CN113744886B - Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining - Google Patents
Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining Download PDFInfo
- Publication number
- CN113744886B CN113744886B CN202010461494.9A CN202010461494A CN113744886B CN 113744886 B CN113744886 B CN 113744886B CN 202010461494 A CN202010461494 A CN 202010461494A CN 113744886 B CN113744886 B CN 113744886B
- Authority
- CN
- China
- Prior art keywords
- symptom
- traditional chinese
- chinese medicine
- node
- mining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003814 drug Substances 0.000 title claims abstract description 96
- 238000011282 treatment Methods 0.000 title claims abstract description 73
- 238000005065 mining Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 32
- 208000024891 symptom Diseases 0.000 claims abstract description 161
- 208000011580 syndromic disease Diseases 0.000 claims abstract description 69
- 201000010099 disease Diseases 0.000 claims abstract description 49
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 49
- 238000003745 diagnosis Methods 0.000 claims abstract description 32
- 239000000203 mixture Substances 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims description 12
- 229940126680 traditional chinese medicines Drugs 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims 4
- 230000007812 deficiency Effects 0.000 abstract 1
- 238000007418 data mining Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a method and a system for mining a traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine mining, wherein the method comprises the following steps: 1) Carrying out standardization and word segmentation processing operation on data information in a traditional Chinese medical record; the standardized processing of the data information refers to designating standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in medical records according to the Chinese word list of traditional Chinese medicine; symptoms consist of symptom attributes and symptom values, wherein the symptom attributes represent the object described by the symptoms, and the symptom values are specific manifestations of the symptom attributes; 2) Modeling the traditional Chinese medical records processed in the step 1) into a graph data structure; 3) The graph data structure is mined according to the mining conditions, and key symptom characteristics of disease diagnosis, applicable treatment rules and treatment methods, applicable formulas and traditional Chinese medicine composition are found, so that a traditional Chinese medicine dialectical treatment mode conforming to the mining conditions is formed. The invention effectively solves the problem of deficiency of key symptoms and ensures the completeness of the diagnosis and treatment mode.
Description
Technical Field
The invention relates to a method and a system for mining a traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining, and belongs to the technical field of software.
Background
The traditional Chinese medicine is the treasure of traditional Chinese national culture. Diagnosis and treatment of traditional Chinese medicine takes diagnosis theory as diagnosis basis, and diagnosis and treatment process and result depend on cognition and understanding of traditional Chinese medicine thinking and theory to a great extent and individual practical experience. Through thousands of years of practice and development, the temporary experience of famous doctors gradually deposits to be valuable wealth of Chinese medicine culture, and is an important component of Chinese medicine culture inheritance. However, the diagnosis and treatment experience of famous doctors exists in a subjective consciousness form, and is mostly hidden in each specific diagnosis and treatment medical record. How to adopt a scientific method to refine, generalize, abstract, summarize and summarize the diagnosis and treatment experience hidden in the medical records, so that the medical records are objectified, standardized and visualized, and the medical records have important significance for developing and inheriting the culture of traditional Chinese medicine.
Data mining is a data analysis technique commonly used in computer science, and aims to search data rules from large-scale data records and find potential and implicit data information. Compared with traditional mining algorithms such as classification, clustering and the like, graph data mining can model and represent more complex data structures and find more complex data association, and has become a fundamental research problem which is paid attention to the current data mining field.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention aims to provide a graph data mining-based traditional Chinese medicine dialectical treatment mode mining method and system, which utilize graph data structures to model complex logic relations among various elements such as symptoms, diseases, symptoms, treatment rules, prescriptions, traditional Chinese medicine components and the like in traditional Chinese medicine medical records, and adopts an extended frequent subgraph mining algorithm to extract key elements of the traditional Chinese medicine dialectical treatment process so as to form the traditional Chinese medicine dialectical treatment mode oriented to various diseases, symptoms and symptoms. The system can display diagnosis and treatment experience hidden in the medical records of the traditional Chinese medicine in an objectified and graphical mode of a traditional Chinese medicine diagnosis and treatment pattern diagram, is beneficial to the inheritance and development of the clinical experience of famous doctors, and has important guiding significance and application value for the research of the diagnosis and treatment theory of the traditional Chinese medicine, the intelligent auxiliary diagnosis of the traditional Chinese medicine and the like.
