: Explained variance ratio = , where: λi is the i-th eigenvalue; is the sum of all eigenvalues.

[0016] As a preferred technical solution of the present invention: in the step S6, four different postprandial blood glucose response patterns are constructed based on the median of the projection values of the top two eigenfunctions of the postprandial blood glucose data set. Among them, if the projection values of the single blood glucose response data on the eigenfunction Ⅰ and the eigenfunction Ⅱ are less than the median, it is judged as L, and if it is greater than or equal to the median, it is judged as H: HH mode: The eigenfunction Ⅰ estimate is judged as H, and the eigenfunction Ⅱ estimate is judged as H; HL mode: The eigenfunction Ⅰ estimate is judged as H, and the eigenfunction Ⅱ estimate is judged as L; LH mode: The eigenfunction Ⅰ estimate is judged as L, and the eigenfunction Ⅱ estimate is judged as H; LL mode: The eigenfunction Ⅰ estimate is judged as L, and the eigenfunction Ⅱ estimate is judged as L.

[0017] The second object of the present invention is to provide an application of the method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data.

[0018] For this reason, the above object of the present invention is achieved by the following technical solutions: An application of a method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data, characterized in that Applied to judge the good and bad postprandial blood glucose responses, where the HL mode is determined as the good response mode; the LH mode, HH mode, and LL mode are determined as the bad response modes.

[0019] Compared with the prior art, the method and application for evaluating the postprandial blood glucose response of a human body based on continuous blood glucose data of the present invention have the following beneficial effects: The present invention uses functional principal component analysis to extract eigenfunction Ⅰ and eigenfunction Ⅱ from the postprandial blood glucose dataset to capture the main trends and variations of the postprandial blood glucose curve, effectively filtering out noise and unimportant information and retaining the main change patterns of the data; by calculating the projection values of the postprandial blood glucose curve on eigenfunction Ⅰ and eigenfunction Ⅱ, the projection values reflect the similarity between the postprandial blood glucose curve and the eigenfunction, quantifying the contribution of each curve to the main change pattern and facilitating the quantification of the blood glucose response characteristics of an individual; using the median of the projection values of eigenfunction Ⅰ and eigenfunction Ⅱ in the postprandial blood glucose dataset as a reference benchmark, comparing the projection value of a single meal with the median to evaluate the blood glucose response intensity at each time point and identifying the main blood glucose fluctuation patterns; by calculating the projection values of the blood glucose response curve of a single meal on eigenfunction Ⅰ and eigenfunction Ⅱ, identifying the dynamic characteristics of the postprandial blood glucose change, opening up a new path for evaluating the personalized postprandial blood glucose of a human body and providing a basis for dynamically adjusting nutritional intervention.

[0020] Specifically, in the present invention, FPCA analysis is used to capture the whole-course fluctuations of blood glucose within 2 hours after a meal. By capturing the instantaneous changes and overall trends of blood glucose, it ensures the complete record of the dynamic changes of blood glucose and the fluctuations at different time points, solving the problems of inaccuracy and non-comprehensiveness of obtaining only the value at a certain time point or a certain comprehensive quantification index; by comprehensively analyzing the data at multiple time points, it provides a more accurate evaluation of postprandial blood glucose, especially in terms of the sensitivity and recovery ability of glucose metabolism regulation; in the present invention, the first two eigenfunctions are extracted by FPCA, which can explain more than 80% of the variance of the postprandial blood glucose response variability, significantly reducing the data dimension while retaining the main variability of the data, solving the problem of overly long and complex data processing in traditional methods, making the analysis of large-scale postprandial blood glucose data more efficient, and at the same time still being able to maintain the interpretability of data variability, realizing the dimensionality reduction and efficient analysis of postprandial blood glucose data; the application of FPCA can effectively smooth the noise data, reduce the influence of monitoring errors on the evaluation results of blood glucose values, and improve the stability and accuracy of the results.

