Construction method, device and equipment of disease treatment process knowledge base

Abstract

The invention relates to the technical field of medical information, in particular to a disease treatment process knowledge base construction method, device and equipment, and the method comprises the steps: collecting multi-dimensional diagnosis and treatment data of historical patients; based on the multi-dimensional diagnosis and treatment data, determining multi-dimensional features of historical patients; determining a potential association rule and a causal relationship between the features based on the multi-dimensional features; on the basis of potential association rules and causal relationships among the features, a disease treatment process knowledge base is formed, various diagnosis data of historical patients are analyzed, a knowledge base with a close association degree is established for various diagnosis data, and then intelligent treatment path recommendation can be realized on the basis of the knowledge base. Therefore, the treatment accuracy and the individuation level are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a method, device and equipment for constructing a disease treatment process knowledge base. Background Art

[0002] With the continuous advancement of medical information technology, hospitals and medical institutions have accumulated a large amount of historical patient medical records, including vital signs, laboratory test results, and imaging data. This data contains rich clinical knowledge and provides an important basis for optimizing disease treatment pathways. However, current treatment processes still rely on manual editing and lack the ability to dynamically optimize and update based on individual patient characteristics, resulting in treatment plans that cannot fully utilize the advantages of data-driven development.

[0003] Traditional disease treatment pathways are mostly manually developed by experts based on experience and clinical guidelines, and lack data-based intelligent analysis and automatic optimization capabilities. In addition, due to real-time changes in the patient's condition during treatment, most existing treatment pathways are difficult to update in a timely manner, and optimal treatment cannot be achieved.

[0004] Therefore, how to provide the best recommendation basis for intelligent treatment pathways is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method, device and equipment for constructing a disease treatment process knowledge base that overcomes the above problems or at least partially solves the above problems.

[0006] In a first aspect, the present invention provides a method for constructing a disease treatment process knowledge base, comprising: Collect multi-dimensional diagnosis and treatment data of historical patients; Determining multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; Based on the multidimensional features, determining potential association rules and causal relationships between the features; Based on the potential association rules and causal relationships between various features, a knowledge base of disease treatment processes is formed.

[0007] Preferably, the acquisition of multi-dimensional diagnosis and treatment data of historical patients includes: Through the hospital information system, electronic medical record system and laboratory data management system, we collect historical patients' basic information, medical history, clinical examination data, imaging data, laboratory test results, treatment plans and their multi-dimensional diagnosis and treatment data.

[0008] Preferably, based on the multidimensional diagnosis and treatment data, determining the multidimensional characteristics of historical patients includes: Based on the multidimensional diagnosis and treatment data, a clustering algorithm is used to classify the multidimensional diagnosis and treatment data with the disease type as the cluster center to obtain a classification result; Based on the classification results, any of the following algorithms is used to screen out features that have imaging power for the treatment process of the target disease: Information gain algorithm, variance selection algorithm and L1 regularization algorithm.

[0009] Preferably, based on the multidimensional features, determining the potential association rules and causal relationships between the features includes: Based on the multidimensional features, determining the association relationship between the features through graph construction and relationship mining; Based on the association relationship, determining potential association rules between the features; Based on the association rules, the causal relationship between the features is determined.

[0010] Preferably, based on the multidimensional features, determining the association relationship between the features through graph construction and relationship mining includes: Based on the multidimensional features, a graph algorithm is used to evaluate the importance of each feature; Through relationship mining and the importance of each feature, the correlation between the features is determined.

[0011] Preferably, based on the association relationship, determining potential association rules between the features includes: Based on the association relationship, a candidate feature item set is generated, where the candidate feature item set is a feature combination related to the disease type or the treatment plan; Based on the candidate feature item sets and the corresponding diseases, as well as the candidate feature item sets and the corresponding treatment plans, calculating the support of each candidate feature item set; Determining a target feature item set based on the support, wherein the support of the target feature item set is greater than a minimum support threshold; Based on the target feature item set, potential association rules between the features are determined.

[0012] Preferably, determining the causal relationship between the features based on the association rules includes: Based on the association rules, a causal graph is constructed, wherein the causal graph includes each node and an edge between nodes, wherein the node corresponds to a feature or a variable of the feature, and the edge corresponds to a causal relationship between features, between variables, or between a variable and a feature; Based on the causal graph, the optimal causal relationship between the features is determined.

[0013] Preferably, after forming a disease treatment process knowledge base based on the potential association rules and causal relationships between the features, the following is also included: Optimize and expand the knowledge base of the treatment process for the aforementioned diseases.

