CN113744886A - Traditional Chinese medicine syndrome differentiation and treatment mode mining method and system based on traditional Chinese medicine case mining - Google Patents
Traditional Chinese medicine syndrome differentiation and treatment mode mining method and system based on traditional Chinese medicine case mining Download PDFInfo
- Publication number
- CN113744886A CN113744886A CN202010461494.9A CN202010461494A CN113744886A CN 113744886 A CN113744886 A CN 113744886A CN 202010461494 A CN202010461494 A CN 202010461494A CN 113744886 A CN113744886 A CN 113744886A
- Authority
- CN
- China
- Prior art keywords
- symptom
- nodes
- chinese medicine
- mining
- traditional chinese
- 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.)
- Granted
Links
- 208000011580 syndromic disease Diseases 0.000 title claims abstract description 113
- 239000003814 drug Substances 0.000 title claims abstract description 93
- 238000005065 mining Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000004069 differentiation Effects 0.000 title claims abstract description 21
- 208000024891 symptom Diseases 0.000 claims abstract description 142
- 201000010099 disease Diseases 0.000 claims abstract description 50
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 50
- 239000000203 mixture Substances 0.000 claims abstract description 26
- 238000003745 diagnosis Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000001225 therapeutic effect Effects 0.000 claims description 6
- 229940126680 traditional chinese medicines Drugs 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 229940126532 prescription medicine Drugs 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 5
- 206010000087 Abdominal pain upper Diseases 0.000 description 4
- 238000007418 data mining Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 2
- 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
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008216 herbs Nutrition 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
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
本发明公开了一种基于中医医案挖掘的中医辨证论治模式挖掘方法及系统，本方法为：1)对中医病案中的数据信息进行标准化和分词处理操作；其中数据信息标准化处理是指依据中医术语词表为病案中出现的症状名称、疾病名称、证型名称、证候名称、方剂名称和中药名称指定标准名称；症状由症状属性和症状值构成，其中症状属性表示症状所描述的对象，症状值是症状属性的具体表现；2)将步骤1)处理后的中医病案数据建模为图数据结构；3)根据挖掘条件对图数据结构进行挖掘，发现病证诊断的关键症状特征、可采用的治则治法、适用的方剂及中药组成，形成符合挖掘条件的中医辨证论治模式。本发明有效解决关键症状缺失问题，保障辨证论治模式的完备性。
The invention discloses a method and system for mining a TCM syndrome differentiation and treatment mode based on the mining of TCM medical records. The method includes: 1) standardizing and segmenting data information in the TCM medical records; wherein the standardization processing of the data information refers to processing based on TCM terms The vocabulary specifies standard names for symptom names, disease names, syndrome names, syndrome names, prescription names, and Chinese medicine names that appear in medical records; symptoms are composed of symptom attributes and symptom values, where symptom attributes represent the objects described by the symptoms, and the symptoms 2) Model the TCM medical record data processed in step 1) into a graph data structure; 3) Mining the graph data structure according to the mining conditions to discover the key symptom characteristics of disease and syndrome diagnosis, which can be used According to the principle of treatment, the applicable formula and the composition of traditional Chinese medicine, a TCM syndrome differentiation and treatment mode that meets the mining conditions is formed. The invention effectively solves the problem of lack of key symptoms and guarantees the completeness of the syndrome differentiation and treatment mode.
Description
Technical Field
The invention relates to a traditional Chinese medicine syndrome differentiation and treatment mode mining method and system based on traditional Chinese medicine case mining, and belongs to the technical field of software.