[0021] A method and application for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data. By using Feature Function I and Feature Function II to extract the main trend and variations of the postprandial blood glucose curve, combined with projection value calculation and median comparison, the individual blood glucose response characteristics are accurately quantified, and the dynamic change patterns are identified. More comprehensive blood glucose fluctuation information can be obtained, which helps to more accurately evaluate the change trend and pattern of postprandial blood glucose. By analyzing the blood glucose values at multiple time points and comprehensively considering the information on both the postprandial blood glucose control range and the rapid restoration of homeostasis, the postprandial blood glucose response can be better evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flowchart of the method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data; Figure 2 is the visualization of Feature Function I and Feature Function II and four postprandial blood glucose response patterns. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.

[0024] As Figure 1 - Figure 2 shown, the method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data of the present invention includes the following steps: S1. Data collection: Each sample data collected includes the meal time point, continuous blood glucose concentration and its corresponding time point; S2. Data preprocessing: Matching the meal time point, intercepting the blood glucose data, processing the missing values so that the number of single postprandial response blood glucose data points is not less than 9, and standardization processing: calculating the mean μ and standard deviation σ of the postprandial blood glucose data set, and converting the collected data into a standardized data set with a mean of 0 and a standard deviation of 1 through the formula to obtain a postprandial blood glucose data set for eliminating the dimension difference; S3. Performing FPCA processing on the postprandial blood glucose data set in step S2: Using a Gaussian kernel function to smooth the postprandial blood glucose data set, processing the boundary points through mirror filling and calculating the weighted average value of each data point to reduce noise interference and retain the data trend; then, constructing a covariance matrix based on the smoothed postprandial blood glucose data set, and calculating the eigenvalues and eigenvectors; finally, sorting according to the eigenvalue size, and selecting the eigenvectors corresponding to the first two largest eigenvalues as Feature Function I and Feature Function II with the top two contribution degrees; S4. Calculating the projection values of the postprandial blood glucose curve on Feature Function I and Feature Function II through inner product: Based on step S3, according to Feature Function I and Feature Function II of the postprandial blood glucose data set, calculate the projection values of the postprandial blood glucose curve at each meal time point on Feature Function I and Feature Function II.

[0025] S5. Calculate the median of the projection values of the characteristic function Ⅰ and the median of the projection values on the characteristic function Ⅱ in the postprandial blood glucose dataset respectively; S6. Postprandial blood glucose response assessment: By calculating the projection values of the single-meal blood glucose response on the characteristic function Ⅰ and the characteristic function Ⅱ respectively, and comparing them with the median of the projection values of the characteristic function Ⅰ and the median of the projection values of the characteristic function Ⅱ in the postprandial blood glucose dataset, it is used to evaluate the postprandial blood glucose response.

[0026] When collecting data: Record the meal time of each meal, and obtain the continuous blood glucose concentration and its corresponding time points after the meal through CGM or venous blood samples. The blood glucose monitoring time after each meal needs to be greater than or equal to 2 hours, and the monitoring intervals are the same. The interval between two time points does not exceed 15 minutes, that is, the number of blood glucose monitoring data points after each meal needs to be greater than or equal to 9. It is preferred to use CGM for data collection.

[0027] In data preprocessing: Match the first blood glucose concentration value recording point after the meal according to each meal time point and intercept the blood glucose data for 2 hours after the meal, and take each blood glucose data point after the meal as a list and store it in the postprandial blood glucose dataset; supplement the blood glucose data point list with missing values or less than 9 data points in the postprandial blood glucose dataset; perform standardization processing on the postprandial blood glucose dataset, convert the data to a mean of 0 and a standard deviation of 1, and eliminate the dimensional differences between the data.

[0028] Perform FPCA processing on the postprandial blood glucose dataset in step S2, including the following steps: S3.1 Data smoothing processing: Select the Gaussian kernel function parameter (the smoothing parameter is selected as 0.1), calculate the weighted average value centered on each data point; perform mirror filling processing on the boundary points, and finally output the smoothed postprandial blood glucose dataset, effectively reducing noise interference and retaining the data trend; S3.2 Calculate the covariance matrix: Calculate the mean of all samples at each time point. Two time points i and j form a pair of time points. Use a double loop to traverse each pair of time points (i, j) to calculate the covariance. For each pair of time points, calculate the covariance of all samples, and fill the calculated covariance value into the covariance matrix to obtain the covariance matrix of the postprandial blood glucose dataset.