[0014] In a second aspect, the present invention further provides a device for constructing a disease treatment process knowledge base, comprising: The acquisition module is used to collect multi-dimensional diagnosis and treatment data of historical patients; A first determination module is used to determine the multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; A second determination module is used to determine potential association rules and causal relationships between the features based on the multi-dimensional features; A module is formed to form a disease treatment process knowledge base based on the potential association rules and causal relationships between various features.

[0015] In a third aspect, the present invention further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0016] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the method described in the first aspect when the program is executed by a processor.

[0017] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages: The present invention provides a method for constructing a disease treatment process knowledge base, including: collecting multidimensional diagnosis and treatment data of historical patients; determining multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; determining potential association rules and causal relationships between each characteristic based on the multidimensional characteristics; forming a disease treatment process knowledge base based on the potential association rules and causal relationships between each characteristic, by analyzing various diagnostic data of historical patients, establishing a knowledge base with a close correlation degree for various diagnostic data, and then realizing intelligent treatment path recommendation based on the knowledge base to improve the accuracy and personalization of treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. Throughout the drawings, the same reference figures denote the same components. In the drawings: Figure 1 A schematic diagram showing the steps of a method for constructing a disease treatment process knowledge base in an embodiment of the present invention is shown; Figure 2 A schematic diagram showing the structure of a device for constructing a disease treatment process knowledge base according to an embodiment of the present invention is shown; Figure 3 A schematic diagram of the structure of a computer device for implementing a method for constructing a disease treatment process knowledge base in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0020] Example 1: The embodiment of the present invention provides a method for constructing a disease treatment process knowledge base, such as Figure 1 Shown, including:

[0021] S101, collect multi-dimensional diagnosis and treatment data of historical patients; S102, determining the multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; S103, based on the multi-dimensional features, determining the potential association rules and causal relationships between the features; S104: Based on the potential association rules and causal relationships between the features, a disease treatment process knowledge base is formed.

[0022] First, building a knowledge base requires a large amount of basic data, which can be historical data of historical patients. Therefore, S101 specifically includes: Multidimensional diagnostic and treatment data including historical patients' basic information, medical history, clinical examination data, imaging data, laboratory test results, treatment plans and their efficacy are collected through the Hospital Information System (HIS), Electronic Medical Record (EMR) and Laboratory Data Management System (LIS).

[0023] Electronic medical records contain basic patient information, including gender, age, address, workplace, and allergy history. They also include medical records, including outpatient and inpatient visits. Hospital information systems contain patient clinical notes. Laboratory data management systems record laboratory test results. Data across these different systems can be linked using a patient's unique identifier, such as their ID number.

[0024] Next, S102 is executed to determine the multidimensional features of the historical patients based on the multidimensional diagnosis and treatment data.

[0025] First, preprocess the multidimensional diagnosis and treatment data, including data cleaning, missing value filling and standardization. Among them, missing value filling is performed in the following way: ; in, Any dimension diagnosis and treatment data The filling value of is the diagnosis and treatment data of sample j in any dimension The value on , N is the number of samples.

[0026] Next, after filling in the missing values, standardization is performed, specifically using Z-score standardization: ; in, For any medical data The value of For any medical data The mean of For any medical data The standard deviation of .

[0027] After standardization, screening is performed to select the features that are most imaging for the disease process.

[0028] Specifically, based on the multidimensional diagnosis and treatment data, a clustering algorithm is used to classify the multidimensional diagnosis and treatment data with the disease type as the cluster center to obtain the classification results; Based on the classification results, use any of the following algorithms to screen out features that have imaging power for the treatment process of the target disease: Information gain algorithm, variance selection algorithm and L1 regularization algorithm.

[0029] When classifying, based on the relationship between the disease and the diagnosis and treatment plan, the characteristics related to the disease are divided into one category. Assuming that the K-means clustering algorithm is used to obtain K cluster centers, the solution goal is: ; in, is the objective function, For the Cluster centers, For any feature sample, is the Euclidean distance between the feature sample and the cluster center, For the clusters.

[0030] The final classification result is determined through continuous iteration. Of course, the classification can also be performed according to other classification standards, which are not limited here.

[0031] Next, using the information gain algorithm as an example, by calculating the contribution of each diagnosis and treatment data to the classification results, we can screen out features that have an impact on the treatment process of the target disease. The specific calculation formula is as follows: ; in, is the entropy of any classification result dataset D, For any feature A The subset of value pairs, is the number of samples in the subset, The imaging power of feature A on the treatment process of the target disease.