Background
The traditional Chinese medicine is a treasure of the traditional culture of the famous Chinese people. The traditional Chinese medicine diagnosis and treatment is based on the concept of treatment and diagnosis based on syndrome differentiation, and the diagnosis and treatment process and results depend on the cognition and understanding of traditional Chinese medicine thinking and concept and the practical experience of individuals to a great extent. Over thousands of years of practice and development, clinical experience of famous physicians in past generations gradually precipitates as precious wealth of Chinese medicine culture in China, and is an important component of Chinese medicine culture inheritance. However, the clinical experience of the famous physicians is in a form of subjective consciousness, and is mostly hidden in each specific medical record. How to adopt a scientific method to refine, summarize, abstract, summarize and summarize the diagnosis and treatment experience hidden in the medical record, so that the diagnosis and treatment experience is objective, standardized and visualized, and has important significance for developing and inheriting Chinese medicine culture.
Data mining is a common data analysis technology in computer science and aims to search data rules from large-scale data records and discover potential and implicit data information. Compared with traditional mining algorithms such as classification and clustering, graph data mining can model and represent more complex data structures and discover more complex data association, and becomes a fundamental research problem which is concerned by the current data mining field.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention aims to provide a traditional Chinese medicine dialectical treatment mode mining method and system based on graph data mining, wherein a graph data structure is utilized to model complex logic association among elements such as symptoms, diseases, syndrome types, syndromes, treatment rules, formulas and traditional Chinese medicine compositions in a traditional Chinese medicine case, and an expanded frequent subgraph mining algorithm is adopted to extract key elements of the traditional Chinese medicine dialectical treatment process, so that a traditional Chinese medicine dialectical treatment mode facing to the diseases, syndrome types and syndromes is formed. The system can display the diagnosis and treatment experience hidden in the traditional Chinese medical record in an objective and graphical traditional Chinese medicine dialectical treatment mode diagram mode, is beneficial to inheritance and development of clinical experience of famous physicians, and has important guiding significance and application value for traditional Chinese medicine dialectical treatment theory research, traditional Chinese medicine intelligent auxiliary diagnosis and the like.
The technical solution of the invention is as follows: the traditional Chinese medicine dialectical treatment mode mining system based on traditional Chinese medicine case mining constructs a traditional Chinese medicine case into a dialectical treatment process diagram when a doctor is on the way, and extracts key diagnosis and treatment information in the case by adopting an expanded diagram mining algorithm to form a traditional Chinese medicine dialectical treatment mode aiming at different diseases, syndrome types and syndromes. The system comprises a data preprocessing module, a data modeling module and a syndrome differentiation and treatment mode mining module. Wherein:
and the data preprocessing module is used for carrying out standardization and word segmentation processing on data information in the medical records. The data standardization process specifies standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in the medical records according to the Chinese medicine term vocabulary. The word segmentation processing is mainly developed aiming at symptom information and is used for splitting the complex symptom description into fine-grained minimum symptom description units. The symptom is composed of a symptom attribute and a symptom value. Wherein, the symptom attribute represents the object described by the symptom, such as the color of tongue coating, the quality of tongue coating, the pulse condition, etc.; symptom values describe the appearance of attributes of the symptom, such as dark red, thick, slippery, etc.
And the data modeling module is used for modeling the traditional Chinese medical record data processed by the data preprocessing module into a graph data structure. The nodes in the graph represent symptoms, diseases, syndrome, treatment rules, prescriptions and traditional Chinese medicine components in the medical record, namely symptom nodes, disease nodes, syndrome nodes, treatment rules nodes, prescription nodes and traditional Chinese medicine component nodes. The symptom nodes are connected with the disease nodes, the syndrome nodes and the syndrome nodes by edges to represent that the symptoms described by the symptom nodes belong to the symptoms of diseases, syndromes and syndromes described by the disease nodes, the syndrome nodes and the syndrome nodes connected with the symptom nodes. The syndrome node and the rule node, and the rule node and the prescription node are connected by edges to represent the corresponding rules and available prescriptions. The edge between the prescription node and the Chinese medicine composition node indicates that the Chinese medicine corresponding to the Chinese medicine composition node is the Chinese medicine composition corresponding to the prescription.