[0029] S3.3 Characteristic function decomposition: Decompose the covariance matrix to obtain eigenvalues and eigenvectors, and the obtained eigenvectors represent characteristic functions; S3.4 Feature function selection: From the obtained feature functions, select the top two feature functions with the highest contribution to the data according to the variance size (eigenvalue size) explained by each feature function. If the cumulative explained variance of the top two feature functions is greater than 80%, it is considered that FPCA can explain the changing trend of the data while reducing the dimensionality of the features; S3.5 Output estimation: Calculate the inner product between the postprandial blood glucose curve of each meal and Feature Function I and Feature Function II to obtain the projection values on Feature Function I and Feature Function II, and calculate the median of the projection values of the continuous postprandial blood glucose dataset on the first two feature functions.

[0030] In the step S3.2, the smoothed postprandial blood glucose dataset is X, which contains n samples and m time points. The covariance matrix C is an m×m matrix, where the element in the i-th row and j-th column represents the covariance between the i-th time point and the j-th time point. The calculation formula for covariance is

[0031] where, refers to the blood glucose concentration value of the k-th sample at the i-th time point, refers to the blood glucose concentration value of the k-th sample at the j-th time point, is the mean value of the i-th time point, is the mean value of the j-th time point, and n is the number of samples.

[0032] In the step S3.4, if the cumulative explained variance of Feature Function I and Feature Function II is greater than 80%, it is determined that the top two feature functions obtained by FPCA can fully characterize the variability of postprandial blood glucose response while reducing the dimensionality of the features; The explained variance of each eigenvalue λi is calculated by the following formula: Explained variance ratio = , where: λi is the i-th eigenvalue; is the sum of all eigenvalues.

[0033] Constructing postprandial blood glucose response patterns: Four different postprandial blood glucose response patterns are constructed based on the median of the projection values of the top two eigenfunctions of the postprandial blood glucose dataset. Among them, if the projection values of the single blood glucose response data on eigenfunction I and eigenfunction II are less than the median, it is judged as L; if it is greater than or equal to the median, it is judged as H: HH (the estimated value of eigenfunction I is H, and the estimated value of eigenfunction II is H), HL (the estimated value of eigenfunction I is H, and the estimated value of eigenfunction II is L), LH (the estimated value of eigenfunction I is L, and the estimated value of eigenfunction II is H), LL (the estimated value of eigenfunction I is L, and the estimated value of eigenfunction II is L); By comparing the mean curves of the four postprandial blood glucose response patterns, the HL pattern meets the clinical blood glucose control range and the postprandial blood glucose regains the fasting steady state at 2 hours after meal, so it is a good response pattern; The LH pattern does not meet the clinical blood glucose control range and the postprandial blood glucose cannot regain the fasting steady state at 2 hours after meal, so it is a poor response pattern.

[0034] Application example of postprandial blood glucose response pattern Collect the postprandial continuous blood glucose dataset that meets the above requirements from the population with normal fasting blood glucose and perform data preprocessing. Subsequently, apply the above FPCA for analysis. The top two eigenfunctions are obtained through the covariance function, and their cumulative explained variance is 85.2%. Therefore, it is considered that FPCA can fully characterize the variability of the data in this dataset. By outputting the estimated values of each list in this postprandial continuous blood glucose dataset on the top two eigenfunctions, it can be calculated that the median of the estimated value of the first eigenfunction of the postprandial blood glucose response of the population with normal fasting blood glucose is 0.085, and the median of the estimated value of the second eigenfunction is 0.82.

[0035] After an individual collects one-time postprandial continuous blood glucose data that meets the above requirements and performs data preprocessing, the Gaussian kernel smoothing method (the smoothing parameter is selected as 0.1) is used to smooth the data. Through the following formula, the inner product of this data and the eigenfunction is calculated to obtain its estimated value on each eigenfunction.

[0036]

[0037] Among them, f(t) is the new input data (the list of postprandial blood glucose data points), is the k-th eigenfunction, is the estimated value of the k-th eigenfunction.

[0038] Subsequently, referring to the medians of eigenfunction I and eigenfunction II calculated for this population, the postprandial blood glucose response pattern of the postprandial blood glucose response curve for a single meal is obtained based on the medians of the two to evaluate the current postprandial blood glucose response.