The technical solution of the invention is as follows: a traditional Chinese medicine dialectical treatment mode mining system based on traditional Chinese medicine mining builds a traditional Chinese medicine medical case into a dialectical treatment process diagram when the traditional Chinese medicine is in the critical state, and adopts an expanded diagram mining algorithm to extract key diagnosis and treatment information in a medical case so as to form the traditional Chinese medicine dialectical treatment modes aiming at different diseases, symptoms and symptoms. The system comprises a data preprocessing module, a data modeling module and a dialectical treatment mode mining module. Wherein:
and the data preprocessing module is used for carrying out standardization and word segmentation processing operation on data information in the traditional Chinese medical records. The data standardization process designates standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in medical records according to the Chinese medical operation word list. The word segmentation process is developed mainly for symptom information and is used for splitting complex symptom descriptions into minimum symptom description units with fine granularity. Symptoms consist of symptom attributes and symptom values. Wherein, the symptom attribute represents the object described by the symptom, such as tongue coating color, tongue coating quality, pulse condition and the like; symptom values describe the specific manifestations of symptom attributes such as dark red, thick, slippery, etc.
And the data modeling module models the traditional Chinese medical records data processed by the data preprocessing module into a graph data structure. The nodes in the graph represent symptoms, diseases, symptoms, rules, prescriptions and traditional Chinese medicine composition in the medical records, namely symptom nodes, disease nodes, syndrome nodes, rule nodes, prescription nodes and traditional Chinese medicine composition nodes. The symptom node is connected with the disease node, the syndrome node and the syndrome node by edges, which means that the symptoms described by the symptom node belong to the symptoms of the diseases, the syndrome and the syndromes described by the disease node, the syndrome node and the syndrome node connected with the symptom node. The syndrome node and the rule node, and the rule node and the prescription node are also connected by edges, which represent the rule corresponding to the syndrome and the prescription available by the rule. Edges between prescription nodes and traditional Chinese medicine composition nodes indicate that traditional Chinese medicines corresponding to the traditional Chinese medicine composition nodes are traditional Chinese medicine compositions corresponding to the prescription.
The pattern mining module adopts an extended frequent subgraph mining algorithm to mine the traditional Chinese medicine medical records with structured graph, discovers key symptom characteristics of disease diagnosis, applicable rule treatment methods, applicable prescriptions and core traditional Chinese medicine compositions, and forms traditional Chinese medicine pattern of diagnosis and treatment aiming at different diseases, syndromes and syndromes. The module comprises the following implementation steps:
1) And selecting a traditional Chinese medical records Z which accords with the mining conditions of the user from the output result of the data preprocessing module according to the mining target of the user. The mining conditions include doctor's name, and the disease, syndrome, or syndrome name to be mined. Wherein the disease name, syndrome name and syndrome name are necessary excavation conditions of three dialectical treatment modes of disease, syndrome type and syndrome type respectively; the doctor name is an optional mining condition. The user may or may not specify the doctor to mine the pattern of diagnosis and treatment of a certain disease, syndrome or syndrome.
2) And traversing all cases in the case set Z, and counting the occurrence frequency of each symptom, rule, prescription and Chinese medicine composition.
Where frequency of occurrence = number of occurrences/total number of medical records.
3) And setting a minimum support parameter according to the node type.
3.1 The three types of nodes of the disease, the syndrome and the syndrome are nodes related to the target mining of the user, and are used for specifying which disease, syndrome or syndrome the diagnosis and treatment mode mined by the user aims at. The three kinds of nodes are necessary nodes of three dialectical treatment modes respectively, and the minimum support degree parameter is not required to be set.
3.2 For the symptom nodes, sequentially acquiring symptom attributes of each symptom node, and then respectively setting minimum support parameters for each symptom attribute according to the occurrence frequency of each symptom value corresponding to the symptom attribute. The setting steps are as follows:
3.2.1 According to the occurrence frequency of each symptom value corresponding to the current symptom attribute, sequencing the symptom values from large to small to obtain a symptom value sequence L, wherein list (L) is the length of the sequence L;
3.2.2 Starting from the first element, sequentially selecting each element L (i), wherein i is more than or equal to 1 and less than or equal to list (L), and accumulating and summing the occurrence frequencies corresponding to L (i) until the accumulated frequency exceeds a preset threshold value;
3.2.3 The frequency of occurrence corresponding to the element L (i) extracted from the L last time is used as the minimum support parameter of the current symptom attribute.
