A symptom management method and system for chronic patients based on symptom network analysis

Abstract

The present invention provides a method and system for managing chronic disease symptoms based on symptom network analysis, relating to the field of data processing technology. The method comprises: collecting a symptom assessment dataset of patients with chronic diseases; extracting symptom clusters from the symptom assessment dataset of patients with chronic diseases by combining principal component analysis and varimax orthogonal rotation; constructing a symptom network using symptoms as nodes and relationships between symptoms as edges; using concurrent network analysis to identify core symptoms and bridge symptoms; constructing a dynamic symptom network based on a cross-lagged network model; introducing influencing factors into the dynamic symptom network, performing subgroup analysis on the dynamic symptom network, and identifying core influencing factors; constructing a chronic disease development trend prediction model based on LSTM; collecting clinical symptoms and clinical indicators of patients with chronic diseases; extracting core influencing factors; and predicting and outputting the development outcomes of patients with chronic diseases using the LSTM-based chronic disease development trend prediction model.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for managing symptoms of chronic patients based on symptom network analysis. Background Art

[0002] Symptom network analysis is a technique that uses graph theory to study how different symptoms relate to each other and identify their relative importance and impact. Symptom management refers to the effective monitoring, assessment, and intervention of patients' symptoms to alleviate pain and improve their quality of life. Symptom management for chronic patients based on symptom network analysis builds and analyzes networks between symptoms, helping doctors and patients identify core symptoms and potential influencing factors, thereby more effectively managing and treating symptoms in patients with chronic diseases.

[0003] Symptom management for patients with chronic diseases can help doctors understand the development trend of symptoms of chronic diseases more accurately, improve the treatment effect of chronic diseases and the quality of life of patients, thereby effectively identifying potential risk factors and providing a basis for patients to develop more scientific intervention measures.

[0004] Traditional symptom management approaches for chronic disease often overlook the complex connections between symptoms and individual differences among patients, failing to fully identify the core influencing factors and potential risk factors. Furthermore, traditional approaches have limited predictive power for chronic disease symptoms, making it difficult to tailor treatment plans to each patient's specific circumstances, thus compromising treatment effectiveness and quality of life. Summary of the Invention

[0005] In order to solve the technical problems that traditional symptom management methods for chronic patients often ignore the complex connections between symptoms and individual differences between different patients, and are unable to fully identify the core influencing factors and potential risk factors between symptoms, and traditional methods have weak predictive capabilities for chronic disease symptoms, and often find it difficult to formulate personalized treatment plans for the specific conditions of each patient, thereby affecting the treatment effect and the patient's quality of life, the present invention provides a chronic patient symptom management method and system based on symptom network analysis.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a method for managing symptoms in chronic patients based on symptom network analysis, comprising:

[0009] S1: Collect symptom data of patients with chronic diseases and obtain a symptom assessment dataset for patients with chronic diseases;

[0010] S2: Combined principal component analysis and varimax orthogonal rotation method, symptom clusters were extracted from the symptom assessment dataset of patients with chronic diseases. Symptom clusters include multiple symptoms.

[0011] S3: Construct a symptom network with each symptom as a node and the relationship between symptoms as an edge;

[0012] S4: Use a concurrent network analysis algorithm to identify core symptoms and bridge symptoms in the symptom network;

[0013] S5: Based on the relationship between core symptoms and bridge symptoms, a dynamic symptom network based on the cross-lagged network model was constructed;

[0014] S6: Introduce influencing factors into the dynamic symptom network, and conduct subgroup analysis of the dynamic symptom network based on the relationship between influencing factors and symptoms to identify the core influencing factors that lead to differences in the symptom network structure;

[0015] S7: Based on the core influencing factors, a LSTM-based chronic disease development trend prediction model was constructed;

[0016] S8: Collect real-time clinical symptom data and real-time clinical indicator data of patients with chronic diseases;

[0017] S9: Extract real-time core influencing factors from real-time clinical symptom data and real-time clinical indicator data;

[0018] S10: Input the real-time core influencing factors into the chronic disease development trend prediction model to predict and output the chronic disease symptom development results of chronic disease patients.

