Chronic disease co-disease mode recognition method and device based on fusion graph convolution constraint enhanced low-rank representation, electronic equipment and storage medium

Abstract

The invention discloses a fusion graph convolution constraint enhanced low-rank representation chronic disease co-disease mode identification method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining medical data resources, constructing a chronic disease co-disease network through the medical data resources, and enabling the chronic disease co-disease network to be used for describing the correlation and influence between diseases, the low-rank representation method of fusion graph convolution constraint is used for performing representation learning on the chronic disease co-disease network so as to excavate and output a community structure therein, a community division mechanism is used for identifying the community structure in the co-disease network, a co-disease mode is explored, the good interpretable clustering characteristic of a low-rank decomposition model is achieved, and the community structure in the co-disease network is identified. Meanwhile, the nonlinear and non-Euclidean representation learning ability of the GCN is integrated, and the representation learning ability is improved.

Description

Technical Field

[0001] The present invention mainly relates to the field of pattern recognition, and in particular to a chronic disease comorbidity pattern recognition method, device, electronic device and storage medium that integrates graph convolution constraints to enhance low-rank representation. Background Art

[0002] Chronic non-communicable diseases (referred to as "chronic diseases") have become a major threat to global public health and human health, bringing heavy economic burdens to patients and society. Due to the characteristics of complex etiology, hidden onset, long course of disease and prolonged illness, some patients often suffer from multiple chronic diseases at the same time. The World Health Organization calls this phenomenon "comorbidity". Under the trend of global population aging, the problem of chronic disease comorbidity has gradually become prominent and has become a major challenge in the field of global health. The complex impact of diseases poses a great challenge to disease diagnosis and treatment. Understanding the specific factors and processes of comorbidity, the interaction of diseases and possible synergies is very important for promoting diagnosis, improving the quality of life of patients, improving prevention and reducing the cost of the health care system. Therefore, the use of new technologies such as artificial intelligence and big data to explore the complex comorbidity patterns between chronic diseases provides important decision-making basis for predicting disease risks, disease prevention, treatment and management, which has practical significance for the sustainable development of human health.

[0003] Diseases do not cluster randomly, and comorbidity patterns reveal statistically significant associations and pathophysiological relationships between diseases. Mining comorbidity patterns and exploring their distribution patterns will help classify diseases, reduce the complexity of chronic disease prevention and treatment, and make preventive measures more accurate and efficient. A systematic review of multi-disease epidemiological studies showed that different studies found different properties and patterns of comorbidity. At present, there is no unified definition of methods for identifying comorbidity patterns. Based on different data analysis principles and technical means, common methods can be summarized into the following four categories:

[0004] (1) Odds ratio: It is used to measure the probability of something happening versus not happening. It is often used to analyze the relative risk of two diseases in comorbidity pattern analysis. A study in the Netherlands showed that the relative risk of depression and anxiety, coronary heart disease and heart failure, and chronic obstructive pulmonary disease and heart failure were the highest. The odds ratio algorithm is simple and easy to use and has become one of the commonly used methods in comorbidity pattern research.

[0005] (2) Factor analysis: aims to identify the complex relationships between multiple diseases, combine multiple related factors into a few comprehensive indicators, simplify the data structure and reveal the association between variables. A study of Japanese adults identified five groups of comorbidity patterns for 17 chronic diseases through factor analysis. Factor analysis does not rely on traditional grouping assumptions. It can more effectively reveal the relationship between variables by reducing the dimension and simplifying the data to extract important information.

[0006] (3) Cluster analysis: A data mining technique used to identify data clusters. Common methods include hierarchical clustering and K-means clustering. The comorbidity patterns of COPD patients may include comorbidities with cardiovascular disease, allergic diseases, and other representative diseases. Cluster analysis can explore the commonalities of potential factors in these comorbidity patterns and help understand the comorbidity phenomenon of chronic diseases.

[0007] (4) Association rules: used to analyze the direct associations between multiple chronic diseases and reveal the strong associations of comorbidity patterns. A British study evaluated the comorbidity patterns of middle-aged and elderly people through cluster analysis and association rule mining, and found three clusters and 30 disease patterns, revealing the complex relationships and central roles between different diseases, such as diabetes, hypertension, and asthma. There are complex interactions and associations between these chronic diseases, which require comprehensive evaluation and treatment to achieve better health outcomes.

