Endocrine data analysis method and system

Abstract

The invention provides an endocrine data analysis method and system, and relates to the technical field of data analysis, and the method comprises the steps: obtaining endocrine data of a target object, preprocessing the endocrine data, and obtaining standardized endocrine data; obtaining dimension reduction data of the standardized endocrine data; according to the endocrine classification method and device, the endocrine global structure characteristics of the target object are obtained by fully utilizing the relationship between different data and the complementary information between different data according to the characteristics of different data, the misdiagnosis or missed diagnosis probability caused by a single index is reduced, and the accuracy of endocrine classification is improved. And the accuracy degree of endocrine result analysis of the target object is further improved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and specifically to an endocrine data analysis method and system. Background Art

[0002] Many endocrine disorders present subtle symptoms in their early stages or mimic those of other diseases, posing significant challenges for physicians. Existing diagnostic methods often rely on testing a single or limited number of indicators, such as blood sugar and thyroid hormones. However, the endocrine system is a complex network, with various hormones interacting to maintain human homeostasis. Therefore, abnormalities in a single indicator may not fully reflect the true extent of the disease. Furthermore, due to the diversity of endocrine disease, different diseases may present similar symptoms but possess distinct underlying pathological mechanisms. This further complicates diagnosis and can easily lead to misdiagnosis or missed diagnosis. A misdiagnosis can severely impact the timing and effectiveness of subsequent treatment. A misdiagnosis can lead to unnecessary treatment, wasting medical resources and placing additional physical and psychological burden on patients. A missed diagnosis, on the other hand, means that the disease is not treated promptly and effectively, potentially worsening.

[0003] Therefore, how to overcome the above-mentioned technical problems and defects becomes a problem that needs to be solved in a key manner. Summary of the Invention

[0004] In order to overcome the above problems existing in the prior art, the present application provides an endocrine data analysis method and system, which adopts the following technical solutions:

[0005] In a first aspect, the present application provides an endocrine data analysis method, comprising:

[0006] Acquire endocrine data of the target subject, preprocess the endocrine data, and obtain standardized endocrine data;

[0007] Obtain dimensionality-reduced data for standardized endocrine data;

[0008] Analyze the dimensionality-reduced data to obtain the endocrine classification results of the target object.

[0009] Furthermore, endocrine data of the target subject is obtained, and the endocrine data is preprocessed to obtain standardized endocrine data, including:

[0010] Obtain the mean and standard deviation of the target object's physiological signals, biochemical indicators, and imaging data, and then transform the target object's physiological signals, biochemical indicators, and imaging data into a distribution with a mean of 0 and a variance of 1.

[0011] Furthermore, the dimensionality reduction data of the standardized endocrine data is obtained, including:

[0012] Normalized endocrine data were merged into a fusion feature;

[0013] Get the covariance matrix of the fused features;

[0014] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues ​​and eigenvectors of the standardized endocrine data;

[0015] determining the number of principal components of the standardized endocrine data based on the obtained eigenvalues;

[0016] The original endocrine data are projected onto the corresponding principal components to obtain the data representation after dimensionality reduction of the standardized endocrine data.

[0017] Furthermore, the standardized endocrine data were merged into a fusion feature, including:

[0018] Each data in the standardized endocrine data is decomposed into the product of the basis matrix and the coefficient matrix through non-negative matrix decomposition;

[0019] The coefficient matrix of each data is obtained through a non-negative matrix, and the similarity graph corresponding to each data is constructed respectively. The similarity graphs constructed for each data are fused to obtain a consensus graph of standardized endocrine data;

[0020] The consensus graph is subjected to fusion feature extraction through graph signal processing to obtain the fusion features after the standardized endocrine data are merged.