[0019] Second aspect:

[0020] An embodiment of the present invention provides a chronic patient symptom management system based on symptom network analysis, comprising:

[0021] processor;

[0022] A memory stores computer-readable instructions, which, when executed by a processor, implement the method for managing symptoms of chronic patients based on symptom network analysis as described in the first aspect.

[0023] The third aspect:

[0024] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for managing symptoms of chronic patients based on symptom network analysis according to the first aspect is implemented.

[0025] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0026] In an embodiment of the present invention, symptom data from patients with chronic diseases is collected to provide real input for subsequent analysis. Symptom clusters are extracted based on principal component analysis and maximum variance orthogonal rotation. Subsequently, a symptom network is constructed with symptoms as nodes and relationships between symptoms as edges. Concurrent network analysis is used to identify core symptoms and bridge symptoms in the symptom network. Based on the relationships between core symptoms and bridge symptoms, a dynamic symptom network based on a cross-lagged network model is constructed. This allows symptom management to not only be limited to static analysis but also capture the evolution of symptoms over time. Furthermore, influencing factors are introduced into the dynamic symptom network, and subgroup analysis is performed on the dynamic symptom network to identify the core influencing factors that lead to differences in the symptom network structure. Based on these core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed, thereby providing forward-looking guidance for treatment. Finally, by collecting clinical symptom data and clinical indicator data from patients and extracting core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed to predict and output the chronic disease symptom development outcomes of chronic disease patients, providing a scientific basis for personalized treatment and long-term management. By analyzing the relationships and interactions between the symptoms of chronic patients, the present invention can effectively manage and treat the symptoms of patients with chronic diseases, help doctors and patients identify core symptoms and potential influencing factors, improve the treatment effect and quality of life of chronic patients, and provide personalized symptom management plans for each patient's unique situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A flowchart of a method for managing symptoms of chronic patients based on symptom network analysis provided by an embodiment of the present invention;

[0029] Figure 2 A schematic structural diagram of a chronic patient symptom management system based on symptom network analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0031] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0032] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0033] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0034] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0035] Reference Manual Figure 1 , shows a flow chart of a chronic patient symptom management method based on symptom network analysis provided by an embodiment of the present invention.

[0036] An embodiment of the present invention provides a method for managing chronic patient symptoms based on symptom network analysis. This method can be implemented by a chronic patient symptom management device based on symptom network analysis, which can be a terminal or a server. The processing flow of the chronic patient symptom management method based on symptom network analysis can include the following steps:

[0037] S1: Collect symptom data of patients with chronic diseases and obtain a symptom assessment dataset for patients with chronic diseases.

[0038] Among them, chronic disease patients refer to patients who suffer from long-term diseases that cannot be completely cured, such as hypertension, diabetes, chronic respiratory diseases, etc., and require long-term management and treatment. The symptom assessment dataset refers to the collection of information collected about patient symptoms, which is used for subsequent analysis to help evaluate and manage patient symptoms.

[0039] It’s important to note that by collecting symptom data, clinical data, and personal information from patients with chronic diseases, we can gain a comprehensive understanding of their health status. This data not only provides effective input for subsequent symptom cluster extraction and network construction, but also provides a basis for personalized treatment and prediction, thereby improving the accuracy and effectiveness of chronic disease management.

[0040] In a possible implementation, the chronic disease patient symptom assessment dataset specifically includes: symptom information, clinical data, and patient personal information.

[0041] Symptom information includes symptom name, severity, frequency, duration, and symptom trends. Clinical data includes the patient's chronic disease type, medical history, and imaging data. Patient personal information includes age, gender, weight, height, and lifestyle information.

[0042] S2: Combining principal component analysis and varimax orthogonal rotation, symptom clusters are extracted from the symptom assessment dataset of patients with chronic diseases. Symptom clusters include multiple symptoms.

[0043] Principal component analysis (PCA) is a statistical method used to transform high-dimensional data into low-dimensional data while preserving as much variability as possible in the original data. Varimax rotation is a rotation method designed to clarify the interpretation of principal components. By rotating the eigenvectors, it allows each factor (principal component) to more strongly reflect certain specific variables, thereby facilitating subsequent analysis and understanding. Symptom clusters refer to the collection of interrelated symptoms extracted through principal component analysis.