The dialectical treatment mode mining module adopts an expanded frequent subgraph mining algorithm to mine a graph-structured traditional Chinese medicine case, finds key symptom characteristics of disease diagnosis, an adopted therapeutic rule and treatment method, an applicable prescription and a core traditional Chinese medicine composition, and forms a traditional Chinese medicine dialectical treatment mode aiming at different diseases, syndrome types and syndromes. The module is realized by the following steps:
1) and according to the mining target of the user, selecting a traditional Chinese medical case set Z meeting the mining condition of the user from the output result of the data preprocessing module. The mining conditions include the name of the doctor and the name of the disease, syndrome or syndrome to be mined. Wherein, the disease name, syndrome type name and syndrome name are the necessary mining conditions of three syndrome differentiation treatment modes of disease, syndrome type and syndrome respectively; doctor names are optional mining conditions. The user can designate and dig the syndrome differentiation and treatment mode of a certain doctor about a certain disease, syndrome type or syndrome, or can not designate the doctor and dig the syndrome differentiation and treatment mode about a certain disease, syndrome type or syndrome in all medical records.
2) Traversing all medical records in the medical record set Z, and counting the occurrence frequency of each symptom, treatment rule, prescription and traditional Chinese medicine composition.
Wherein, the frequency of occurrence is the number of occurrences/total number of cases.
3) And setting a minimum support parameter according to the node type.
And 3.1) the three types of nodes of diseases, syndrome types and syndromes are nodes related to the user mining target and are used for appointing which disease, syndrome type or syndrome the dialectical treatment mode mined by the user aims at. The three types of nodes are necessary nodes of three syndrome differentiation treatment modes respectively, and minimum support degree parameters are not required to be set.
And 3.2) for the symptom nodes, sequentially acquiring the symptom attribute to which each symptom node belongs, and then respectively setting a minimum support degree parameter 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) sorting the symptom values from large to small according to the occurrence frequency of each symptom value corresponding to the current symptom attribute to obtain a symptom value sequence L, wherein list (L) is the length of the sequence L;
3.2.2) sequentially selecting each element L (i) in L from the first element, wherein i is more than or equal to 1 and less than or equal to list (L), and accumulating and summing the appearance frequencies corresponding to L (i) until the accumulation frequency exceeds a preset threshold value;
3.2.3) taking the appearance frequency corresponding to the element L (i) taken out from L for the last time as the minimum support degree parameter of the current symptom attribute.
3.3) for three types of nodes formed by rules of treatment, prescriptions and traditional Chinese medicine, respectively setting minimum support degree parameters of the three types of nodes according to actual application requirements.
4) And (3) screening a graph data set G (Z) corresponding to the medical record set Z from the output result of the data modeling module according to the medical record ID, and then mining on G (Z) by adopting an expanded frequent subgraph mining algorithm, wherein the obtained frequent subgraph is a traditional Chinese medicine syndrome differentiation and treatment mode which consists of key elements such as symptoms, syndrome types, syndromes, diseases, treatment rules, prescriptions, traditional Chinese medicines and the like and can reflect internal logic association. The excavating steps are as follows:
4.1) selecting a corresponding minimum support parameter as a filtering condition according to the node type, mining on G (Z) by adopting a frequent subgraph mining algorithm to obtain frequent nodes and frequent edges, and sequencing the frequent edges according to the sequence of descending frequency and ascending DFS (depth-first search) code values;
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 the inner edges which can be connected with the frequent subtree from the frequent edge set, and adding the inner edges into the subtree to form a frequent subgraph, namely, a traditional Chinese medicine dialectical treatment mode corresponding to the mining condition.
Compared with the prior art, the invention has the advantages that:
(1) modeling the traditional Chinese medical record into a graph structure, extracting key diagnosis and treatment information in the traditional Chinese medical record based on the thought of frequent subgraph mining, forming a graphical traditional Chinese medicine dialectical treatment mode, and showing traditional Chinese medicine dialectical thinking and a method in a more visualized mode.