[0021] Furthermore, the coefficient matrix of each data is obtained through the non-negative matrix, and the similarity graph corresponding to each data is constructed respectively. The similarity graphs constructed for each data are fused to obtain the consensus graph of standardized endocrine data, including:

[0022] By calculating the similarity between the corresponding coefficient matrices of different types of data, an undirected graph is constructed based on the similarity threshold. The nodes in the graph represent samples, and the weights of the edges represent the similarity between samples. The similarity graphs of physiological signals, biochemical indicators, and imaging data obtained are fused to obtain a consensus graph.

[0023] Furthermore, the dimensionality-reduced data is analyzed to obtain the endocrine classification results of the target object, including:

[0024] The dimensionality-reduced data is used as the input of the decision tree model to obtain the important features in the endocrine data. The important features are used as the input of the support vector machine algorithm to obtain the endocrine classification results of the target object.

[0025] Furthermore, the dimensionality-reduced data is used as input to the decision tree model to obtain important features of the endocrine data, including:

[0026] Preset the number of decision trees and other related hyperparameters in the random forest; perform self-service sampling on the dimensionality reduction data obtained by the decision tree model to obtain multiple sample subsets;

[0027] Build a decision tree for each sample subset; based on each decision tree, obtain the importance score of each feature;

[0028] According to the calculated feature importance scores, all features are sorted from high to low, and features with importance scores higher than the preset threshold are regarded as important features.

[0029] In a second aspect, the present application further provides an endocrine data analysis system, comprising:

[0030] Acquire endocrine data of the target subject, preprocess the endocrine data, and obtain standardized endocrine data;

[0031] A dimensionality reduction data acquisition module, used to obtain dimensionality reduction data of standardized endocrine data;

[0032] The dimensionality reduction data analysis module is used to analyze the dimensionality reduction data and obtain the endocrine classification results of the target object.

[0033] In a third aspect, the present application provides an electronic device, comprising:

[0034] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the method as described in the first aspect.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0036] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0037] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged with the processor, or may be stored in whole or in part on a memory not packaged with the processor.

[0038] This application has the following beneficial effects:

[0039] This application obtains the endocrine data of the target object, pre-processes the endocrine data, and obtains standardized endocrine data; obtains dimensionality-reduced data of the standardized endocrine data; and analyzes the dimensionality-reduced data to obtain the endocrine classification results of the target object. This application obtains the global structural characteristics of the target object based on the characteristics of different data, fully utilizes the relationship between different data and the complementary information between different data, reduces the probability of misdiagnosis or missed diagnosis due to a single indicator, and further improves the accuracy of the endocrine result analysis of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0041] Figure 2 This is a flow chart of the endocrine data analysis method according to an embodiment of the present application;

[0042] Figure 3 This is a flowchart of dimensionality reduction data acquisition in an embodiment of the present application;

[0043] Figure 4 This is a flowchart of the fusion feature acquisition of an embodiment of the present application;

[0044] Figure 5 This is a system flow chart of an embodiment of the present application;

[0045] Figure 6 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0047] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[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 accompanying drawings.

[0049] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0050] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0051] Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers, desktop computers, etc.

[0052] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0053] It should be noted that the endocrine data analysis method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the endocrine data analysis system is generally set in the server / terminal device.

[0054] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0055] Continue to refer Figure 2 , the figure shows a flow chart of an endocrine data analysis method of the present application, the method comprising the following steps:

[0056] Step 201 : Acquire endocrine data of a target subject, pre-process the endocrine data, and acquire standardized endocrine data.

[0057] It should be noted that the target object refers to an endocrine patient, and this application uniformly represents endocrine patients as target objects. The endocrine data in this application are multi-index data from different sources, and the endocrine data in this application include the physiological signals, biochemical indicators, and imaging data of the target object. The physiological signals of the target object in this application refer to the data of the physiological activities of the target object obtained through various physiological monitoring equipment. Biochemical indicator data are the analysis results of the target object's blood, urine, etc. through laboratory tests. Imaging data are image information obtained from the target object's organs or tissues through medical imaging technology. The acquired physiological signals can be a sequence of blood glucose values ​​obtained by the target object through a blood glucose meter, as well as a continuous monitoring signal of a heart rhythm signal, or dynamic blood pressure data obtained by an ambulatory blood pressure monitor, etc. The biochemical indicator data can be various specific numerical values ​​of the target object and thyroid function monitoring, or various test data such as blood glucose, blood lipids, liver function indicators, and kidney function indicators.