3.3 For three types of nodes consisting of rules, prescriptions and traditional Chinese medicine, the minimum support parameters of the three types of nodes are respectively set according to actual application requirements.
4) And according to the medical records ID, a graph data set G (Z) corresponding to the medical records Z is screened from the output result of the data modeling module, then an expanded frequent subgraph mining algorithm is adopted to mine on the G (Z), and the obtained frequent subgraph is a traditional Chinese medicine dialectical treatment mode which consists of key elements such as symptoms, syndromes, diseases, treatment rules, prescriptions, traditional Chinese medicines and the like and can reflect the internal logic association of the key elements. The digging steps are as follows:
4.1 Selecting a corresponding minimum support parameter as a filtering condition according to the node type, adopting a frequent subgraph mining algorithm to mine on G (Z) to obtain frequent nodes and frequent edges, and sequencing the frequent edges according to the sequence of decreasing frequency and increasing DFS (depth first search) coding value;
4.2 Sequentially acquiring edges in the frequent edge set, calculating DFS codes, and constructing frequent subtrees by using the frequent edges;
4.3 For each frequent subtree, finding out all inner edges which can be connected with each frequent subtree from the frequent edge set, and adding the inner edges into the subtree to form a frequent subtree, namely, the traditional Chinese medicine dialectical treatment mode corresponding to the excavation condition.
Compared with the prior art, the invention has the advantages that:
(1) The traditional Chinese medical records are modeled into graph structures, key diagnosis and treatment information in the traditional Chinese medical records is extracted based on the concept of frequent subgraph mining, a graphical traditional Chinese medical dialectical treatment mode is formed, and the traditional Chinese medical dialectical thinking and the method are displayed in a more visual mode.
(2) The three common requirements of Chinese medicine diagnosis and treatment mining on the diagnosis and treatment modes of diseases and the diagnosis and treatment modes of symptoms and symptoms can be met; the diagnosis and treatment mode mining for the famous doctors can be realized aiming at the famous doctors of individuals.
(3) The traditional frequent subgraph mining algorithm is expanded, different minimum support parameters are set according to the types of the nodes, the flexibility of mode mining is improved, and the requirements of users on multiple mode mining requirements can be met. The method comprises the steps of setting a minimum support parameter for each symptom attribute according to the symptom attribute of the symptom node, effectively solving the problem of missing key symptoms and guaranteeing the completeness of the diagnosis and treatment mode.
Drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 shows the implementation process of the dialectical treatment mode mining module in the system of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples.
As shown in FIG. 1, the system comprises three functional modules of data preprocessing, data modeling and diagnosis and treatment mode mining.
And the data preprocessing module is used for carrying out standardization and word segmentation processing operation on data information in the traditional Chinese medical records. The data standardization process designates standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in medical records according to the Chinese medical operation word list. Standard names and aliases of common traditional Chinese medicine terms are defined in the Chinese medicine vocabulary. The Chinese terms appearing in the medical records of traditional Chinese medicine can be standardized by utilizing the Chinese word list of traditional Chinese medicine, such as the symptoms of "epigastric pressing pain", "epigastric pressing pain" and "epigastric pressing pain" can be unified and standardized as "epigastric pressing pain". The word segmentation processing is mainly developed aiming at symptom information, and is used for splitting complex symptom description into minimum symptom description units with fine granularity, for example, the symptom of deep, wiry and fine pulse can be segmented into four independent symptoms of deep, wiry, fine and fine pulse.
And the data modeling module models the traditional Chinese medical records data processed by the data preprocessing module into a graph data structure. Nodes in the graph represent symptoms, diseases, syndromes, symptoms, rules of treatment, prescriptions and traditional Chinese medicine compositions in the medical records. The side connection between the symptoms and the diseases, syndromes and syndromes means that the symptoms belong to the manifestation symptoms of the diseases, syndromes or syndromes. If there are multiple diseases, syndromes and symptoms, each symptom is connected with the multiple diseases, syndromes and symptoms respectively. The symptoms and treatment rules and the prescriptions are also connected by edges, which indicates the treatment rules corresponding to the symptoms and the prescriptions available by the treatment rules. The side between the prescription and the Chinese medicine components indicates that the Chinese medicine is a component of the prescription. If there are several symptoms, rules and prescriptions, all the symptoms, rules and prescriptions and the prescriptions are connected by full connection.