(2) The mining requirements of three common traditional Chinese medicine dialectical treatment modes including the mode mining of disease dialectical treatment, the mode mining of syndrome dialectical treatment and the mode mining of syndrome dialectical treatment can be met; the method can realize the dialectical treatment mode excavation facing to the famous doctors and the famous families aiming at individual famous doctors.
(3) The traditional frequent subgraph mining algorithm is expanded, different minimum support degree parameters are set according to the type of the node, the flexibility of mode mining is improved, and the requirements of a user on various mode mining requirements can be met. Particularly, aiming at the symptom nodes, the minimum support degree parameter is respectively set for each symptom attribute according to the symptom attribute, so that the problem of key symptom deficiency is effectively solved, and the completeness of a syndrome differentiation treatment mode is guaranteed.
Drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a diagram illustrating the implementation of the dialectical treatment model mining module in the system of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples.
As shown in FIG. 1, the system of the present invention comprises three functional modules of data preprocessing, data modeling and dialectical treatment mode mining.
And the data preprocessing module is used for carrying out standardization and word segmentation processing on data information in the medical records. The data standardization process specifies standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in the medical records according to the Chinese medicine term vocabulary. The vocabulary of Chinese medicine terms defines the standard names and aliases of common Chinese medicine terms. The Chinese medicine terms appearing in the Chinese medicine medical record can be standardized by utilizing the word list of the Chinese medicine terms, for example, the symptom names of 'epigastric pain by pressing', 'epigastric pain by pressing' and 'epigastric pain by pressing' can be unified and standardized into 'epigastric pain by pressing'. The word segmentation processing is mainly developed aiming at symptom information and is used for segmenting the complex symptom description into fine-grained minimum symptom description units, for example, the symptom ' pulse condition is deep, wiry and thin, and the number of the pulses ' can be segmented into four independent symptoms ' pulse condition is deep ', ' pulse condition is wiry ', ' pulse condition is thin, and ' pulse condition is number '.
And the data modeling module is used for modeling the traditional Chinese medical record data processed by the data preprocessing module into a graph data structure. The nodes in the graph represent symptoms, diseases, syndrome types, syndromes, treatment rules, prescriptions and traditional Chinese medicine compositions in the medical records. The side connection between the symptom and the disease, syndrome or syndrome indicates that the symptom belongs to the manifestation of the disease, syndrome or syndrome. If a plurality of diseases, syndromes and syndromes exist, each symptom is connected with the plurality of diseases, syndromes and syndromes respectively. The syndrome and the rules of treatment, and the rules of treatment are also connected by the border, indicating the corresponding rules of treatment for the syndrome and the available formulas for the rules of treatment. The border between the prescription and the Chinese medicine composition indicates that the Chinese medicine is the composition component of the prescription. If there are multiple syndromes, treatment principles and prescriptions, the syndromes are connected with the treatment principles, the treatment principles are connected with the prescriptions, and the prescriptions are connected with the Chinese herbs.
The dialectical treatment mode mining module adopts an expanded frequent subgraph mining algorithm to mine a graph-structured traditional Chinese medicine case, finds key symptom characteristics of disease diagnosis, an adopted therapeutic rule and treatment method, an applicable prescription and a core traditional Chinese medicine composition, and forms a traditional Chinese medicine dialectical treatment mode aiming at different diseases, syndrome types and syndromes. The module implementation process is shown in fig. 2. Firstly, a medical record set is screened according to mining conditions input by a user. The excavation conditions include: 1) the 'doctor name' is mined according to the medical record of the doctor; 2) the "disease name", "syndrome name" and "syndrome name" refer to which disease, syndrome or syndrome is mined. Then, different mining parameters, namely the minimum support degree parameter, are set 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 degree parameter comprise a rule node, a prescription node, a traditional Chinese medicine composition node and a symptom node. The minimum support parameter of the symptom node can be set in two ways: 1) unifying the minimum support degree, namely adopting a unified minimum support degree parameter for all symptom nodes; 2) and multiple minimum support degrees, namely setting a special minimum support degree parameter for each symptom attribute according to the value range and the data distribution characteristics of different symptom attributes. And finally, mining frequent subgraphs in a graph set by taking the minimum support degree parameters corresponding to different node types as filtering conditions of the frequency to obtain a traditional Chinese medicine syndrome differentiation treatment mode comprising key symptom characteristics, a common treatment rule treatment method, an applicable prescription and core traditional Chinese medicines.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and are not limited. Although the present invention has been described in detail with reference to the embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A traditional Chinese medicine dialectical treatment mode mining method based on traditional Chinese medicine medical record mining comprises the following steps:
1) carrying out standardization and word segmentation processing operation on data information in the medical records; wherein the data information standardization processing refers to assigning standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in the medical records according to the Chinese medicine term vocabulary; the word segmentation processing is used for splitting the complex symptom description in the traditional Chinese medical record into fine-grained minimum symptom description units; the symptom is composed of a symptom attribute and a symptom value, wherein the symptom attribute represents an object described by the symptom, and the symptom value is a concrete expression of the symptom attribute;
2) modeling the traditional Chinese medicine medical record data processed in the step 1) into a graph data structure, wherein nodes in the graph data structure represent symptoms, diseases, syndrome types, syndromes, rules of treatment, prescriptions and traditional Chinese medicines in the traditional Chinese medicine medical record, namely symptom nodes, disease nodes, syndrome nodes, rules of treatment nodes, prescription nodes and traditional Chinese medicine composition nodes; the symptom nodes are connected with the disease nodes, the syndrome nodes and the syndrome nodes by edges to represent that the symptoms described by the symptom nodes belong to the symptoms of diseases, syndromes and syndromes described by the disease nodes, the syndrome nodes and the syndrome nodes connected with the symptom nodes; the syndrome node and the rule node are connected by edges, and the rule node and the prescription node are connected by edges to represent the corresponding rule of the syndrome and the available prescription of the rule; the prescription nodes and the Chinese medicine composition nodes are connected by edges to indicate that the Chinese medicine corresponding to the Chinese medicine composition nodes is the Chinese medicine composition corresponding to the prescription;
3) mining the graph data structure according to the received mining conditions, and finding out key symptom characteristics of disease diagnosis, an adopted therapeutic rule and treatment method, an applicable prescription and traditional Chinese medicine composition to form a traditional Chinese medicine dialectical treatment mode according with the mining conditions; wherein the mining condition includes a disease, syndrome, or syndrome name to be mined.
2. The method of claim 1, wherein the dialectical treatment model of TCM conforming to mining conditions is formed by: firstly, selecting a traditional Chinese medical record set Z meeting mining conditions from output results of a data preprocessing module; then traversing all medical records in the medical record set Z, and counting the occurrence frequency of each symptom, treatment rule, prescription and traditional Chinese medicine composition; then, for a symptom node, acquiring a symptom attribute to which the symptom node belongs, and setting a minimum support parameter of the symptom attribute to which the symptom node belongs according to the occurrence frequency of each symptom value corresponding to the symptom attribute; respectively setting corresponding minimum support degree parameters for the therapeutic rule node, the prescription node and the Chinese medicine composition node according to application requirements; then, according to the traditional Chinese medical record ID, a graph data set G (Z) corresponding to the medical record set Z is screened out from an output result of the data modeling module, then mining is carried out on the G (Z) by adopting a frequent subgraph mining algorithm, and the obtained frequent subgraph is a traditional Chinese medical syndrome differentiation and treatment mode which accords with mining conditions; the traditional Chinese medicine syndrome differentiation treatment mode comprises symptoms, syndrome types, syndromes, diseases, treatment rules, a prescription and traditional Chinese medicines and can reflect internal logic correlation.