[0058] This application can solve the problem of incomplete analysis of the target subject's endocrine condition due to a single indicator by obtaining the target subject's physiological signals, biochemical indicators, and imaging data, thereby reducing the probability of misdiagnosis or missed diagnosis.

[0059] In one possible implementation, endocrine data for a target subject is obtained through a hospital information system, a laboratory information management system, and an electronic medical record system. The hospital information system contains basic information about the target subject, such as age, gender, and family medical history; the laboratory information management system contains various endocrine-related test data; and the electronic medical record system contains detailed information such as the patient's symptom description, medical history, diagnosis results, and treatment records.

[0060] In a possible implementation, the physiological signals, biochemical indicators, and imaging data of the target object are standardized to obtain standardized data.

[0061] In one possible implementation, normalizing the physiological signals, biochemical indicators, and imaging data of the target subject to obtain the standardized data includes:

[0062] First, the mean and standard deviation of the target object's physiological signals, biochemical indicators, and imaging data are obtained, and then the target object's physiological signals, biochemical indicators, and imaging data are converted into a distribution with a mean of 0 and a variance of 1. This application can unify data of different scales into the same dimension by first obtaining the mean and standard deviation of the physiological signals, biochemical indicators, and imaging data. The target object's physiological signals, biochemical indicators, and imaging data are converted into a distribution with a mean of 0 and a variance of 1, where the part with a mean of 0 represents the center position of the data, and the variance of 1 represents the degree of discreteness of the data.

[0063] The target object's physiological signals, biochemical indicators, and imaging data are converted into a distribution with a mean of 0 and a variance of 1 using the following formula: Where x1 is the standardized data, x is the original data, μ is the mean, and σ is the standard deviation.

[0064] Step 202: Obtain dimension-reduced data of the standardized endocrine data.

[0065] In one possible implementation, to obtain the dimension-reduced data of the standardized endocrine data, please refer to Figure 3 , specifically including:

[0066] In step 31, the normalized endocrine data are merged into a fusion feature.

[0067] It should be noted that when merging the standardized endocrine data into a fusion feature, there may be potential dependencies between the standardized physiological signals, biochemical indicators, and imaging data. By merging the standardized physiological signals, biochemical indicators, and imaging data into one data set and subsequently performing dimensionality reduction on the physiological signals, biochemical indicators, and imaging data, the potential dependencies among the physiological signals, biochemical indicators, and imaging data can be captured. Dimensionality reduction of the merged data set can obtain global data structure characteristics, while facilitating unified data processing and reducing processing complexity.

[0068] It should be noted that this application can retain the characteristics of different data and make full use of the relationship between different data by fusing the standardized physiological signals, biochemical indicators, and imaging data before data dimensionality reduction.

[0069] In one possible implementation, the normalized endocrine data are combined into a fusion feature, see Figure 4 , specifically including:

[0070] In step 41, each type of standardized endocrine data is subjected to non-negative matrix factorization (NMF), which is the product of a basis matrix and a coefficient matrix. The coefficient matrix reflects the relationship between different types of data. For example, for the nth type of data, NMF is performed, V ≈ WH, where W is the basis matrix and H is the coefficient matrix.

[0071] Step 42: Obtain a coefficient matrix for each data type through a non-negative matrix, construct a similarity graph corresponding to each data type, fuse the similarity graphs constructed for each data type, and obtain a consensus graph for the standardized endocrine data.