[0044] It's important to note that PCA can extract the most representative factors from a large number of symptoms, reducing dimensionality while retaining important information. Varimax rotation further enhances the interpretability of these factors. This approach not only makes symptom data more concise and understandable, but also reveals the inherent connections between symptoms, helping doctors better identify symptom clusters within patients and laying a solid foundation for subsequent symptom network construction and analysis.

[0045] In a possible implementation, S2 specifically includes:

[0046] S201: Standardize a symptom assessment dataset for patients with chronic diseases.

[0047] S202: Based on the principal component analysis method, calculate the covariance matrix of the standardized data set:

[0048]

[0049] Where C represents the covariance matrix, Z irepresents the normalized feature vector of the i-th symptom, i=1,…,n, n represents the total number of symptoms, and T represents the transpose.

[0050] S203: Calculate the eigenvalues ​​and eigenvectors of the covariance matrix:

[0051] CV k =λ k V k

[0052] Among them, V k represents the kth eigenvector, λ k represents the kth eigenvalue.

[0053] S204: Select the principal component according to the size of the eigenvalue.

[0054] S205: Calculate the weight of the principal component and determine the eigenvector to be rotated:

[0055] PC k =ZV k

[0056] Among them, PC k represents the kth principal component, and Z represents the data matrix.

[0057] S206: Rotate the feature vector to be rotated by the maximum variance orthogonal rotation method:

[0058] V rot =VQ

[0059] Among them, V rot Represents the rotated eigenvector, V represents the eigenvector to be rotated, and Q represents the rotation matrix.

[0060] S207: Determine the factor loading matrix with the goal of maximizing the rotation target:

[0061]

[0062] Among them, Varimax represents the rotation method, F ij represents the loading of the i-th variable on the j-th factor.

[0063] S208: Determine the symptom cluster based on the factor loading matrix.

[0064] It should be noted that extracting symptom clusters through principal component analysis and varimax orthogonal rotation can effectively categorize and simplify large amounts of symptom data. This step transforms large amounts of symptom data into more actionable symptom clusters, facilitating subsequent analysis and management.

[0065] S3: Construct a symptom network with each symptom as a node and the relationship between symptoms as an edge.

[0066] In graph theory, a node is a basic element in a graph, representing an entity. In a symptom network, each symptom is a node, representing a specific symptom. In a symptom network, edges represent the relationships or interactions between different symptoms. A symptom network is a network structure constructed by treating the symptoms of chronic disease patients as nodes and using the relationships between symptoms.

[0067] It's important to note that by constructing a symptom network, different symptoms are considered nodes, and the relationships between symptoms are considered edges, forming a complex network structure. This approach can help reveal the inherent connections and interactions between symptoms, identifying their dependencies and mutual influences. Through the symptom network, doctors can clearly see which symptoms are interconnected and which symptoms may be key points in disease progression, providing a powerful tool for subsequent symptom analysis, management, and prediction.

[0068] S4: Use a concurrent network analysis algorithm to identify core symptoms and bridge symptoms in the symptom network.

[0069] Among them, the concurrent network analysis algorithm refers to analyzing symptoms that are temporally related to each other to find out the interactive relationship between different symptoms. Core symptoms refer to symptoms that occupy an important position in the symptom network and affect other symptoms or disease progression. Bridge symptoms refer to symptoms that connect different symptom groups. These symptoms play a key bridging role between different symptoms. Understanding bridge symptoms helps to reveal important links in the symptom network.

[0070] In a possible implementation, S4 specifically includes:

[0071] S401: Through linear projection, the node features and edge features are converted into hidden features, and the hidden features are input into the GAT model:

[0072]

[0073] in, represents the initial eigenvector of node i, U 0 represents the initial node weight matrix, α i represents the input feature vector of node i, u 0 represents the initial node bias vector, Represents the feature vector of edge (x, y) in the initial layer, V 0 represents the initial edge weight matrix, β ij represents the input feature vector of edge (x,y), v 0 Represents the initial edge bias vector.

[0074] S402: Calculate the attention weight of each symptom node through the graph attention mechanism of the GAT model:

[0075]

[0076] in, represents the feature representation of edge (x, y) under the k-th head, LeakyReLU represents the nonlinear activation function, a l Represents the scalar coefficient of the lth layer, Concat represents the concatenation operation, W l represents the weight matrix of layer l, represents the feature vector of node i in layer l, Represents the feature vector of node j in layer l.

[0077] It should be noted that the graph attention mechanism (GAT) is a mechanism based on graph neural networks that can assign different attention weights to each node, thereby prioritizing the most important parts of the network for the model.

[0078] S403: Normalize the attention weights:

[0079]

[0080] in, represents the normalized attention weight of edge (x, y) under the kth head and lth layer, exp represents the exponential function, N i Represents the set of neighbor nodes of node i.

[0081] S404: Based on the normalized attention weights, the symptom nodes are updated by introducing asymmetry in the neighborhood aggregation function:

[0082]

[0083] in, represents the feature vector of node i in layer l+1, Concat represents the concatenation operation, ELU represents the activation function, and U k,l represents the weight matrix of the kth attention head in layer l, k = 1, 2, ..., K, and K represents the total number of attention heads.

[0084] S405: Based on the updated symptom nodes, calculate the degree centrality and betweenness centrality respectively, and determine the core symptoms and bridge symptoms:

[0085] CoreSymptoms={i|DegreeCentrality(i)>θ}

[0086] BridgeSymptoms={i|Betweenness(i)>θ′}

[0087] Among them, CoreSymptoms represents the set of core symptoms, DegreeCentrality(i) represents the degree centrality of node i, θ represents the core symptom threshold, BridgeSymptoms represents the set of bridge symptoms, Betweenness(i) represents the betweenness centrality of node i, and θ′ represents the bridge symptom threshold.

[0088] It should be noted that the introduction of the graph attention mechanism enables more precise analysis, automatically focusing on the most important parts of the symptom network, improving overall management efficiency and treatment accuracy. This makes chronic disease symptom management not only more personalized, but also more scientific and efficient.

[0089] S5: Based on the relationship between core symptoms and bridge symptoms, a dynamic symptom network based on the cross-lagged network model was constructed.

[0090] Among them, the cross-lagged network model is a dynamic model used to study the relationship between symptoms at different time steps. The dynamic symptom network refers to the mutual connection and evolution of symptoms over time. Based on the cross-lagged network model, it can reflect the changing trend of symptoms over time.

[0091] It's important to note that constructing a dynamic symptom network based on a cross-lagged network model can reveal how symptoms change over time and how they interact. Compared to static analysis, this approach captures the evolution of symptoms and the causal relationships between them, providing a more dynamic and real-time analysis for symptom management of chronic diseases. By identifying core and bridge symptoms, physicians can more accurately understand the dynamics and impact pathways between symptoms, enabling timely interventions.

[0092] In one possible implementation, the dynamic symptom network based on the cross-lagged network model is specifically:

[0093]

[0094] in, represents the feature vector of node i in layer l-1, It represents the feature vector of node j in the l-1 layer, and edgefeatures represents the edge features.

[0095] It should be noted that dynamic symptom networks can help develop personalized treatment plans for patients, predict future development trends of diseases, and improve the treatment effects of chronic diseases and the quality of life of patients.

[0096] S6: Introduce influencing factors into the dynamic symptom network, and conduct subgroup analysis of the dynamic symptom network based on the relationship between influencing factors and symptoms to identify the core influencing factors that lead to differences in the symptom network structure.

[0097] Among them, influencing factors refer to external or internal factors that may have a significant impact on the symptom network and its structure, such as the patient's lifestyle, eating habits, environmental factors, psychological state, etc. Subgroup analysis refers to dividing patients into different subgroups (such as severity of illness, age group, etc.) according to certain characteristics or conditions, and analyzing these subgroups separately to reveal the differences in symptom networks among different groups. Symptom network structure differences refer to the possible differences in the relationship between symptoms and network structure in different patient groups. These differences may be related to the course of the disease, the individual characteristics of the patients or external factors.

[0098] It should be noted that by introducing influencing factors and conducting subgroup analysis, it is possible to identify the core factors that influence differences in symptom network structure. This method can deeply explore the characteristics of different patient groups and reveal the impact of individual differences on symptom networks, making symptom management more personalized and refined.

[0099] In a possible implementation, S6 specifically includes:

[0100] S601: Introducing influencing factors into node features of the dynamic symptom network through feature splicing.

[0101] S602: Update node features.

[0102] S603: Divide the updated node features into multiple subgroups.

[0103] S604: Analyze each subgroup and identify multiple different patient populations:

[0104]

[0105] Among them, Group k represents the patient population in group k, Indicates the influencing factors of the lth layer, G k Represents the condition set of the kth group.

[0106] S605: Calculate the differences in symptom network structures among subgroups and identify core influencing factors:

[0107]

[0108] Among them, Difference(G k ,G l ) represents the symptom network G of group k k and the symptom network G of group l l The difference measure between k Represents the number of nodes in the symptom network of group k.

[0109] It's important to note that considering multiple factors, such as a patient's lifestyle and psychological state, can help doctors identify potential risk factors and provide more precise treatment and intervention plans for different patient groups. Furthermore, subgroup analysis can reveal differences in symptom presentation and network structure across different patient groups, further optimizing chronic disease management and improving treatment outcomes.

[0110] S7: Based on the core influencing factors, construct a chronic disease development trend prediction model based on LSTM.

[0111] Among them, LSTM (Long Short-Term Memory Network) is a special recursive neural network (RNN) that can process and predict time series data. The chronic disease development trend prediction model refers to a model based on the LSTM model that predicts the future symptom change trend of chronic diseases by learning historical symptom data.

[0112] S8: Collect real-time clinical symptom data and real-time clinical indicator data of patients with chronic diseases.

[0113] Among them, clinical symptom data refers to the various clinical symptoms exhibited by patients during the course of the disease, such as pain, fatigue, and difficulty breathing. These symptoms reflect changes in the patient's health status and are an important basis for disease management and prediction. Clinical indicator data refers to data obtained through medical examinations and tests, such as blood pressure, blood sugar levels, electrocardiograms, etc., which provide specific information on the patient's physiological state and help doctors diagnose and assess the severity of the disease.

[0114] It's important to note that collecting data on patients' clinical symptoms and clinical indicators provides a comprehensive information foundation for symptom management of chronic diseases. This ensures accurate input data for symptom management systems, helping doctors gain a more comprehensive understanding of their patients' health status. Combining symptom data with clinical indicator data allows for a multi-faceted and comprehensive assessment of a patient's condition, enabling more scientific and personalized treatment decisions.

[0115] S9: Extract real-time core influencing factors from real-time clinical symptom data and real-time clinical indicator data.

[0116] S10: Input the real-time core influencing factors into the chronic disease development trend prediction model to predict and output the chronic disease symptom development results of chronic disease patients.

[0117] Among them, the results of chronic disease symptom development refer to the results of future symptom changes or disease development of patients based on the output of the LSTM prediction model, which helps doctors judge the development trend of the disease and provides a basis for adjusting the treatment plan.

[0118] It should be noted that through the training and prediction of the LSTM model, the development results of patients' chronic disease symptoms are output, providing a scientific basis for personalized treatment and long-term management.

[0119] In a possible implementation, S10 specifically includes:

[0120] S1001: Smoothing the core influencing factors to obtain the time parameter vector:

[0121]

[0122] Among them, p Δt-1:t represents the time parameter vector from time step t-1 to time step t, Δ t-1:t Represents the time interval from time step t-1 to time step t.

[0123] It's important to note that a time parameter vector is a vector used to represent the changes between time steps in time series data. In the LSTM model, the time parameter vector reflects the changes between different time points, helping the model capture the dynamic characteristics of symptom evolution over time.