[0008] Due to the complex interactions and influences between diseases, traditional methods are difficult to explore the deep relationships and complex connections between diseases, and it is difficult to obtain accurate comorbidity patterns. With the development of complex science, complex network analysis describes complex relationships from a holistic and systematic perspective, which is conducive to comprehensively revealing the complex influence patterns between diseases from a holistic perspective and has become a mainstream tool for exploring chronic disease comorbidity patterns. Community detection algorithms can discover closely connected clusters in the network, which can be used to identify disease comorbidity patterns.

[0009] The present invention designs a low-rank representation modeling method that integrates graph convolution constraints to extract nonlinear features in the target comorbidity network, while incorporating graph convolution regularization and graph Laplacian regularization methods to maintain global and local structural features, thereby improving the model representation learning ability to obtain higher community detection accuracy and comorbidity pattern recognition accuracy. Summary of the invention

[0010] Based on this, it is necessary to provide a chronic disease comorbidity pattern recognition method, device, electronic device and storage medium that integrates graph convolution constraints to enhance low-rank representation to address existing problems.

[0011] In a first aspect, an embodiment of the present application provides a method for recognizing chronic disease comorbidity patterns by integrating graph convolution constraints to enhance low-rank representation, characterized in that it includes:

[0012] Acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources;

[0013] A chronic disease comorbidity network is constructed using medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients based on multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data, wherein the chronic disease comorbidity network is represented by a graph G = (V, E), V = {v i |i∈{1,...,n}} represents a set of n disease nodes, E={e ij |i, j∈{1,...,m}} represents a set of m edges; the adjacency matrix A = [a ij ] is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j );

[0014] Performing low-rank representation learning and mining on the chronic disease comorbidity network to output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to characterize the comorbidity network;

[0015] Use the community partitioning mechanism to identify the community structure in the comorbidity network and discover the comorbidity pattern.

[0016] Preferably, the method for constructing the chronic disease comorbidity network includes:

[0017] Sort out chronic disease records, and sort out data records from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data;

[0018] Count the frequency of disease occurrence, and calculate the frequency Q(s) of each disease occurrence from the data records. i ) and the frequency of disease combinations occurring together Q(s i ,s j ), among which a disease i If it appears in a disease record, it is counted once. i and j If they co-occur in one disease record, they are counted once, where i, j = 1, 2, ..., n represents the number of diseases of interest;

[0019] Calculate the mutual information value between two diseases as follows:

[0020]

[0021] Among them, p(s i )=Q(si ) / F,p(s j )=Q(s j ) / F respectively calculate disease s i and j The observation frequency, where F represents the total observation frequency, p(s i ,s j )=Q(s i ,s j ) / F calculates the number of diseases observed at the same time i and j frequency;

[0022] Constructing a comorbidity network to describe the complex impact relationships of chronic diseases.

[0023] Preferably, the low-rank characterization method using fused graph convolution constraints to characterize the comorbidity network includes:

[0024] Design the objective function, which is as follows:

[0025]

[0026]

[0027] U, H, W( 1) , W(2)≥0

[0028] Where A is the adjacency matrix of the comorbidity network, U is a feature matrix of size n×K, and n and K are the number of nodes and communities in the comorbidity network, respectively; is the F-norm of the calculation matrix; Tr(·) is the trace of the calculation matrix; U T represents the transpose of the matrix U; L = DA is the Laplace matrix of A, where D = ∑ l A il is the degree matrix of A, where A il is the element value at the corresponding subscript in A; represents the hidden layer feature matrix of the GCN module, where h i Corresponding to node v i The feature vector of , d represents the feature dimension; and Represents the weight matrix of the GCN module; is the normalized adjacency matrix, where To add a self-connected adjacency matrix, for The degree matrix of for The element value at the corresponding subscript in ; λ1 is the graph regularization coefficient; σ(·) is the nonlinear activation function of the GCN module;

[0029] Convert the graph convolution constraints into the following regularized form:

[0030]

[0031] stU,H,W( 1) , W(2)≥0

[0032] Solve the following optimization problem and obtain the parameter matrices U, H, and W (1) and W (2) :

[0033] (U, H, W (1) , W (2) )←argminJ GCGS , stU, H, W (1) , W (2) ≥0

[0034] Combining the Lagrangian function method and the KKT conditions of inequality constraints, the learning rules for the optimization problem are derived:

[0035]

[0036]

[0037]

[0038]

[0039] Among them, λ1 is the graph regularization coefficient, λ2 is the graph convolution regularization coefficient, g1 and g1′ (derivative of g1) represent and g2 and g2′ (derivative of g2), respectively represent and σ′(·) is the derivative of σ(·); β is the linear adjustment coefficient of the learning scale factor of the control feature factor matrix U, which takes values ​​in the interval (0, 1); ⊙ represents the Hadamard product of the matrix; according to the learning rule, the feature and weight matrices U, H, W are iteratively updated respectively. (1) and W (2) , until the convergence condition is reached, and the final feature matrix U, H and weight W are obtained (1) , W (2) As a solution to the optimization problem, a feature matrix U is output as an indicator matrix for community division.