[0072] It should be noted that in the embodiment of the present application, by calculating the similarity between the coefficient matrices corresponding to different types of data, an undirected graph is constructed based on the similarity threshold. The nodes in the graph represent samples, and the weights of the edges represent the similarity between the samples. The similarity graphs of physiological signals, biochemical indicators, and imaging data obtained are fused to obtain a consensus graph. In the fusion process, a weighted fusion method can be used to obtain a consensus graph, and the weight coefficient of each data is determined based on the importance. Assuming that H1, H2, and H3 are similarity graphs of physiological signals, biochemical indicators, and imaging data, respectively, the consensus graph G is: G = αH1 + βH2 + γH3, where α + β + γ = 1, and α, β, and γ are the weight coefficients corresponding to the similarity graphs of physiological signals, biochemical indicators, and imaging data, respectively. In the embodiment of the present application, the similarity between the coefficient matrices corresponding to different types of data is calculated using cosine similarity or Euclidean distance as a similarity metric.

[0073] Step 43: extract fusion features from the consensus graph through graph signal processing to obtain fusion features after merging the standardized endocrine data.

[0074] It should be noted that the consensus graph is subjected to fusion feature extraction through graph signal processing to obtain the fusion features after the standardized endocrine data is merged, including:

[0075] Obtain the Laplace matrix of the consensus map, perform eigendecomposition on the Laplace matrix, obtain eigenvectors and eigenvalues, and use the eigenvectors corresponding to the maximum eigenvalues ​​of a preset number as fusion information. The fusion features obtained in this application reflect the global structural characteristics of the consensus map by fusing physiological signals, biochemical indicators, and imaging data. By fusing standardized physiological signals, biochemical indicators, and imaging data into one feature, this application can fully utilize the complementary information of each data.

[0076] Step 32, obtaining the covariance matrix of the fused features; the present application obtains the covariance matrix of the fused features in order to obtain the main components in the data and the importance of the main components.

[0077] It should be noted that after the physiological signals, biochemical indicators, and imaging data are fused, a fusion matrix X containing multiple samples is obtained, where each row of the fusion matrix represents a sample and each column represents the feature dimension after fusion.

[0078] It should be further explained that obtaining the covariance matrix of the fused feature includes: obtaining the mean vector of each feature in the fused feature, where the dimension of the mean vector is the same as the feature dimension. The i-th element is the average value u of all sample values ​​in the i-th column of the fused feature matrix X i ,Right now Where n is the number of samples, x ij is the i-th eigenvalue of the j-th sample.

[0079] Then the element C of the covariance matrix C ij It can be expressed as where x ki with x kj are the i-th and j-th eigenvalues ​​of the k-th sample, u i and u j are the means of the i-th and j-th features respectively. By calculating all i and j through the formula, we can get the complete covariance matrix C.

[0080] Step 33: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors of the standardized endocrine data.

[0081] It should be noted that the eigenvalue decomposition of the covariance matrix is ​​to find a set of special eigenvectors and eigenvalues. When the covariance matrix C is on these eigenvectors, it only stretches or compresses the eigenvectors without changing other directions. i =λ i v i , where λ i is the eigenvalue, v i is the eigenvector. Solve the characteristic polynomial det(C-λI)=0 and get the eigenvalue λ i and the eigenvector v i . Set the eigenvalue λ i Arrange them in descending order and put the corresponding eigenvector v i Also arranged in the same order. Where I is the identity matrix. The sorted eigenvector v i As a column vector, construct the eigenvector matrix V: V=[v1,v2,...v n ].

[0082] This application obtains the covariance matrix of the fused features in order to describe the correlation and discreteness between the fused features, and performs eigenvalue decomposition on the covariance matrix in order to further reveal the intrinsic structure and variation patterns of the endocrine data.

[0083] In the embodiment of the present application, eigenvalue decomposition is performed on the covariance matrix to obtain the eigenvalues ​​and eigenvectors of the standardized endocrine data, including:

[0084] Step 34: Determine the number of principal components of the standardized endocrine data based on the acquired eigenvalues. It should be noted that the eigenvectors corresponding to the first k largest eigenvalues ​​are selected to construct the eigenvector matrix V after dimensionality reduction. k , the eigenvector matrix V k as the principal components of the original endocrine data.