The pattern mining module adopts an extended frequent subgraph mining algorithm to mine the traditional Chinese medicine medical records with structured graph, discovers key symptom characteristics of disease diagnosis, applicable rule treatment methods, applicable prescriptions and core traditional Chinese medicine compositions, and forms traditional Chinese medicine pattern of diagnosis and treatment aiming at different diseases, syndromes and syndromes. The module implementation is shown in fig. 2. First, a set of medical records is screened according to mining conditions entered by a user. The excavation conditions include: 1) The name of the doctor, namely, the medical records of which doctor are mined; 2) "disease name", "syndrome name", i.e. which disease, syndrome or syndrome is targeted for. And then, setting different mining parameters, namely minimum support parameters, for different types of nodes in the medical record graph according to the actual mining requirements of the user. The node types capable of independently setting the minimum support parameters comprise rule nodes, prescription nodes, traditional Chinese medicine composition nodes and symptom nodes. The minimum support parameter of the symptom node can adopt two setting modes: 1) Unified minimum support, namely, all symptom nodes adopt unified minimum support parameters; 2) And (3) multiple minimum support, namely setting a special minimum support parameter for each symptom attribute according to the value range and the data distribution characteristics of different symptom attributes. And finally, taking the minimum support parameters corresponding to different node types as filtering conditions of frequency, and mining frequent subgraphs in the graph set to obtain a traditional Chinese medicine dialectical treatment mode comprising key symptom characteristics, common treatment rules and treatment methods, applicable formulas and core traditional Chinese medicines.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and are not limiting. Although the present invention has been described in detail with reference to the embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the appended claims.
Claims (8)
1. A method for mining Chinese medicine dialectical treatment mode based on Chinese medicine case mining comprises the following steps:
1) Carrying out standardization and word segmentation processing operation on data information in a traditional Chinese medical record; the standardized processing of the data information refers to designating standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in medical records according to the Chinese word list of traditional Chinese medicine; the word segmentation processing is used for splitting complex symptom descriptions in the traditional Chinese medicine medical records into minimum symptom description units with fine granularity; symptoms consist of symptom attributes and symptom values, wherein the symptom attributes represent the object described by the symptoms, and the symptom values are specific manifestations of the symptom attributes;
2) Modeling the traditional Chinese medical records data processed in the step 1) into a graph data structure, wherein nodes in the graph data structure represent symptoms, diseases, symptoms, rules, prescriptions and traditional Chinese medicine composition nodes in the traditional Chinese medical records, namely symptom nodes, disease nodes, syndrome nodes, rule nodes, prescription nodes and traditional Chinese medicine composition nodes; the symptom node is connected with the disease node, the syndrome node and the syndrome node by edges, which means that the symptoms described by the symptom node belong to the symptoms of the diseases, the syndrome type and the syndromes described by the disease node, the syndrome node and the syndrome node connected with the symptom node; the syndrome node is connected with the rule node through an edge, and the rule node is connected with the prescription node through an edge, so that the rule corresponding to the syndrome and the prescription usable by the rule are represented; the prescription nodes are connected with the traditional Chinese medicine composition nodes by edges, which means that the traditional Chinese medicine corresponding to the traditional Chinese medicine composition nodes is the traditional Chinese medicine composition of the corresponding prescription;
3) Digging the graph data structure according to the received digging condition, and finding out key symptom characteristics of disease diagnosis, an applicable treatment method, an applicable prescription and a traditional Chinese medicine composition to form a traditional Chinese medicine dialectical treatment mode conforming to the digging condition; wherein the mining conditions include a disease, syndrome, or syndrome name to be mined; the method for forming the traditional Chinese medicine dialectical treatment mode conforming to the excavation condition comprises the following steps: firstly, selecting a traditional Chinese medical records set Z conforming to mining conditions from output results of a data preprocessing module; then traversing all cases in the case set Z, and counting the occurrence frequency of each symptom, treatment rule, prescription and Chinese medicine composition; then, for the symptom node, acquiring the symptom attribute of the symptom node, and setting the minimum support parameter of the symptom attribute of the symptom node according to the occurrence frequency of each symptom value corresponding to the symptom attribute; for the rule node, the prescription node and the traditional Chinese medicine composition node, respectively setting corresponding minimum support parameters according to application requirements; then, according to the traditional Chinese medical records ID, a graph data set G (Z) corresponding to a medical records set Z is screened out from the output result of the data modeling module, then a frequent subgraph mining algorithm is adopted to mine on the G (Z), and the obtained frequent subgraph is the traditional Chinese medical diagnosis and treatment mode which accords with the mining condition; the pattern of treatment based on syndrome differentiation of traditional Chinese medicine comprises symptoms, syndrome type, diseases, treatment rules, prescriptions and traditional Chinese medicines, and can reflect the internal logical association of the pattern of treatment based on syndrome differentiation of traditional Chinese medicine.