[0032] By calculating the influence, we can screen out the features with high influence and determine the multidimensional characteristics of historical patients.

[0033] Next, S103 is executed to determine the potential association rules and causal relationships between the features based on the multi-dimensional features.

[0034] Specifically, based on multidimensional features, the correlation between features is determined through graph construction and relationship mining; Based on the association relationship, determine the potential association rules between each feature; Based on association rules, the causal relationship between features is determined.

[0035] In S103 , the association relationship between each feature is first determined. Specifically, based on multidimensional features, a graph algorithm is used to evaluate the importance of each feature. Then, the association relationship between each feature is determined through relationship mining and the importance of each feature.

[0036] The features include age, gender, and treatment methods, which are represented by nodes, and edges represent the relationships between them.

[0037] For example, hypertension and overweight are connected by an edge, indicating that being overweight increases the risk of hypertension; diabetes and hypertension are also connected by an edge, indicating that diabetics are more likely to develop hypertension; diabetes and insulin are connected by an edge, indicating that diabetics need insulin to control their blood sugar. These are conventional associations, specifically associations established between any two features, or three or more features.

[0038] Next, the importance of nodes with different features is evaluated through the graph algorithm (PageRank) to screen out some features with low importance and improve processing efficiency. The specific calculation formula for evaluating the importance of nodes with different features using the graph algorithm (PageRank) is as follows: ; in, For nodes The importance ranking of is the regulating factor, For nodes The in-degree, For nodes The out-degree.

[0039] Based on the importance ranking of the nodes with different features, the correlation relationship of each feature is determined.

[0040] After determining the association relationships between the features, potential association rules between the features are determined based on the association relationships.

[0041] Specifically, based on the association relationship, a candidate feature item set is generated, and the candidate feature item set is a feature combination related to the disease type or treatment plan; Based on the candidate feature item sets and the corresponding diseases, as well as the candidate feature item sets and the corresponding treatment methods, the support of each candidate feature item set is calculated; Based on the support, the target feature item set is determined, and the support of the target feature item set is greater than the minimum support threshold; Based on the target feature item set, the potential association rules between the features are determined.

[0042] For example, based on these data, we found frequent occurrence patterns of some features (such as "high blood sugar") and certain treatment paths (such as insulin treatment), so that these association rules can help us understand which features and treatment plans have strong regularities.

[0043] Therefore, first, based on the disease type and the correlation relationship, or the treatment plan and the correlation relationship, the features related to the disease type or the features related to the treatment plan are divided into multiple candidate feature item sets. These candidate feature item sets contain the same features but in different combinations. Then, the support of each candidate feature item set is calculated, (Y1, Y2, ..., Y m ), the support is the ratio of the number of occurrences of each candidate feature item set to the total number of diseases. When the support is greater than the minimum support threshold, it is determined as the target feature item set, that is, S (Y1, Y2, ..., Y m )>min_support, thus obtaining the potential association rules between each feature.

[0044] Next, the causal relationships between features are determined. Specifically, based on association rules, a causal graph is constructed. This graph includes each node and the edges between them. Nodes correspond to features or feature variables, and edges correspond to causal relationships between features, between variables, or between variables and features. Based on the causal graph, the optimal causal relationship between features is determined.

[0045] For example, increased body temperature may directly affect the choice of drug treatment options.

[0046] Specifically, we use known data to learn parameters and determine the optimal causal model according to the following calculation process: ; in, is the direct causal parent node, is the conditional probability, is the optimal causal relationship combination, All are characteristics.

[0047] After determining the potential association rules and causal relationships between the features, S104 is executed to form a disease treatment process knowledge base based on the potential association rules and causal relationships between the features.

[0048] The core of this knowledge base is to efficiently store the relationship between different diseases and treatment plans to support fast query, update and reasoning. Therefore, the knowledge base is designed as a multi-layer structure, including a patient information table: a disease treatment plan table and an association table. The patient information table is used to store the basic information and other characteristics of historical patients; the disease treatment plan table is used to store the treatment plans corresponding to different diseases; the association table is used to record the relationship between features and treatment plans, including information such as rule support and confidence.

[0049] Every additional feature and treatment plan and other related content will be automatically identified and added through the knowledge base to continuously improve the knowledge base.

[0050] After S104, the process also includes optimizing and expanding the disease treatment process knowledge base. To ensure the efficiency of the knowledge base, data storage structure can be optimized through data deduplication and compression algorithms to reduce redundant data and improve query speed.