[0124] S1002: Input the time parameter vector into the chronic disease development trend prediction model for training until the loss function value is less than the preset loss function value:

[0125]

[0126] Among them, f t represents the output of the forget gate at time step t, σ represents the Sigmoid activation function, and h t-1 represents the hidden state at time step t-1, x t represents the input at time step t, P f represents the weight parameter of the forget gate, b f Represents the bias term of the forget gate, W f represents the weight matrix of the forget gate, represents the candidate memory unit at time step t, tanh represents the hyperbolic tangent activation function, b c represents the bias term of the candidate memory unit, C t Represents the memory unit at time step t, i t represents the output of the input gate, h t represents the hidden state output at time step t, ⊙ represents the element-by-element multiplication operation, o t Represents the output of the output gate.

[0127] S1003: Output the chronic disease symptom development results of chronic disease patients.

[0128] Among them, during the machine learning model training process, the loss function is used to measure the difference between the model's predicted results and the actual results.

[0129] Among them, those skilled in the art can set the size of the preset loss function value according to actual conditions, and the present invention does not limit it.

[0130] It's important to note that by training the LSTM model, the system can capture the temporal evolution of symptoms based on historical symptom data and predict future symptom changes. This allows chronic disease management to not only rely on current symptoms but also identify potential disease trends in advance, providing doctors with forward-looking treatment guidance. By optimizing the loss function, the model can continuously improve prediction accuracy, further enhancing the effectiveness of personalized treatment.

[0131] In one possible implementation, the loss function value is calculated as follows:

[0132]

[0133] Among them, loss represents the loss function value, α represents the hyperparameter, and T represents the total number of time steps. represents the predicted value at time step t, y (t) represents the actual label at time step t, represents the loss function value at time step t, C represents the number of classification labels, and y i represents the actual value of the i-th category, Represents the predicted value of the i-th category.

[0134] Among them, methods based on time series prediction can help doctors make more scientific decisions and adjust treatment plans in a timely manner, thereby effectively managing chronic diseases and improving patients' long-term health status.

[0135] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0136] In an embodiment of the present invention, symptom data from patients with chronic diseases is collected to provide real input for subsequent analysis. Symptom clusters are extracted based on principal component analysis and maximum variance orthogonal rotation. Subsequently, a symptom network is constructed with symptoms as nodes and relationships between symptoms as edges. Concurrent network analysis is used to identify core symptoms and bridge symptoms in the symptom network. Based on the relationships between core symptoms and bridge symptoms, a dynamic symptom network based on a cross-lagged network model is constructed. This allows symptom management to not only be limited to static analysis but also capture the evolution of symptoms over time. Furthermore, influencing factors are introduced into the dynamic symptom network, and subgroup analysis is performed on the dynamic symptom network to identify the core influencing factors that lead to differences in the symptom network structure. Based on these core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed, thereby providing forward-looking guidance for treatment. Finally, by collecting clinical symptom data and clinical indicator data from patients and extracting core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed to predict and output the chronic disease symptom development outcomes of chronic disease patients, providing a scientific basis for personalized treatment and long-term management. By analyzing the relationships and interactions between the symptoms of chronic patients, the present invention can effectively manage and treat the symptoms of patients with chronic diseases, help doctors and patients identify core symptoms and potential influencing factors, improve the treatment effect and quality of life of chronic patients, and provide personalized symptom management plans for each patient's unique situation.

[0137] Reference Manual Figure 2 , showing a structural schematic diagram of a chronic patient symptom management system based on symptom network analysis provided by the present invention.

[0138] The present invention further provides a chronic patient symptom management system 20 based on symptom network analysis, which is applied to the above-mentioned chronic patient symptom management method based on symptom network analysis, comprising:

[0139] Processor 201.

[0140] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201 , the method for managing symptoms of chronic patients based on symptom network analysis as described in the method embodiment is implemented.

[0141] The chronic patient symptom management system 20 based on symptom network analysis provided by the present invention can execute the above-mentioned chronic patient symptom management method based on symptom network analysis and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate on it.