2. The method of claim 1, wherein the method of mining the graph data structure is: firstly, selecting a corresponding minimum support parameter as a filtering condition according to the node type, and adopting a frequent subgraph mining algorithm to mine on G (Z) to obtain frequent nodes and frequent edges; then constructing a frequent subtree by using the frequent edges; and finally expanding the frequent subtrees to form frequent subgraphs, namely, the traditional Chinese medicine dialectical treatment mode corresponding to the mining conditions.
3. The method of claim 1, wherein the setting of the minimum support parameter for the symptom attribute to which the symptom node belongs comprises: firstly, acquiring a symptom attribute of the symptom node, and sequencing the symptom values from large to small according to the occurrence frequency of each symptom value corresponding to the symptom attribute to obtain a symptom value sequence L; then, starting from the first element of the symptom value sequence L, sequentially selecting each element in the symptom value sequence L, and accumulating and summing the occurrence frequencies corresponding to the selected elements until the accumulated frequency exceeds a preset threshold value; and then taking the appearance frequency corresponding to the element which is finally taken out from the symptom value sequence L as the minimum support parameter of the symptom attribute of the symptom node.
4. The method of claim 1, wherein the mining conditions further comprise doctor name.
5. The traditional Chinese medicine dialectical treatment mode mining system based on traditional Chinese medicine case mining is characterized by comprising a data preprocessing module, a data modeling module and a dialectical treatment mode mining module; wherein the method comprises the steps of
The data preprocessing module is used for carrying out standardization and word segmentation processing operation on data information in the traditional Chinese medical records; the standardized processing of the data information refers to designating standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in medical records according to the Chinese word list of traditional Chinese medicine; the word segmentation processing is used for splitting complex symptom descriptions in the traditional Chinese medicine medical records into minimum symptom description units with fine granularity; symptoms consist of symptom attributes and symptom values, wherein the symptom attributes represent the object described by the symptoms, and the symptom values are specific manifestations of the symptom attributes;
the data modeling module is used for modeling the traditional Chinese medical records data processed by the data preprocessing module into a graph data structure, wherein nodes in the graph data structure represent symptoms, diseases, symptoms, rules, prescriptions and traditional Chinese medicine components in the traditional Chinese medical records; namely symptom nodes, disease nodes, syndrome nodes, rule nodes, prescription nodes and traditional Chinese medicine composition nodes; the symptom node is connected with the disease node, the syndrome node and the syndrome node by edges, which means that the symptoms described by the symptom node belong to the symptoms of the diseases, the syndrome type and the syndromes described by the disease node, the syndrome node and the syndrome node connected with the symptom node; the syndrome node is connected with the rule node through an edge, and the rule node is connected with the prescription node through an edge, so that the rule corresponding to the syndrome and the prescription usable by the rule are represented; the prescription nodes are connected with the traditional Chinese medicine composition nodes by edges, which means that the traditional Chinese medicine corresponding to the traditional Chinese medicine composition nodes is the traditional Chinese medicine composition of the corresponding prescription;
the dialectical treatment mode mining module is used for mining the graph data structure according to the received mining conditions, finding key symptom characteristics of disease diagnosis, an applicable treatment method, an applicable prescription and traditional Chinese medicine composition, and forming a traditional Chinese medicine dialectical treatment mode conforming to the mining conditions; wherein the mining conditions include a disease, syndrome, or syndrome name to be mined;