[0039] In the method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data of the present invention, it has the following characteristics: Collect accurate meal times and continuous blood glucose data that meet the requirements, and perform corresponding data preprocessing.

[0040] Analyze postprandial blood glucose through FPCA to achieve the purpose of evaluating postprandial blood glucose from the time dimension.

[0041] Four postprandial blood glucose patterns constructed using the estimated values of the first two eigenfunctions obtained from FPCA analysis: HH, HL, LL, LH. The postprandial blood glucose patterns can evaluate postprandial blood glucose comprehensively in terms of both the blood glucose control range and the ability to quickly regain fasting homeostasis.

[0042] Compared with the prior art, the method for evaluating the postprandial blood glucose response of the human body based on continuous blood glucose data of the present invention has the following beneficial effects: Evaluate the postprandial blood glucose response from the time dimension: The present invention can capture the full-course fluctuation characteristics of blood glucose within 2 hours after a meal, rather than just the value at a certain time point or a comprehensive quantitative index, thus more accurately reflecting the instantaneous changes and overall trends of blood glucose, providing a more accurate evaluation of the postprandial blood glucose response, especially in terms of the sensitivity and recovery ability of glucose metabolism regulation.

[0043] Reduce the data dimension and improve the calculation efficiency: By extracting the first two eigenfunctions through FPCA, the data dimension is significantly reduced, making the analysis of large-scale postprandial blood glucose data more efficient, while still maintaining the interpretability of data variability, thus avoiding the problems of overly long and complex data processing in traditional methods.

[0044] High accuracy and stability: The application of FPCA can effectively smooth noise data, reduce the influence of individual fluctuations or monitoring errors on the evaluation results of blood glucose values, improve the stability and accuracy of the results, and provide a more reliable basis for clinical decision-making.

[0045] A method and application for evaluating the postprandial blood glucose response based on continuous blood glucose data provided by the present invention, the method comprising: obtaining continuous blood glucose detection values and the start meal time; matching the first blood glucose recording point after eating according to the meal time and intercepting the blood glucose data for 2 hours after the meal and preprocessing the data; applying FPCA to the continuous blood glucose data, and constructing four postprandial blood glucose response patterns based on the first two eigenfunctions with the highest interpretability obtained from the FPCA; proving by comparing the mean curves of the postprandial blood glucose responses of the four blood glucose response patterns that these four response patterns can evaluate the postprandial blood glucose response comprehensively in terms of both the blood glucose concentration range and the ability to quickly regain fasting homeostasis.

[0046] The above specific embodiments are used to explain the present invention, which are only the preferred embodiments of the present invention, rather than limiting the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and scope of the claims of the present invention fall within the protection scope of the present invention.

Claims

1. A method for evaluating a human body's postprandial blood glucose response based on continuous blood glucose data, characterized in that: The following steps are involved: S1, data collection: the collected sample data include meal time points, continuous blood glucose concentrations and their corresponding time points; S2, data preprocessing: matching meal time points, intercepting blood glucose data, processing missing values ​​to a single post-meal response blood glucose data point of no less than 9 and standardization: calculating the mean μ and standard deviation σ of the post-meal blood glucose data set, using the formula The collected data are converted into a standardized data set with a mean of 0 and a standard deviation of 1 to eliminate dimensional differences and obtain a postprandial blood glucose data set; S3, performing functional principal component analysis on the postprandial blood glucose data set in step S2: using a Gaussian kernel function to smooth the postprandial blood glucose data set, processing the boundary points by mirror filling and calculating the weighted average of each data point to reduce noise interference and retain the data trend; then, constructing a covariance matrix based on the smoothed postprandial blood glucose data set, and calculating the eigenvalues ​​and eigenvectors; finally, sorting by eigenvalue size, selecting the eigenvectors corresponding to the first two largest eigenvalues ​​as the eigenfunction I and eigenfunction II with the top two contribution rankings; S4, calculating the projection value of the postprandial blood glucose curve on the characteristic function I and the characteristic function II by inner product: based on step S3, according to the characteristic function I and the characteristic function II of the postprandial blood glucose data set, calculating the projection value of each postprandial blood glucose curve of the data set on the characteristic function I and the characteristic function II; S5, respectively calculating the median value of the projection value of the characteristic function I and the median value of the projection value on the characteristic function II in the postprandial blood glucose data set; S6, evaluation of postprandial blood glucose response: by calculating the projection value of the blood glucose response of a single meal on characteristic function I and the projection value on characteristic function II, and comparing them with the median value of the projection value of characteristic function I and the median value of the projection value of characteristic function II of the postprandial blood glucose dataset, they are used to evaluate the postprandial blood glucose response.