[0142] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0143] In an embodiment of the present invention, symptom data from patients with chronic diseases is collected to provide real input for subsequent analysis. Symptom clusters are extracted based on principal component analysis and maximum variance orthogonal rotation. Subsequently, a symptom network is constructed with symptoms as nodes and relationships between symptoms as edges. Concurrent network analysis is used to identify core symptoms and bridge symptoms in the symptom network. Based on the relationships between core symptoms and bridge symptoms, a dynamic symptom network based on a cross-lagged network model is constructed. This allows symptom management to not only be limited to static analysis but also capture the evolution of symptoms over time. Furthermore, influencing factors are introduced into the dynamic symptom network, and subgroup analysis is performed on the dynamic symptom network to identify the core influencing factors that lead to differences in the symptom network structure. Based on these core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed, thereby providing forward-looking guidance for treatment. Finally, by collecting clinical symptom data and clinical indicator data from patients and extracting core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed to predict and output the chronic disease symptom development outcomes of chronic disease patients, providing a scientific basis for personalized treatment and long-term management. By analyzing the relationships and interactions between the symptoms of chronic patients, the present invention can effectively manage and treat the symptoms of patients with chronic diseases, help doctors and patients identify core symptoms and potential influencing factors, improve the treatment effect and quality of life of chronic patients, and provide personalized symptom management plans for each patient's unique situation.

[0144] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0145] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0146] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function according to the embodiments of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (such as floppy disks, hard disks, tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0147] It should be understood that the term "and / or" as used herein simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the preceding and following related objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0148] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0149] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0150] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0151] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0152] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0153] Units described as separate components may or may not be physically separate, and 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.

[0154] In addition, each functional unit in each embodiment of the present invention 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.

[0155] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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, server, or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0156] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for managing symptoms of chronic patients based on symptom network analysis as described in the method embodiment is implemented.

[0157] The computer-readable storage medium provided by the present invention can implement the steps and effects of the chronic patient symptom management method based on symptom network analysis of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0158] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0159] In an embodiment of the present invention, symptom data from patients with chronic diseases is collected to provide real input for subsequent analysis. Symptom clusters are extracted based on principal component analysis and maximum variance orthogonal rotation. Subsequently, a symptom network is constructed with symptoms as nodes and relationships between symptoms as edges. Concurrent network analysis is used to identify core symptoms and bridge symptoms in the symptom network. Based on the relationships between core symptoms and bridge symptoms, a dynamic symptom network based on a cross-lagged network model is constructed. This allows symptom management to not only be limited to static analysis but also capture the evolution of symptoms over time. Furthermore, influencing factors are introduced into the dynamic symptom network, and subgroup analysis is performed on the dynamic symptom network to identify the core influencing factors that lead to differences in the symptom network structure. Based on these core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed, thereby providing forward-looking guidance for treatment. Finally, by collecting clinical symptom data and clinical indicator data from patients and extracting core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed to predict and output the chronic disease symptom development outcomes of chronic disease patients, providing a scientific basis for personalized treatment and long-term management. By analyzing the relationships and interactions between the symptoms of chronic patients, the present invention can effectively manage and treat the symptoms of patients with chronic diseases, help doctors and patients identify core symptoms and potential influencing factors, improve the treatment effect and quality of life of chronic patients, and provide personalized symptom management plans for each patient's unique situation.

[0160] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0161] There are a few points to note:

[0162] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0163] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or intervening elements may be present.

[0164] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0165] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for symptom management of chronic patients based on symptom network analysis, characterized in that: include: S1: Collect symptom data of patients with chronic diseases and obtain a symptom assessment dataset for patients with chronic diseases; S2: extracting symptom clusters from the symptom assessment dataset of patients with chronic diseases by combining principal component analysis and varimax orthogonal rotation, where the symptom clusters include multiple symptoms; S3: construct a symptom network with each symptom as a node and the relationship between symptoms as an edge; S4: Using a concurrent network analysis algorithm, identify the core symptoms and bridge symptoms in the symptom network; S4 specifically includes: S401: converting node features and edge features into hidden features through linear projection, and inputting the hidden features into the GAT model; S402: calculating the attention weight of each symptom node through the graph attention mechanism of the GAT model; S403: normalizing the attention weight; S404: updating the symptom node according to the normalized attention weight by introducing asymmetry in the neighborhood aggregation function; S405: calculating the degree centrality and betweenness centrality according to the updated symptom node, and determining the core symptom and the bridge symptom; S5: Based on the relationship between the core symptoms and the bridge symptoms, construct a dynamic symptom network based on a cross-lagged network model; S6: Introducing influencing factors into the dynamic symptom network, and based on the relationship between the influencing factors and symptoms, performing subgroup analysis on the dynamic symptom network to identify the core influencing factors that lead to differences in the symptom network structure; wherein influencing factors refer to external or internal factors that affect the symptom network and its structure, including: the patient's lifestyle, dietary habits, environmental factors, and psychological state; S7: Based on the core influencing factors, a chronic disease development trend prediction model based on LSTM is constructed; S8: Collect real-time clinical symptom data and real-time clinical indicator data of patients with chronic diseases; S9: extracting real-time core influencing factors from the real-time clinical symptom data and the real-time clinical indicator data; S10: Inputting the real-time core influencing factors into the chronic disease development trend prediction model to predict and output the chronic disease symptom development results of the chronic disease patient.

2. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 1, characterized in that: The chronic disease patient symptom assessment dataset specifically includes: symptom information, clinical data and patient personal information.

3. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 1, characterized in that: The S2 specifically includes: S201: performing standardization processing on the symptom assessment dataset of the chronic disease patients; S202: Calculating the covariance matrix of the standardized data set based on the principal component analysis method; S203: Calculating the eigenvalues ​​and eigenvectors of the covariance matrix; S204: selecting a principal component according to the magnitude of the eigenvalue; S205: Calculate the weight of the principal component and determine the eigenvector to be rotated; S206: Rotating the feature vector to be rotated by using the maximum variance orthogonal rotation method; S207: Determine the factor loading matrix with the goal of maximizing the rotation target; S208: Determine the symptom cluster according to the factor loading matrix.

4. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 1, characterized in that: The S405 specifically further includes: CoreSymptoms={i|DegreeCentrality(i)>θ} BridgeSymptoms={i|Betweenness(i)>θ′} Among them, CoreSymptoms represents the set of core symptoms, DegreeCentrality(i) represents the degree centrality of node i, θ represents the core symptom threshold, BridgeSymptoms represents the set of bridge symptoms, Betweenness(i) represents the betweenness centrality of node i, and θ′ represents the bridge symptom threshold.

5. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 1, characterized in that: The dynamic symptom network based on the cross-lagged network model is specifically: ； in, represents the feature vector of node i in layer l-1, It represents the feature vector of node j in the l-1 layer, and edgefeatures represents the edge features.

6. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 1, characterized in that: The S6 specifically includes: S601: Introducing the influencing factors into the node features of the dynamic symptom network by feature splicing; S602: Update the node features; S603: Divide the updated node features into multiple subgroups; S604: Analyze each of the subgroups to identify multiple patient groups; S605: Calculate the differences between the symptom network structures of each of the subgroups and identify the core influencing factors.

7. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 6, characterized in that: The S10 specifically includes: S1001: Smoothing the core influencing factors to obtain a time parameter vector; S1002: Inputting the time parameter vector into the chronic disease development trend prediction model for training until the loss function value is less than a preset loss function value; S1003: Output the chronic disease symptom development result of the chronic disease patient.

8. The method for managing symptoms of chronic patients based on symptom network analysis according to claim 7, characterized in that: The calculation formula of the loss function value is specifically: ； Among them, loss represents the loss function value, α represents the hyperparameter, and T represents the total number of time steps. represents the predicted value at time step t, y (t) represents the actual label at time step t, represents the loss function value at time step t, C represents the number of classification labels, and y i represents the actual value of the i-th category, Represents the predicted value of the i-th category.

9. A chronic patient symptom management system based on symptom network analysis, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for managing symptoms of chronic patients based on symptom network analysis according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for managing symptoms of chronic patients based on symptom network analysis according to any one of claims 1 to 8 is implemented.

Images