the diagnosis and treatment mode mining module firstly selects a traditional Chinese medical records set Z conforming to mining conditions from the output result of the data preprocessing module; then traversing all cases in the case set Z, and counting the occurrence frequency of each symptom, treatment rule, prescription and Chinese medicine composition; then acquiring the symptom attribute of the symptom node, and setting the minimum support parameter of the symptom node according to the occurrence frequency of each symptom value corresponding to the symptom attribute; for the rule node, the prescription node and the traditional Chinese medicine composition node, respectively setting corresponding minimum support parameters according to application requirements; then, according to the traditional Chinese medical records ID, a graph data set G (Z) corresponding to a medical records set Z is screened out from the output result of the data modeling module, then a frequent subgraph mining algorithm is adopted to mine on the G (Z), and the obtained frequent subgraph is the traditional Chinese medical diagnosis and treatment mode which accords with the mining condition; the pattern of treatment based on syndrome differentiation of traditional Chinese medicine comprises symptoms, syndrome type, diseases, treatment rules, prescriptions and traditional Chinese medicines, and can reflect the internal logical association of the pattern of treatment based on syndrome differentiation of traditional Chinese medicine.
6. The system of claim 5, wherein the method of mining the graph data structure is: firstly, selecting a corresponding minimum support parameter as a filtering condition according to the node type, and adopting a frequent subgraph mining algorithm to mine on G (Z) to obtain frequent nodes and frequent edges; then constructing a frequent subtree by using the frequent edges; and finally expanding the frequent subtrees to form frequent subgraphs, namely, the traditional Chinese medicine dialectical treatment mode corresponding to the mining conditions.
7. The system of claim 5, wherein the method for setting the minimum support parameter for the symptom attribute to which the symptom node belongs is: firstly, acquiring a symptom attribute of the symptom node, and sequencing the symptom values from large to small according to the occurrence frequency of each symptom value corresponding to the symptom attribute to obtain a symptom value sequence L; then, starting from the first element of the symptom value sequence L, sequentially selecting each element in the symptom value sequence L, and accumulating and summing the occurrence frequencies corresponding to the selected elements until the accumulated frequency exceeds a preset threshold value; and then taking the appearance frequency corresponding to the element which is finally taken out from the symptom value sequence L as the minimum support parameter of the symptom attribute of the symptom node.
8. The system of claim 5, wherein the mining conditions further comprise doctor name.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010461494.9A CN113744886B (en) | 2020-05-27 | 2020-05-27 | Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010461494.9A CN113744886B (en) | 2020-05-27 | 2020-05-27 | Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113744886A CN113744886A (en) | 2021-12-03 |
| CN113744886B true CN113744886B (en) | 2024-03-19 |
Family
ID=78723965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010461494.9A Active CN113744886B (en) | 2020-05-27 | 2020-05-27 | Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113744886B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407650A (en) * | 2016-08-29 | 2017-02-15 | 首都医科大学附属北京中医医院 | Traditional Chinese medicine data processing device and method |
| CN106648636A (en) * | 2016-12-08 | 2017-05-10 | 北京航空航天大学 | Software function change prediction system and method based on graph mining |
| CN106874680A (en) * | 2017-02-22 | 2017-06-20 | 天津天士力医药商业有限公司 | It is a kind of to detect the brain network analysis method that blood-nourishing and brain-refreshing ball improves cognitive function |
| CN106919671A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of traditional Chinese medical science text medical record is excavated and aid decision intelligence system |
| CN107591204A (en) * | 2017-08-01 | 2018-01-16 | 山东大学 | Be in hospital again Forecasting Methodology and system based on sequential portrait figure |
| CN110335684A (en) * | 2019-06-14 | 2019-10-15 | 电子科技大学 | The intelligent dialectical aid decision-making method of Chinese medicine based on topic model technology |