[0051] The expansion method is to expand the knowledge base by introducing new feature algorithms when there are new treatment plans or diseases. For example, new machine learning models can be used to predict and optimize the treatment paths of new diseases.

[0052] With the continuous optimization and expansion of the knowledge base of the treatment process for this disease, it can gradually adapt to the development of time and gradually improve, so as to make effective recommendations for subsequent treatment paths.

[0053] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages: The present invention provides a method for constructing a disease treatment process knowledge base, including: collecting multidimensional diagnosis and treatment data of historical patients; determining multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; determining potential association rules and causal relationships between each characteristic based on the multidimensional characteristics; forming a disease treatment process knowledge base based on the potential association rules and causal relationships between each characteristic, by analyzing various diagnostic data of historical patients, establishing a knowledge base with a close correlation degree for various diagnostic data, and then realizing intelligent treatment path recommendation based on the knowledge base to improve the accuracy and personalization of treatment.

[0054] Example 2: Based on the same inventive concept, the present invention also provides a device for constructing a disease treatment process knowledge base, such as Figure 2 Shown, including: The acquisition module 201 is used to collect multi-dimensional diagnosis and treatment data of historical patients; A first determination module 202 is configured to determine multidimensional features of historical patients based on the multidimensional diagnosis and treatment data; A second determination module 203 is configured to determine potential association rules and causal relationships between the features based on the multi-dimensional features; The forming module 204 is used to form a disease treatment process knowledge base based on the potential association rules and causal relationships between the various features.

[0055] In an optional implementation, the acquisition module 201 is configured to: Through the hospital information system, electronic medical record system and laboratory data management system, we collect historical patients' basic information, medical history, clinical examination data, imaging data, laboratory test results, treatment plans and their multi-dimensional diagnosis and treatment data.

[0056] In an optional implementation, the first determining module 202 is configured to: Based on the multidimensional diagnosis and treatment data, a clustering algorithm is used to classify the multidimensional diagnosis and treatment data with the disease type as the cluster center to obtain a classification result; Based on the classification results, any of the following algorithms is used to screen out features that have imaging power for the treatment process of the target disease: Information gain algorithm, variance selection algorithm and L1 regularization algorithm.

[0057] In an optional implementation, the second determining module 203 is configured to: Based on the multidimensional features, determining the association relationship between the features through graph construction and relationship mining; Based on the association relationship, determining potential association rules between the features; Based on the association rules, the causal relationship between the features is determined.

[0058] In an optional implementation, the second determining module 203 is configured to: Based on the multidimensional features, a graph algorithm is used to evaluate the importance of each feature; Through relationship mining and the importance of each feature, the correlation between the features is determined.

[0059] In an optional implementation, the second determining module 203 is configured to: Based on the association relationship, a candidate feature item set is generated, where the candidate feature item set is a feature combination related to the disease type or the treatment plan; Based on the candidate feature item sets and the corresponding diseases, as well as the candidate feature item sets and the corresponding treatment plans, calculating the support of each candidate feature item set; Determining a target feature item set based on the support, wherein the support of the target feature item set is greater than a minimum support threshold; Based on the target feature item set, potential association rules between the features are determined.

[0060] In an optional implementation, the second determining module 203 is configured to: Based on the association rules, a causal graph is constructed, wherein the causal graph includes each node and an edge between nodes, wherein the node corresponds to a feature or a variable of the feature, and the edge corresponds to a causal relationship between features, between variables, or between a variable and a feature; Based on the causal graph, the optimal causal relationship between the features is determined.

[0061] In an optional embodiment, the system further includes an optimization and expansion module for: Optimize and expand the knowledge base of the treatment process for the aforementioned diseases.

[0062] Example 3: Based on the same inventive concept, an embodiment of the present invention provides a computer device, such as Figure 3 As shown, it includes a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302. When the processor 302 executes the program, the steps of the method for constructing the above-mentioned disease treatment process knowledge base are implemented.

[0063] Among them, Figure 3In the present invention, a bus architecture (represented by bus 300) is shown. Bus 300 may include any number of interconnected buses and bridges. Bus 300 links various circuits, including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits, such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and, therefore, will not be described further herein. Bus interface 306 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same component, namely a transceiver, which provides a means for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0064] Example 4: Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for constructing the above-mentioned disease treatment process knowledge base are implemented.