[0040] Preferably, the method of using a community partitioning mechanism to identify the community structure in the comorbidity network to discover the comorbidity pattern includes:

[0041] After training to obtain the characteristic parameters U and H, U is used as the indicator matrix for node-disease comorbidity module affiliation division, and the nodes in the comorbidity network are judged one by one and assigned to the comorbidity module. The assignment rules are as follows:

[0042]

[0043] Where V represents the node set in the comorbidity network, v i represents any node; C s is the comorbidity combination s, s∈{1, 2, ..., K}, K is the total number of comorbidity combinations; u ik is an element in the low-rank matrix U, representing node v i The probability of being classified into the comorbidity combination k; if u is is the maximum value among them, then node v i The probability of being classified into the comorbidity combination s is the highest. After the comorbidity combinations of all nodes in the target comorbidity network are divided, all possible comorbidity combinations identified can be obtained. C = {C1, C2, ..., C K}.

[0044] In a second aspect, an embodiment of the present application provides a chronic disease comorbidity pattern recognition device based on relaxed constrained symmetric low-rank representation, characterized in that it includes:

[0045] An acquisition unit, used to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from inspections, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources;

[0046] A construction unit is used to construct a chronic disease comorbidity network using medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients according to multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data, wherein the chronic disease comorbidity network is represented by a graph G = (V, E), V = {v i |i∈{1,...,n}} represents a set of n disease nodes, E={e ij |i, j∈{1,...,m}} represents a set of m edges; the adjacency matrix A = [a ij ] is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j );

[0047] A representation unit, used for performing low-rank representation learning on the chronic disease comorbidity network to mine and output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to characterize the comorbidity network;

[0048] The partitioning unit is used to identify the community structure in the comorbidity network and discover the comorbidity pattern using the community partitioning mechanism.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, characterized in that it includes:

[0050] processor:

[0051] a memory for storing instructions executable by the processor;

[0052] The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the above method steps.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program is used to execute the above method.

[0054] Compared with the prior art, the present invention has the following advantages: (1) Compared with the existing non-negative matrix decomposition algorithm, the present invention not only has the good interpretable clustering characteristics of the low-rank decomposition model, but also incorporates the nonlinear and non-Euclidean representation learning ability of GCN, thereby improving its representation learning ability; (2) The GCN module can learn the global structural characteristics of the network, and the introduction of graph regularization technology effectively maintains the inherent geometric structure characteristics of the network. Therefore, the technical solution of the present invention can theoretically obtain better global nonlinear and local feature representation capabilities; (3) The NMU-based optimization scheme is used to realize the parameter solution of the designed model under non-negative constraints, thereby ensuring the interpretability of the model for the numerical non-negative characteristics of the comorbidity network. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] By referring to the following drawings, the exemplary embodiments of the present invention can be more completely understood. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings, the same reference numerals generally represent the same parts or steps.

[0056] Figure 1 A flowchart of a method for recognizing chronic disease comorbidity patterns by integrating graph convolution constraints to enhance low-rank representation according to an exemplary embodiment of the present application;

[0057] Figure 2A schematic diagram of a chronic disease comorbidity pattern recognition device that integrates graph convolution constraints to enhance low-rank representation according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0058] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0059] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0060] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0062] An embodiment of the present application provides a method for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation, which is described below in conjunction with the accompanying drawings.

[0063] Reference Figure 1 , which shows a chronic disease comorbidity pattern recognition method based on relaxed constrained symmetric low-rank representation provided by some embodiments of the present application, such as Figure 1 As shown, the method may include the following:

[0064] S101: Acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources;

[0065] S102: constructing a chronic disease comorbidity network using the medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients based on multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data;

[0066] Specifically, the chronic disease comorbidity network is represented by a graph G = (V, E), V = {v i |i∈{1,...,n}} represents a set of n disease nodes, E={e ij |i, j∈{1,...,m}} represents a set of m edges; the adjacency matrix A = [a ij ] is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j );

[0067] S103: Perform low-rank representation learning on the chronic disease comorbidity network to mine and output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to characterize the comorbidity network;

[0068] S104: Use community partitioning mechanism to identify community structure in comorbidity network and discover comorbidity patterns.