[0085] Step 35, project the original endocrine data onto the corresponding principal component to obtain the data representation of the standardized endocrine data after dimensionality reduction. It should be noted that the eigenvector matrix V after dimensionality reduction is used. k The standardized endocrine data is projected to obtain a data representation of the standardized endocrine data after dimensionality reduction. By selecting the eigenvectors corresponding to the first k largest eigenvalues, this application ensures that the data after dimensionality reduction retains the maximum variance, that is, retains the most important information in the endocrine data, achieving effective data dimensionality reduction. The data after dimensionality reduction in this application reduces redundancy and noise.

[0086] Step 203: Analyze the dimension-reduced data to obtain the endocrine classification result of the target object.

[0087] The dimensionality-reduced data is used as the input of the decision tree model to obtain the important features in the endocrine data. The important features are used as the input of the support vector machine algorithm to obtain the endocrine classification results of the target object.

[0088] In one possible implementation, the dimensionality-reduced data is used as input to a decision tree model to obtain important features of the endocrine data, including:

[0089] Preset the number of decision trees and other related hyperparameters in the random forest. Perform bootstrapping on the dimension-reduced data obtained from the decision tree model to obtain multiple sample subsets.

[0090] A decision tree is constructed for each sample subset. During the construction process, feature subsets are selected according to the principle of feature randomness, and nodes are split according to the corresponding splitting criteria (Gini impurity or mean square error) until the stopping condition is met (such as reaching the maximum depth or the number of samples is less than a certain threshold).

[0091] For each decision tree, record the reduction in impurity or mean square error caused by each feature when the node is split, accumulate the impurity or mean square error reduction of each feature in all decision trees, and average the accumulated results in all decision trees to obtain the importance score of each feature.

[0092] According to the calculated feature importance scores, all features are sorted from high to low, and features with importance scores higher than the preset threshold are regarded as important features.

[0093] It should be noted that this application uses a decision tree model to screen important features of the data after dimensionality reduction. By selecting important features, the number of features can be reduced and the data processing efficiency can be further improved.

[0094] In one possible implementation, the important features are used as input to a support vector machine algorithm to obtain an endocrine classification result for a target subject, including:

[0095] The acquired important features are used as the input of the support vector machine algorithm, and the support vector machine algorithm outputs the endocrine classification results of the target object according to the decision rule of the optimal hyperplane, thereby completing the classification task of the target object.

[0096] It should be noted that the present application uses a support vector machine algorithm to find the hyperplane with the largest interval by solving an optimization problem for linearly separable important feature data. For nonlinear important feature data, a kernel function is used to map the data to a high-dimensional space so that it is linearly separable in the high-dimensional space, and then the optimal hyperplane is found in the high-dimensional space. The present application can improve the accuracy of the endocrine classification results of the target object by first extracting important features from the dimensionality-reduced data through a decision tree model and then classifying based on the important features through a support vector machine algorithm.

[0097] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0098] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0099] Continue to refer Figure 5 The endocrine data analysis system described in this embodiment includes:

[0100] Acquiring endocrine data of a target subject 501 and preprocessing the endocrine data to obtain standardized endocrine data;

[0101] A dimension reduction data acquisition module 502 is used to acquire dimension reduction data of standardized endocrine data;

[0102] The dimension reduction data analysis module 503 is used to analyze the dimension reduction data to obtain the endocrine classification result of the target object.

[0103] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0104] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 6a-6c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0105] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0106] The memory 6a includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, etc. In some embodiments, the memory 6a may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 6a may also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Of course, the memory 6a may also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 6a is generally used to store the operating system and various application software installed on the computer device 6, such as the program code of the endocrine data analysis method. In addition, the memory 6a can also be used to temporarily store various types of data that have been output or are to be output.

[0107] In some embodiments, the processor 6b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to execute program code stored in the memory 6a or process data, such as executing the program code of the endocrine data analysis method.