[0065] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages can be utilized to realize the content of the present invention described herein, and the above description of specific languages is for the purpose of disclosing the best mode of the present invention.

[0066] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0067] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than those explicitly recited in each embodiment. Rather, as reflected in each embodiment, inventive aspects lie in fewer than all the features of the individual embodiments previously disclosed. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0068] Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively modified and installed in one or more devices different from the embodiments. The modules, units, or components in the embodiments can be combined into a single module, unit, or component, and furthermore, they can be divided into multiple sub-modules, sub-units, or sub-components. All features disclosed in this specification (including the accompanying claims, abstract, and drawings), and all processes or units of any method or device disclosed therein, can be combined in any combination, unless at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0069] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in a specific embodiment, any one of the claimed embodiments may be used in any combination.

[0070] The various component embodiments of the present invention can be implemented in hardware, as software modules running on one or more processors, or as a combination thereof. Those skilled in the art will appreciate that, in practice, a microprocessor or digital signal processor (DSP) can be used to implement some or all of the functions of some or all of the components of the apparatus for constructing a disease treatment process knowledge base and a computer device according to embodiments of the present invention. The present invention can also be implemented as an apparatus or device program (e.g., a computer program or computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium or in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0071] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for constructing a disease treatment process knowledge base, characterized in that: include: Collect multi-dimensional diagnosis and treatment data of historical patients; Determining multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; Based on the multidimensional features, determining potential association rules and causal relationships between the features; Based on the potential association rules and causal relationships between various features, a knowledge base of disease treatment processes is formed.

2. The method according to claim 1, wherein The multi-dimensional diagnosis and treatment data of historical patients are collected, including: Through the hospital information system, electronic medical record system and laboratory data management system, we collect historical patients' basic information, medical history, clinical examination data, imaging data, laboratory test results, treatment plans and their multi-dimensional diagnosis and treatment data.

3. The method according to claim 1, wherein Based on the multidimensional diagnosis and treatment data, multidimensional characteristics of historical patients are determined, including: Based on the multidimensional diagnosis and treatment data, a clustering algorithm is used to classify the multidimensional diagnosis and treatment data with the disease type as the cluster center to obtain a classification result; Based on the classification results, any of the following algorithms is used to screen out features that have imaging power for the treatment process of the target disease: Information gain algorithm, variance selection algorithm and L1 regularization algorithm.

4. The method according to claim 1, wherein Based on the multidimensional features, potential association rules and causal relationships between the features are determined, including: Based on the multidimensional features, determining the association relationship between the features through graph construction and relationship mining; Based on the association relationship, determining potential association rules between the features; Based on the association rules, the causal relationship between the features is determined.

5. The method according to claim 4, wherein Based on the multidimensional features, the association relationship between the features is determined through graph construction and relationship mining, including: Based on the multidimensional features, a graph algorithm is used to evaluate the importance of each feature; Through relationship mining and the importance of each feature, the correlation between the features is determined.

6. The method according to claim 4, wherein Based on the association relationship, potential association rules between the features are determined, including: Based on the association relationship, a candidate feature item set is generated, where the candidate feature item set is a feature combination related to the disease type or the treatment plan; Based on the candidate feature item sets and the corresponding diseases, as well as the candidate feature item sets and the corresponding treatment plans, calculating the support of each candidate feature item set; Determining a target feature item set based on the support, wherein the support of the target feature item set is greater than a minimum support threshold; Based on the target feature item set, potential association rules between the features are determined.

7. The method according to claim 4, wherein Based on the association rules, the causal relationship between the features is determined, including: Based on the association rules, a causal graph is constructed, wherein the causal graph includes each node and an edge between nodes, wherein the node corresponds to a feature or a variable of the feature, and the edge corresponds to a causal relationship between features, between variables, or between a variable and a feature; Based on the causal graph, the optimal causal relationship between the features is determined.

8. The method according to claim 1, wherein After forming a disease treatment process knowledge base based on the potential association rules and causal relationships between various features, it also includes: Optimize and expand the knowledge base of the treatment process for the aforementioned diseases.

9. A device for constructing a disease treatment process knowledge base, characterized in that: include: The acquisition module is used to collect multi-dimensional diagnosis and treatment data of historical patients; A first determination module is used to determine the multidimensional characteristics of historical patients based on the multidimensional diagnosis and treatment data; A second determination module is used to determine potential association rules and causal relationships between the features based on the multi-dimensional features; A module is formed to form a disease treatment process knowledge base based on the potential association rules and causal relationships between various features.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

Images