[0069] Specifically, the method for constructing a chronic disease comorbidity network includes the following steps:

[0070] (1) Sort out chronic disease records and extract data records from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data;

[0071] (2) Count the frequency of disease occurrence, and calculate the frequency Q (s) of each disease occurrence from the data records. i ) and the frequency of disease combinations occurring together Q(s i ,s j ), among which a disease i If it appears in a disease record, it is counted once. i and j If they co-occur in one disease record, they are counted once, where i, j = 1, 2, ..., n represents the number of diseases of interest;

[0072] Calculate the mutual information value between two diseases as follows:

[0073]

[0074] Among them, p(s i )=Q(s i ) / F,p(s j )=Q(s j ) / F respectively calculate disease s i and j The observation frequency, where F represents the total observation frequency, p(s i ,s j )=Q(s i ,s j ) / F calculates the number of diseases observed at the same time i and j frequency;

[0075] (3) Construct a comorbidity network to describe the complex impact relationships of chronic diseases.

[0076] Specifically, the low-rank representation method fused with graph convolution constraints to characterize the comorbidity network includes the following steps:

[0077] (1) Design the objective function, which is as follows:

[0078]

[0079]

[0080] U, H, W( 1) , W(2)≥0

[0081] Where A is the adjacency matrix of the comorbidity network, U is a feature matrix of size n×K, and n and K are the number of nodes and communities in the comorbidity network, respectively; is the F-norm of the calculation matrix; Tr(·) is the trace of the calculation matrix; U T represents the transpose of the matrix U; L = DA is the Laplace matrix of A, where D = ∑ l A il is the degree matrix of A, where A il is the element value at the corresponding subscript in A; represents the hidden layer feature matrix of the GCN module, where h i Corresponding to node v i The feature vector of , d represents the feature dimension; and Represents the weight matrix of the GCN module; is the normalized adjacency matrix, where To add a self-connected adjacency matrix, for The degree matrix of for The element value at the corresponding subscript in ; λ1 is the graph regularization coefficient; σ(·) is the nonlinear activation function of the GCN module;

[0082] (2) Convert the graph convolution constraint into the following regularized form:

[0083]

[0084] stU,H,W( 1) , W(2)≥0

[0085] Solve the following optimization problem and obtain the parameter matrices U, H, and W (1) and W (2) :

[0086] (U, H, W (1) , W (2) )←argminJ GCGS , stU, H, W (1) , W (2) ≥0

[0087] (3) Combining the Lagrangian function method and the KKT condition of inequality constraints, the learning rule of the optimization problem is derived:

[0088]

[0089]

[0090]

[0091]

[0092] Among them, λ1 is the graph regularization coefficient, λ2 is the graph convolution regularization coefficient, g1 and g1′ (derivative of g1) represent and g2 and g2′ (derivative of g2), respectively represent and σ′(·) is the derivative of σ(·); β is the linear adjustment coefficient of the learning scale factor of the control feature factor matrix U, which takes values ​​in the interval (0, 1); ⊙ represents the Hadamard product of the matrix; according to the learning rule, the feature and weight matrices U, H, W are iteratively updated respectively. (1) and W (2) , until the convergence condition is reached, and the final feature matrix U, H and weight W are obtained (1) , W (2) As a solution to the optimization problem, a feature matrix U is output as an indicator matrix for community division.

[0093] Specifically, the community partitioning mechanism is used to identify the community structure in the comorbidity network to discover the comorbidity pattern, including:

[0094] After training to obtain the characteristic parameters U and H, U is used as the indicator matrix for node-disease comorbidity module affiliation division, and the nodes in the comorbidity network are judged one by one and assigned to the comorbidity module. The assignment rules are as follows:

[0095]

[0096] Where V represents the node set in the comorbidity network, v i represents any node; C s is the comorbidity combination s, s∈{1,2,…,K}, K is the total number of comorbidity combinations; u ik is an element in the low-rank matrix U, representing node v i The probability of being classified into the comorbidity combination k; if u is is the maximum value among them, then node v i The probability of being classified into the comorbidity combination s is the highest. After the comorbidity combinations of all nodes in the target comorbidity network are divided, all possible comorbidity combinations identified can be obtained. C = {C1, C2, …, C K}.

[0097] Compared with the prior art, the present invention has the following advantages: (1) Compared with the existing non-negative matrix decomposition algorithm, the present invention not only has the good interpretable clustering characteristics of the low-rank decomposition model, but also incorporates the nonlinear and non-Euclidean representation learning ability of GCN, thereby improving its representation learning ability. (2) The GCN module can learn the global structural characteristics of the network, and the introduction of graph regularization technology effectively maintains the inherent geometric structure characteristics of the network. Therefore, the technical solution of the present invention can theoretically obtain better global nonlinear and local feature representation capabilities. (3) The NMU-based optimization scheme is used to realize the parameter solution of the designed model under non-negative constraints, ensuring the model's interpretability of the numerical non-negative characteristics of the comorbidity network.

[0098] In the above embodiment, a method is provided, and correspondingly, the present application also provides a device. The device provided in the embodiment of the present application can implement the above method, and the device can be implemented by software, hardware, or a combination of software and hardware. For example, the device may include integrated or separate functional modules or units to perform the corresponding steps in the above methods.

[0099] In some implementation modes of the embodiments of the present application, the device provided by the embodiments of the present application is based on the same inventive concept as the method provided by the aforementioned embodiments of the present application and has the same beneficial effects.

[0100] like Figure 2 As shown, the device 20 may include:

[0101] An acquisition unit 201 is used to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from inspections, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources;

[0102] A construction unit 202 is used to construct a chronic disease comorbidity network using medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients based on multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data;

[0103] The chronic disease comorbidity network is represented by graph G = (V, E), V = {v i |i∈{1,…,n}} represents a set of n disease nodes, E={e ij |i,j∈{1,…,m}} represents a set of m edges; the adjacency matrix A=[a ij} is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j );

[0104] A representation unit is used to perform low-rank representation learning on the chronic disease comorbidity network and mine and output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to represent the comorbidity network;

[0105] The partitioning unit is used to identify the community structure in the comorbidity network and discover the comorbidity pattern using the community partitioning mechanism.

[0106] An embodiment of the present application also provides an electronic device corresponding to the method provided in the aforementioned embodiment. The device may be an electronic device used on the server side, such as a server, including an independent server and a distributed server cluster, etc., to execute the above method; the electronic device may also be an electronic device used on the client side to execute the above method.

[0107] The electronic device includes: a processor, a memory, a bus and a communication interface, wherein the processor, the communication interface and the memory are connected via a bus; the memory stores a computer program that can be run on the processor, and the processor executes the aforementioned method of the present application when running the computer program.

[0108] The memory may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0109] The bus may be an ISA bus, a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store a program, and the processor executes the program after receiving an execution instruction. The method disclosed in any implementation of the above-mentioned embodiment of the present application may be applied to the processor or implemented by the processor.

[0110] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The electronic device provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented.

[0111] The embodiments of the present application also provide a computer-readable medium corresponding to the method provided in the aforementioned embodiments, on which a computer program (ie, a program product) is stored. When the computer program is executed by a processor, the aforementioned method is executed.

[0112] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0113] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0118] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A method for recognizing chronic disease comorbidity patterns by integrating graph convolution constraints to enhance low-rank representation, characterized in that: include: Acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources; A chronic disease comorbidity network is constructed using medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients based on multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data, wherein the chronic disease comorbidity network is represented by a graph G = (V, E), V = {v i |i∈{1,…,n}} represents a set of n disease nodes, E={e ij |i,j∈{1,…,m}} represents a set of m edges; the adjacency matrix A=[a ij ] is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j ); Performing low-rank representation learning and mining on the chronic disease comorbidity network to output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to characterize the comorbidity network; Use the community partitioning mechanism to identify the community structure in the comorbidity network and discover the comorbidity pattern.

2. The method according to claim 1, characterized in that The method for constructing the chronic disease comorbidity network includes: Sort out chronic disease records, and sort out data records from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data; Count the frequency of disease occurrence, and calculate the frequency Q(s) of each disease occurrence from the data records. i ) and the frequency of disease combination co-occurrence Q(s i ,s j ), where a disease i If it appears in a disease record, it is counted once. i and j If they appear together in one disease record, they are counted once, where i,j = 1, 2, …, n represents the number of diseases of interest; Calculate the mutual information value between two diseases as follows: Among them, p(s i )=Q(s i ) / F,p(s j )=Q(s j ) / F respectively calculate disease s i and j The observation frequency, where F represents the total observation frequency, p(s i ,s j )=Q(s i ,s j ) / F calculates the number of diseases observed at the same time i and j frequency; Constructing a comorbidity network to describe the complex impact relationships of chronic diseases.