2. The method for evaluating a human body's postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S1, the collected data includes recording the meal time of each meal, and obtaining the continuous blood glucose concentration and its corresponding time point after the meal through a continuous blood glucose monitor or venous blood samples, wherein the blood glucose monitoring time after each meal is greater than or equal to 2 hours, and the monitoring interval is the same, and the interval between two time points does not exceed 15 minutes.

3. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S2, the first blood glucose concentration value recording point after a meal is matched according to each meal time point of the sample and the blood glucose data 2 hours after the meal is intercepted, and the blood glucose data point after each meal is taken as a list and stored in the post-meal blood glucose data set.

4. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: Step S3 includes the following steps: S3.1 Data smoothing: Use the Gaussian kernel function parameters to smooth the postprandial blood glucose data set, use mirror filling processing for the boundary points, traverse each data point, calculate its weighted average, and finally output the smoothed postprandial blood glucose data set to reduce noise interference and retain the data trend; S3.2 Calculate the covariance matrix: Calculate the mean of all samples at each time point. Two time points i and j constitute a pair of time points. Use a double loop to traverse each pair of time points (i, j) to calculate the covariance. For each pair of time points, calculate the covariance of all samples and fill the calculated covariance values ​​into the covariance matrix to obtain the covariance matrix of the postprandial blood glucose dataset. S3.3 Eigenfunction decomposition: Decompose the covariance matrix to obtain eigenvalues ​​and eigenvectors. The obtained eigenvectors represent the eigenfunctions. S3.4 Feature function selection: Sort the eigenvalues ​​according to their sizes, and select the eigenvectors corresponding to the first two largest eigenvalues ​​as feature function I and feature function II, as the top two feature functions in terms of contribution.

5. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S3.1, the smoothing parameter is selected as 0.

1.

6. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S3.2, the smoothed postprandial blood glucose data set is X, which contains n samples and m time points. The covariance matrix C is an m×m matrix, in which the element in the i-th row and j-th column represents the covariance between the i-th time point and the j-th time point. The calculation formula of the covariance is , in, refers to the blood glucose concentration value of the kth sample at the i-th time point, refers to the blood glucose concentration value of the kth sample at the jth time point, is the mean value at the ith time point, is the mean at the jth time point, and n is the number of samples.

7. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S3.4, the cumulative explained variance of the characteristic function I and the characteristic function II is greater than 80%, and it is determined that the first two characteristic functions obtained by FPCA can fully characterize the variability of the postprandial blood glucose response and reduce the dimension of the feature; The explained variance of each eigenvalue λi is calculated by the following formula: Proportion of variance explained = , Among them: λi is the i-th eigenvalue; is the sum of all eigenvalues.

8. The method for evaluating human postprandial blood glucose response based on continuous blood glucose data according to claim 1, characterized in that: In step S6, four different postprandial blood glucose response modes are constructed based on the median of the projection values ​​of the first two characteristic functions of the postprandial blood glucose data set, wherein the projection value of the single blood glucose response data on the characteristic function I and the characteristic function II is less than the median and is judged as L, and greater than or equal to the median and is judged as H: HH mode: the characteristic function I is estimated as H, and the characteristic function II is estimated as H; HL mode: the characteristic function I is estimated as H, and the characteristic function II is estimated as L; LH mode: the characteristic function I is estimated as L, and the characteristic function II is estimated as H; LL mode: The estimated value of characteristic function I is L, and the estimated value of characteristic function II is L.

9. Application of a method for evaluating a human body's postprandial blood glucose response based on continuous blood glucose data, characterized in that: It is used to judge whether the postprandial blood sugar response is good or not, among which the HL mode is judged as a good response mode; the LH mode, HH mode and LL mode are judged as poor response modes.

Images