| CN110379520A (en) * | 2019-06-18 | 2019-10-25 | 北京百度网讯科技有限公司 | The method for digging and device of medical knowledge map, computer equipment and readable medium |
-
2020
- 2020-05-27 CN CN202010461494.9A patent/CN113744886B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407650A (en) * | 2016-08-29 | 2017-02-15 | 首都医科大学附属北京中医医院 | Traditional Chinese medicine data processing device and method |
| CN106648636A (en) * | 2016-12-08 | 2017-05-10 | 北京航空航天大学 | Software function change prediction system and method based on graph mining |
| CN106919671A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of traditional Chinese medical science text medical record is excavated and aid decision intelligence system |
| CN106874680A (en) * | 2017-02-22 | 2017-06-20 | 天津天士力医药商业有限公司 | It is a kind of to detect the brain network analysis method that blood-nourishing and brain-refreshing ball improves cognitive function |
| CN107591204A (en) * | 2017-08-01 | 2018-01-16 | 山东大学 | Be in hospital again Forecasting Methodology and system based on sequential portrait figure |
| CN110335684A (en) * | 2019-06-14 | 2019-10-15 | 电子科技大学 | The intelligent dialectical aid decision-making method of Chinese medicine based on topic model technology |
| CN110379520A (en) * | 2019-06-18 | 2019-10-25 | 北京百度网讯科技有限公司 | The method for digging and device of medical knowledge map, computer equipment and readable medium |
Non-Patent Citations (4)
| Title |
|---|
| Graph mining: procedure, application to drug discovery and recent advances;Ichigaku Takigawa et al.;《Drug Discovery Today》;第18卷(第1-2期);第50-57页 * |
| 基于gSpan改进算法的中医辨证论治模式挖掘研究;任晋宇等;《中国中医药信息杂志》;第28卷(第10期);第22-28页 * |
| 基于图的数据挖掘算法在中医方剂中的应用;张焕生等;《河北工程技术高等专科学校学报》(第03期);第59-62页 * |
| 频繁闭图挖掘算法在中医方剂中的应用;窦立君等;《吉林大学学报(理学版)》;第50卷(第06期);第1223-1227页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113744886A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766445B (en) | Knowledge graph construction method and data processing device | |
| US9430616B2 (en) | Extracting clinical care pathways correlated with outcomes | |
| CN110189831A (en) | A kind of case history knowledge mapping construction method and system based on dynamic diagram sequences | |
| CN104115145A (en) | Generating visualizations of display group of tags representing content instances in objects satisfying search criteria | |
| WO2023124191A1 (en) | Depth map matching-based automatic classification method and system for medical data elements | |
| CN113161001B (en) | Improved LDA-based process path mining method | |
| WO2020258483A1 (en) | Clinical medication behavior analysis system based on highly effective negative sequential mining pattern, and working method therefor | |
| US20060136467A1 (en) | Domain-specific data entity mapping method and system | |
| US20210202111A1 (en) | Method of classifying medical records | |
| CN110246590A (en) | A kind of construction method of blood disease knowledge mapping database | |
| Luo et al. | An analysis of FMA using structural self-bisimilarity | |
| Jazayeri et al. | Frequent subgraph mining algorithms in static and temporal graph-transaction settings: A survey | |
| McLachlan et al. | Realistic synthetic data generation: The ATEN framework | |
| CN113744886B (en) | Method and system for mining traditional Chinese medicine dialectical treatment mode based on traditional Chinese medicine case mining | |
| CN117196028A (en) | Medical knowledge graph production method and system based on knowledge graph | |
| CN114188024A (en) | Livestock and poultry disease prediction classification method based on livestock and poultry disease knowledge graph | |
| CN114385845A (en) | Image classification management method and system based on graph clustering | |
| CN110010231A (en) | A kind of data processing system and computer readable storage medium | |
| Bruno et al. | Temporal pattern mining for medical applications | |
| US7657417B2 (en) | Method, system and machine readable medium for publishing documents using an ontological modeling system | |
| CN115066673A (en) | System and method for ETL pipeline processing | |
| Shi et al. | Transfer significant subgraphs across graph databases | |
| EP3654339A1 (en) | Method of classifying medical records | |
| Melo et al. | A conceptual approach to gene expression analysis enhanced by visual analytics | |
| Jaulent et al. | A Case-Based Reasoning method for computer-assisted diagnosis in histopathology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |