A method, device, electronic device and storage medium for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation

Abstract

The present application discloses a method, device, electronic device and storage medium for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation. The method acquires medical data resources and uses the medical data resources to construct a chronic disease comorbidity network. The chronic disease comorbidity network is used to describe the correlation and influence between diseases. Low-rank representation learning is performed on the chronic disease comorbidity network to mine and output the community structure therein. The community partitioning mechanism is used to identify the community structure in the comorbidity network and explore the comorbidity pattern. The introduction of relaxed symmetric constraints in the learning objectives can well perceive the inherent symmetric structural characteristics of the network, and the introduction of graph regularization technology that captures local topological features effectively maintains the inherent geometric structural characteristics of the network.

Description

Technical Field

[0001] The present invention mainly relates to the field of pattern recognition, and in particular to a method, device, electronic device and storage medium for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation. Background Art

[0002] Chronic noncommunicable diseases (NCDs) have become a major threat to global public health and human well-being, placing a heavy economic burden on patients and society. Due to the complex etiology, insidious onset, long course, and persistent nature of chronic diseases, some patients often suffer from multiple chronic conditions simultaneously, a phenomenon referred to by the World Health Organization as "comorbidity." With the global aging population, the issue of chronic disease comorbidity has become increasingly prominent, posing a major challenge for global health. The complex interplay between diseases poses significant challenges to diagnosis and treatment. Understanding the specific factors and processes of comorbidity, as well as their interactions and potential synergies, is crucial for facilitating diagnosis, improving patient quality of life, improving prevention, and reducing healthcare system costs. Therefore, leveraging emerging technologies such as artificial intelligence and big data to explore complex patterns of comorbidity among chronic diseases provides important decision-making support for predicting disease risk, prevention, treatment, and management, and has practical implications 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. Exploring comorbidity patterns and exploring their distribution patterns can 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 have different findings on the nature 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, commonly used methods are summarized into the following four categories:

[0004] (1) Odds ratio: This 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 Dutch study 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 most correlated. 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: This method aims to identify the complex relationships between multiple diseases, combine multiple related factors into a few comprehensive indicators, simplify the data structure, and reveal variable associations. A study of Japanese adults used factor analysis to identify five comorbidity patterns for 17 chronic diseases. Factor analysis does not rely on traditional grouping assumptions. It extracts important information by reducing dimensionality and simplifying data, and can more effectively reveal variable relationships.

[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 cardiovascular disease, allergic diseases, and other representative diseases. Cluster analysis can explore the commonalities of the underlying factors of these comorbidity patterns and help understand the phenomenon of chronic disease comorbidity.

[0007] (4) Association rules: used to analyze direct associations between multiple chronic diseases and reveal strong correlations in comorbidity patterns. A UK study evaluated comorbidity patterns in middle-aged and elderly people through cluster analysis and association rule mining, discovering three clusters and 30 disease patterns, revealing the complex relationships and central roles of different diseases, such as diabetes, hypertension, and asthma. These chronic diseases have complex interactions and associations, requiring comprehensive assessment and treatment to achieve better health outcomes.

[0008] Due to the complex interactions and influences between diseases, traditional methods struggle to uncover the deep relationships and complex connections between diseases, making it difficult to accurately identify patterns of comorbidity. With the development of complexity science, complex network analysis, which describes complex relationships from a holistic, systemic perspective, is helping to fully reveal the complex influence patterns between diseases from a holistic perspective and has become a mainstream tool for exploring patterns of chronic disease comorbidity. Community detection algorithms can identify closely connected clusters within a network and thus be used to identify patterns of disease comorbidity.

[0009] This paper designs a new relaxed constrained symmetric low-rank representation method to achieve a balance between symmetry representation and representation learning ability, and then constructs a community detection model for chronic disease comorbidity networks to explore comorbidity patterns among chronic diseases from the perspective of complex network representation learning. 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 based on relaxed constrained symmetric 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 based on relaxed constrained symmetric low-rank representation, characterized by comprising:

[0012] Acquiring medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from testing, diagnosis, treatment, 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. The multi-source data includes basic patient information and test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data. The chronic disease comorbidity network is represented by a graph G = (V, E), where 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; where the adjacency matrix A=[a ij ] is used to represent and store the target comorbidity network G, a ij Represents the disease node v i and v j The interaction relationship between them is equal to I(s i , s j );

[0014] 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 symmetric non-negative matrix factorization algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network;

[0015] Use the community division 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 from the above data records. i ) and the frequency of disease combinations occurring together Q(s i , s j ), among which a disease s i If it appears in one disease record, it is counted as 1. i and s j If they co-occur in one disease record, they are counted as 1, 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(s i ) / F,p(s j )=Q(s j ) / F were used to calculate disease s i and s 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 s j frequency;

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

[0023] Preferably, the characterization of the comorbidity network using a symmetric low-rank characterization method with relaxed constraints includes:

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

[0025]

[0026] stW=P, H=Q, P=Q; P, Q≥0

[0027] Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent learnable feature matrices, and P and Q are auxiliary parameter matrices, whose sizes are the same as the feature matrices W and H, respectively; represents the F-norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) is used to calculate the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A. The purpose of introducing auxiliary matrices P and Q is to separate the training and constraints of decision parameters W and H, and to achieve symmetric characterization under the relaxed constraints "W = P, H = Q, P = Q", and numerical characteristic characterization under the non-negative constraints "P, Q ≥ 0".

[0028] Construct the augmented Lagrangian function and use the ADMM alternating direction multiplier method to construct the augmented Lagrangian function:

[0029]

[0030] Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent the feature matrix, and P and Q are auxiliary parameter matrices that are the same as the feature matrix W and H; represents the F norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) calculates the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A; ○ represents the Hadamard product of the matrix; α, β, and θ correspond to the weights of the three penalty terms, respectively, controlling their proportionality. The non-negativity of P and Q can be achieved by mapping their value ranges to non-negative space;

[0031] The update rule for parameters is derived. In the ADMM optimization framework, let t and t+1 represent the current and updated iteration states of the parameters, respectively. All parameters are updated iteratively using the update rule until the convergence condition is reached. The convergence condition is: (1) the absolute value of the difference between the objective function values ​​after two consecutive iterative training is less than 0.1; (2) or the number of iterations reaches 20, so the update rule is as follows:

[0032]

[0033] in represents the gradient, η is the learning rate in gradient ascent, outputs feature parameters W, H, P and Q, and Q is used as the community partition indicator matrix.

[0034] Preferably, the method of using a community partitioning mechanism to identify the community structure in the comorbidity network to discover the comorbidity pattern includes:

[0035] After training to obtain the characteristic parameters W, H, P, and Q, Q is used as the indicator matrix for node-disease comorbidity module affiliation division. The nodes in the comorbidity network are judged one by one and assigned to the comorbidity module. The assignment rules are as follows:

[0036]

[0037] Where V represents the node set in the comorbidity network, v j Represents any node; C s is the comorbidity combination s, s∈{1,2,…,K}, K is the total number of comorbidity combinations; q jk is an element in the low-rank matrix Q, representing node v j The probability of being classified into comorbidity combination k, q js is the maximum value among them, indicating that node v j The probability of being divided into the comorbidity combination s is the highest. After dividing the comorbidity combinations of all nodes in the target comorbidity network, all the possible comorbidity combinations identified can be obtained. C = {C1, C2, ..., C K}.

[0038] 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 by comprising:

[0039] An acquisition unit is used to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from examinations, diagnoses, treatments, prescriptions, electronic medical records, and clinical data resources;

[0040] A construction unit constructs 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, and the chronic disease comorbidity network is represented by a graph G = (V, E), wherein 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 relationship between them is equal to I(s i , s j );

[0041] A representation unit is used to 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 symmetric non-negative matrix factorization algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network;

[0042] The partitioning unit is used to identify the community structure in the comorbidity network and discover the comorbidity pattern using the community partitioning mechanism.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, characterized by including:

[0044] processor;

[0045] a memory for storing instructions executable by the processor;

[0046] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the above method steps.

[0047] 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.

[0048] Compared with the existing technology, the present invention has the following advantages: (1) Compared with the standard symmetric non-negative matrix factorization (SNMF) algorithm, the technical solution RSN of the present invention has an expanded feature space. Multiple feature matrices are used to represent the target undirected network, thereby maintaining its representation learning ability; (2) Relaxed constraints are used to achieve symmetry characterization. Compared with the standard non-negative matrix factorization (NMF) algorithm, by introducing relaxed symmetry constraints in the learning objectives, the designed model can well perceive the inherent symmetric structural characteristics of the network; (3) The spatial geometric structure constraints are effectively maintained, and the graph regularization technology that captures local topological features is introduced to effectively maintain the inherent geometric structure characteristics of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] A more complete understanding of the exemplary embodiments of the present invention can be obtained by referring to the following drawings. The drawings are intended 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 components or steps.

[0050] Figure 1 A flowchart of a method for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation according to an exemplary embodiment of the present application is provided;

[0051] Figure 2 This is a schematic diagram of a chronic disease comorbidity pattern recognition device based on relaxed constrained symmetric low-rank representation according to another exemplary embodiment of the present application. DETAILED DESCRIPTION

[0052] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although 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. Rather, these embodiments are provided 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.

[0053] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0054] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0055] 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.

[0056] 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 with reference to the accompanying drawings.

[0057] 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:

[0058] S101: Acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions compiled from testing, diagnosis, treatment, prescriptions, electronic medical records, and clinical data resources;

[0059] S102: Utilize medical data resources to construct a chronic disease comorbidity network. The chronic disease comorbidity network is used to describe the correlation and influence between diseases. It can be constructed by calculating the correlation between diseases or patients based on multi-source data. The multi-source data includes basic patient information as well as test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data.

[0060] Specifically, the chronic disease comorbidity network is represented by a graph G = (V, E), where 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; where the adjacency matrix A=[a ij ] is used to represent and store the target comorbidity network G, a ij Represents the disease node v i and v j The interaction relationship between them is equal to I(s i , s j );

[0061] 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 uses a symmetric non-negative matrix factorization algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network;

[0062] S104: Use the community division mechanism to identify the community structure in the comorbidity network and discover the comorbidity pattern. Specifically, the method for constructing the chronic disease comorbidity network includes the following steps:

[0063] (1) Sort out chronic disease records and extract data records from tests, diagnoses, treatments, prescriptions, electronic medical records, and clinical data;

[0064] (2) Count the frequency of disease occurrence, and calculate the frequency Q(s) of each disease from the data records. i ) and the frequency of disease combinations occurring together Q(s i , s j ), among which a disease s i If it appears in one disease record, it is counted as 1. i and s j If they co-occur in one disease record, they are counted as 1, where i, j = 1, 2, ..., n represents the number of diseases of interest;

[0065] Among them, the mutual information value between two diseases is calculated as follows:

[0066]

[0067] Among them, p(s i )=Q(s i ) / F,p(s j )=Q(s j ) / F were used to calculate disease s i and s 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 s j frequency;

[0068] (3) Construct a comorbidity network to describe the complex impact relationships of chronic diseases.

[0069] Specifically, the characterization of the comorbidity network using a symmetric low-rank representation method with relaxed constraints includes the following steps:

[0070] (1) Design objective function;

[0071] Specifically, the objective function is as follows:

[0072]

[0073] stW=P, H=Q, P=Q; P, Q≥0

[0074] Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent learnable feature matrices, and P and Q are auxiliary parameter matrices, whose sizes are the same as the feature matrices W and H, respectively; represents the F-norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) is used to calculate the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A. The purpose of introducing auxiliary matrices P and Q is to separate the training and constraints of decision parameters W and H, and to achieve symmetric characterization under the relaxed constraints "W = P, H = Q, P = Q", and numerical characteristic characterization under the non-negative constraints "P, Q ≥ 0".

[0075] (2) Constructing the augmented Lagrangian function;

[0076] Specifically, the ADMM alternating direction multiplier method is used to construct the augmented Lagrangian function:

[0077]

[0078] Where A is the adjacency matrix corresponding to the comorbidity network; the decision parameters W and H represent the feature matrix, and P and Q are auxiliary parameter matrices that are the same as the feature matrix W and H; represents the F norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) calculates the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A; ○ represents the Hadamard product of the matrix; α, β, and θ correspond to the weights of the three penalty terms, respectively, controlling their proportionality. The non-negativity of P and Q can be achieved by mapping their value ranges to non-negative space;

[0079] The update rule for parameters is derived. In the ADMM optimization framework, let t and t+1 represent the current and updated iteration states of the parameters, respectively. All parameters are updated iteratively using the update rule until the convergence condition is reached. The convergence condition is: (1) the absolute value of the difference between the objective function values ​​after two consecutive iterative training is less than 0.1; (2) or the number of iterations reaches 20, so the update rule is as follows:

[0080]

[0081] in, represents the gradient, η is the learning rate in gradient ascent, outputs feature parameters W, H, P and Q, and Q is used as the community partition indicator matrix.

[0082] Specifically, using the community partitioning mechanism to identify the community structure in the comorbidity network to discover comorbidity patterns includes:

[0083] After training to obtain the characteristic parameters W, H, P, and Q, Q is used as the indicator matrix for node-disease comorbidity module affiliation division. The nodes in the comorbidity network are judged one by one and assigned to the comorbidity module. The assignment rules are as follows:

[0084]

[0085] Among them, V represents the node set in the comorbidity network, v j Represents any node; C s is the comorbidity combination s, s∈{1,2,…,K}, K is the total number of comorbidity combinations; q jk is an element in the low-rank matrix Q, representing node v j The probability of being classified into comorbidity combination k, q js is the maximum value among them, indicating that node v j The probability of being classified into the comorbidity combination s is the highest. After dividing the comorbidity combinations of all nodes in the target comorbidity network, all the possible comorbidity combinations identified can be obtained. C={C1,C2,…,C K}.

[0086] Compared with the existing technology, the present invention has the following advantages: (1) Compared with the standard symmetric non-negative matrix factorization (SNMF) algorithm, the technical solution RSN of the present invention has an expanded feature space. Multiple feature matrices are used to represent the target undirected network, thereby maintaining its representation learning ability; (2) Relaxed constraints are used to achieve symmetry characterization. Compared with the standard non-negative matrix factorization (NMF) algorithm, by introducing relaxed symmetry constraints in the learning objectives, the designed model can well perceive the inherent symmetric structural characteristics of the network; (3) The spatial geometric structure constraints are effectively maintained, and the graph regularization technology that captures local topological features is introduced to effectively maintain the inherent geometric structure characteristics of the network.

[0087] In the above embodiments, a method is provided. Accordingly, the present application also provides an apparatus. The apparatus provided in the embodiments of the present application can implement the above methods. The apparatus can be implemented through software, hardware, or a combination of software and hardware. For example, the apparatus can include integrated or separate functional modules or units to perform the corresponding steps in each of the above methods.

[0088] In some implementations 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.

[0089] like Figure 2 As shown, the apparatus 20 may include:

[0090] An acquisition unit 201 is configured to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions compiled from testing, diagnosis, treatment, prescriptions, electronic medical records, and clinical data resources;

[0091] A construction unit 202 constructs 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 as well as test, diagnosis, treatment, prescription data, electronic medical records, clinical data, and omics big data;

[0092] Specifically, the chronic disease comorbidity network is represented by a graph G = (V, E), where 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 relationship between them is equal to I(s i ,s j );

[0093] A representation unit 203 is configured to 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 symmetric non-negative matrix factorization algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network;

[0094] The partitioning unit 204 is configured to use a community partitioning mechanism to identify the community structure in the comorbidity network and discover comorbidity patterns.

[0095] 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.

[0096] 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.

[0097] The memory may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface (which may be wired or wireless), such as the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0098] The bus may be an ISA bus, a PCI bus, or an EISA bus. 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 of the aforementioned embodiments of the present application may be applied to the processor or implemented by the processor.

[0099] The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. 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), an off-the-shelf field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The electronic device provided in the embodiments of this application and the method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the method adopted, operated, or implemented therein.

[0100] The embodiments of the present application further 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.

[0101] 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.

[0102] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architectures, 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, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that 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 boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] Those skilled in the art will 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.

[0104] In the several embodiments provided in this 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 interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0106] 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.

[0107] 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method 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.

[0108] 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 them. 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 make equivalent replacements for some or all of the technical features therein. 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 description of the present application.

Claims

1. A method for recognizing chronic disease comorbidity patterns based on relaxed constrained symmetric low-rank representation, characterized by: include: Acquiring medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from testing, diagnosis, treatment, 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 as well as 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), where 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; where the adjacency matrix A=[a ij ] is used to represent and store the target comorbidity network G, a ij Represents the disease node v i and v j The interaction relationship between them is equal to I(s i ,s j ); Low-rank representation learning is performed on the chronic disease comorbidity network to mine and output the community structure therein, wherein the low-rank representation learning adopts a symmetric non-negative matrix decomposition algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network; using a symmetric low-rank representation method with relaxed constraints to characterize the comorbidity network includes: Design the objective function, which is as follows: Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent learnable feature matrices, and P and Q are auxiliary parameter matrices, whose sizes are the same as the feature matrices W and H, respectively; represents the F-norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) is used to calculate the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A. The purpose of introducing auxiliary matrices P and Q is to separate the training and constraints of decision parameters W and H, and to achieve symmetric characterization under the relaxed constraints "W=P,H=Q,P=Q", and numerical characteristic characterization under the non-negative constraints "P,Q≥0". Construct the augmented Lagrangian function and use the ADMM alternating direction multiplier method to construct the augmented Lagrangian function: Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent the feature matrix, and P and Q are auxiliary parameter matrices that are the same as the feature matrix W and H; represents the F norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) calculates the trace of the matrix; L represents the Laplace matrix of the adjacency matrix A; ° represents the Hadamard product of the matrix; α, β, and θ correspond to the weights of the three penalty terms, respectively, controlling their proportional sizes. The non-negativity of P and Q can be achieved by mapping their value ranges to non-negative space; The update rule for parameters is derived. In the ADMM optimization framework, let t and t+1 represent the current and updated iteration states of the parameters, respectively. All parameters are updated iteratively using the update rule until the convergence condition is reached. The convergence condition is: (1) the absolute value of the difference between the objective function values ​​after two consecutive iterative training is less than 0.1; (2) or the number of iterations reaches 20, so the update rule is as follows: in, represents the gradient, η is the learning rate in gradient ascent, outputs feature parameters W, H, P and Q, and Q is used as the community partition indicator matrix; Use the community division 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 from the above data records. i ) and the frequency of disease combinations occurring together Q(s i ,s j ), among which a disease s i If it appears in one disease record, it is counted as 1. i and s j If they appear together in one disease record, they are counted as 1, 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 were used to calculate disease s i and s 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 s j frequency; Construct a comorbidity network to describe the complex impact relationships of chronic diseases.

3. The method according to claim 2, characterized in that The use of 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 W, H, P, and Q, Q is used as the indicator matrix for node-disease comorbidity module affiliation division. 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 j Represents any node; C s is the comorbidity combination s, s∈{1,2,…,K}, K is the total number of comorbidity combinations; q jk is an element in the low-rank matrix Q, representing node v j The probability of being classified into comorbidity combination k, q js is the maximum value among them, indicating that node v j The probability of being classified into the comorbidity combination s is the highest. After dividing the comorbidity combinations of all nodes in the target comorbidity network, all the possible comorbidity combinations identified can be obtained. C={C1,C2,…,C K }.

4. A chronic disease comorbidity pattern recognition device based on relaxed constrained symmetric low-rank representation, characterized in that: include: An acquisition unit is used to acquire medical data resources, wherein the medical data resources include data records of chronic disease conditions sorted out from examinations, 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 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, and the chronic disease comorbidity network is represented by a graph G = (V, E), wherein 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 relationship between them is equal to I(s i ,s j ); A representation unit is configured to perform low-rank representation learning on the chronic disease comorbidity network and output the community structure therein, wherein the low-rank representation learning adopts a symmetric non-negative matrix decomposition algorithm with relaxed constraints to obtain a low-rank representation matrix of the target network; characterizing the comorbidity network using a symmetric low-rank representation method with relaxed constraints includes: Design the objective function, which is as follows: Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent learnable feature matrices, and P and Q are auxiliary parameter matrices, whose sizes are the same as the feature matrices W and H, respectively; represents the F-norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) is used to calculate the trace of the matrix; L represents the Laplacian matrix of the adjacency matrix A. The purpose of introducing auxiliary matrices P and Q is to separate the training and constraints of decision parameters W and H, and to achieve symmetric characterization under the relaxed constraints "W=P,H=Q,P=Q", and numerical characteristic characterization under the non-negative constraints "P,Q≥0". Construct the augmented Lagrangian function and use the ADMM alternating direction multiplier method to construct the augmented Lagrangian function: Where A is the adjacency matrix corresponding to the comorbidity network; decision parameters W and H represent the feature matrix, and P and Q are auxiliary parameter matrices that are the same as the feature matrix W and H; represents the F norm of the matrix; λ is a positive constant representing the coefficient of the graph regularization term; Tr(·) calculates the trace of the matrix; L represents the Laplace matrix of the adjacency matrix A; ° represents the Hadamard product of the matrix; α, β, and θ correspond to the weights of the three penalty terms, respectively, controlling their proportional sizes. The non-negativity of P and Q can be achieved by mapping their value ranges to non-negative space; The update rule for parameters is derived. In the ADMM optimization framework, let t and t+1 represent the current and updated iteration states of the parameters, respectively. All parameters are updated iteratively using the update rule until the convergence condition is reached. The convergence condition is: (1) the absolute value of the difference between the objective function values ​​after two consecutive iterative training is less than 0.1; (2) or the number of iterations reaches 20, so the update rule is as follows: in, represents the gradient, η is the learning rate in gradient ascent, outputs feature parameters W, H, P and Q, and Q is used as the community partition indicator matrix; The partitioning unit is used to identify the community structure in the comorbidity network and discover the comorbidity pattern using the community partitioning mechanism.

5. 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 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 3.

Images