3. The method according to claim 2, characterized in that The low-rank characterization method using fused graph convolution constraints to characterize the comorbidity network includes: Design the objective function, which is as follows: U,H,W (1) ,W (2) ≥0 Where A is the adjacency matrix of the comorbidity network, U is a feature matrix of size n×K, and n and K are the number of nodes and communities in the comorbidity network, respectively; is the F-norm of the calculation matrix; Tr(·) is the trace of the calculation matrix; U T represents the transpose of the matrix U; L = DA is the Laplace matrix of A, where D = ∑ l A il is the degree matrix of A, where A il is the element value at the corresponding subscript in A; represents the hidden layer feature matrix of the GCN module, where h i Corresponding to node v i The feature vector of , d represents the feature dimension; and Represents the weight matrix of the GCN module; is the normalized adjacency matrix, where To add a self-connected adjacency matrix, for The degree matrix of for The element value at the corresponding subscript in ; λ1 is the graph regularization coefficient; σ(·) is the nonlinear activation function of the GCN module; Convert the graph convolution constraints into the following regularized form: Solve the following optimization problem and obtain the parameter matrices U, H, W (1) and W (2) : (U,H,W (1) ,W (2) )←argmin J GCGS ,s.t.U,H,W (1) ,W (2) ≥0 Combining the Lagrangian function method and the KKT conditions of inequality constraints, the learning rules for the optimization problem are derived: Among them, λ1 is the graph regularization coefficient, λ2 is the graph convolution regularization coefficient, g1 and g1′ (derivative of g1) represent and g2 and g2′ (derivative of g2), respectively represent and σ′(·) is the derivative of σ(·); β is the linear adjustment coefficient of the learning scale factor of the control feature factor matrix U, which takes values ​​in the interval (0,1); ⊙ represents the Hadamard product of the matrix; according to the learning rule, the feature and weight matrices U, H, W are iteratively updated respectively. (1) and W (2) , until the convergence condition is reached, and the final feature matrix U, H and weight W are obtained (1) , W (2) As a solution to the optimization problem, a feature matrix U is output as an indicator matrix for community division.

4. The method according to claim 3, characterized in that The method of using the community partitioning mechanism to identify the community structure in the comorbidity network to discover the comorbidity pattern includes: After training to obtain the characteristic parameters U and H, U is used as the indicator matrix for node-disease comorbidity module affiliation division, and the nodes in the comorbidity network are judged one by one and assigned to the comorbidity module. The assignment rules are as follows: Where V represents the node set in the comorbidity network, v i represents any node; C s is the comorbidity combination s, s∈{1,2,…,K}, K is the total number of comorbidity combinations; u ik is an element in the low-rank matrix U, representing node v i The probability of being classified into the comorbidity combination k; if u is is the maximum value among them, then node v i The probability of being classified into the comorbidity combination s is the highest. After the comorbidity combinations of all nodes in the target comorbidity network are divided, all possible comorbidity combinations identified can be obtained. C = {C1, C2, …, C K }.

5. A chronic disease comorbidity pattern recognition device integrating graph convolution constraint enhanced low-rank representation, characterized in that: include: An acquisition unit, used to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from inspections, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources; A construction unit is used to construct a chronic disease comorbidity network using medical data resources, wherein the chronic disease comorbidity network is used to describe the correlation and influence between diseases, and can be constructed by calculating the correlation between diseases or patients according to multi-source data, wherein the multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data, wherein the chronic disease comorbidity network is represented by a graph G = (V, E), V = {v i |i∈{1,…,n}} represents a set of n disease nodes, E={e ij |i,j∈{1,…,m}} represents a set of m edges; the adjacency matrix A=[a ij ] is used to represent and store the target comorbidity network G, where a ij Represents the disease node v i and v j The interaction between them is equal to I(s i ,s j ); A representation unit, used for performing low-rank representation learning on the chronic disease comorbidity network to mine and output the community structure therein, wherein the low-rank representation learning adopts a low-rank representation method fused with graph convolution constraints to characterize the comorbidity network; The partitioning unit is used to identify the community structure in the comorbidity network and discover the comorbidity pattern using the community partitioning mechanism.

6. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 4 above.

Images