[0108] The network interface 6c may include a wireless network interface or a wired network interface. The network interface 6c is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0109] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, which stores a program of an endocrine data analysis method, and the endocrine data analysis can be executed by at least one processor so that the at least one processor performs the steps of the endocrine data analysis method as described above.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0111] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A method for analyzing endocrine data, characterized in that: include: Acquire endocrine data of the target subject, preprocess the endocrine data, and obtain standardized endocrine data; Obtain dimensionality-reduced data for standardized endocrine data; Analyze the dimensionality-reduced data to obtain the endocrine classification results of the target object.

2. The endocrine data analysis method according to claim 1, characterized in that: Obtain the endocrine data of the target subject, pre-process the endocrine data, and obtain standardized endocrine data, including: Obtain the mean and standard deviation of the target object's physiological signals, biochemical indicators, and imaging data, and then transform the target object's physiological signals, biochemical indicators, and imaging data into a distribution with a mean of 0 and a variance of 1.

3. The endocrine data analysis method according to claim 1, characterized in that: Obtain dimensionality reduction data for standardized endocrine data, including: Normalized endocrine data were merged into a fusion feature; Get the covariance matrix of the fused features; Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues ​​and eigenvectors of the standardized endocrine data; determining the number of principal components of the standardized endocrine data based on the obtained eigenvalues; The original endocrine data are projected onto the corresponding principal components to obtain the data representation after dimensionality reduction of the standardized endocrine data.

4. The endocrine data analysis method according to claim 3, characterized in that: Merge normalized endocrine data into a fusion feature including: Each data in the standardized endocrine data is decomposed into the product of the basis matrix and the coefficient matrix through non-negative matrix decomposition; The coefficient matrix of each data is obtained through a non-negative matrix, and the similarity graph corresponding to each data is constructed respectively. The similarity graphs constructed for each data are fused to obtain a consensus graph of standardized endocrine data; The consensus graph is subjected to fusion feature extraction through graph signal processing to obtain the fusion features after the standardized endocrine data are merged.

5. The endocrine data analysis method according to claim 4, characterized in that: The coefficient matrix of each data is obtained through the non-negative matrix, and the similarity graph corresponding to each data is constructed respectively. The similarity graphs constructed for each data are fused to obtain the consensus graph of standardized endocrine data, including: By calculating the similarity between the corresponding coefficient matrices of different types of data, an undirected graph is constructed based on the similarity threshold. The nodes in the graph represent samples, and the weights of the edges represent the similarity between samples. The similarity graphs of physiological signals, biochemical indicators, and imaging data obtained are fused to obtain a consensus graph.

6. The endocrine data analysis method according to claim 1, characterized in that: Analyze the dimensionality reduction data to obtain the endocrine classification results of the target object, including: The dimensionality-reduced data is used as the input of the decision tree model to obtain the important features in the endocrine data. The important features are used as the input of the support vector machine algorithm to obtain the endocrine classification results of the target object.

7. The endocrine data analysis method according to claim 6, characterized in that: The dimensionality-reduced data is used as input to the decision tree model to obtain important features of the endocrine data, including: Preset the number of decision trees and other related hyperparameters in the random forest; perform self-service sampling on the dimensionality reduction data obtained by the decision tree model to obtain multiple sample subsets; Build a decision tree for each sample subset; based on each decision tree, obtain the importance score of each feature; According to the calculated feature importance scores, all features are sorted from high to low, and features with importance scores higher than the preset threshold are regarded as important features.

8. An endocrine data analysis system for implementing the endocrine data analysis method of claims 1-7, characterized in that: include: Acquire endocrine data of the target subject, preprocess the endocrine data, and obtain standardized endocrine data; A dimensionality reduction data acquisition module, used to obtain dimensionality reduction data of standardized endocrine data; The dimensionality reduction data analysis module is used to analyze the dimensionality reduction data and obtain the endocrine classification results of the target object.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images