3. The method of claim 2, wherein the graph data structure is mined by: firstly, selecting a corresponding minimum support parameter as a filtering condition according to the node type, and mining on G (Z) by adopting a frequent subgraph mining algorithm to obtain frequent nodes and frequent edges; then constructing a frequent subtree by using the frequent edge; and finally, expanding the frequent subtrees to form frequent subgraphs, namely mining the traditional Chinese medicine syndrome differentiation treatment mode corresponding to the conditions.
4. The method of claim 2, wherein the method for setting the minimum support parameter of the symptom attribute to which the symptom node belongs comprises: firstly, obtaining symptom attributes to which the symptom nodes belong, and sorting the symptom values from large to small according to the occurrence frequency of each symptom value corresponding to the symptom attributes to obtain a symptom value sequence L; sequentially selecting each element in the symptom value sequence L from the first element of the symptom value sequence L, and accumulating and summing the occurrence frequencies corresponding to the selected elements until the accumulation frequency exceeds a preset threshold value; and then, taking the appearance frequency corresponding to the element extracted from the symptom value sequence L for the last time as the minimum support degree parameter of the symptom attribute to which the symptom node belongs.
5. The method of claim 1, wherein the mining condition further comprises a doctor name.
6. A 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 data preprocessing module is used for carrying out standardization and word segmentation processing operation on data information in the medical records; wherein the data information standardization processing refers to assigning standard names for symptom names, disease names, syndrome names, prescription names and traditional Chinese medicine names appearing in the medical records according to the Chinese medicine term vocabulary; the word segmentation processing is used for splitting the complex symptom description in the traditional Chinese medical record into fine-grained minimum symptom description units; the symptom is composed of a symptom attribute and a symptom value, wherein the symptom attribute represents an object described by the symptom, and the symptom value is a concrete expression of the symptom attribute;
the data modeling module is used for modeling the traditional Chinese medicine medical record data processed by the data preprocessing module into a graph data structure, wherein nodes in the graph data structure represent symptoms, diseases, syndrome types, syndromes, treatment rules, prescriptions and traditional Chinese medicines in the traditional Chinese medicine medical record; namely symptom nodes, disease nodes, syndrome nodes, treatment rules nodes, prescription nodes and Chinese medicine composition nodes; the symptom nodes are connected with the disease nodes, the syndrome nodes and the syndrome nodes by edges to represent that the symptoms described by the symptom nodes belong to the symptoms of diseases, syndromes and syndromes described by the disease nodes, the syndrome nodes and the syndrome nodes connected with the symptom nodes; the syndrome node and the rule node are connected by edges, and the rule node and the prescription node are connected by edges to represent the corresponding rule of the syndrome and the available prescription of the rule; the prescription nodes and the Chinese medicine composition nodes are connected by edges to indicate that the Chinese medicine corresponding to the Chinese medicine composition nodes is the Chinese medicine composition corresponding to the 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 adopted therapeutic principle and treatment method, an applicable prescription and traditional Chinese medicine composition, and forming a traditional Chinese medicine dialectical treatment mode according with the mining conditions; wherein the mining condition includes a disease, syndrome, or syndrome name to be mined.
7. The system of claim 6, wherein the dialectical treatment mode mining module first selects a traditional Chinese medical case set Z meeting mining conditions from the output results of the data preprocessing module; then traversing all medical records in the medical record set Z, and counting the occurrence frequency of each symptom, treatment rule, prescription and traditional Chinese medicine composition; then obtaining 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; respectively setting corresponding minimum support degree parameters for the therapeutic rule node, the prescription node and the Chinese medicine composition node according to application requirements; then, according to the traditional Chinese medical record ID, a graph data set G (Z) corresponding to the medical record set Z is screened out from an output result of the data modeling module, then mining is carried out on the G (Z) by adopting a frequent subgraph mining algorithm, and the obtained frequent subgraph is a traditional Chinese medical syndrome differentiation and treatment mode which accords with mining conditions; the traditional Chinese medicine syndrome differentiation treatment mode comprises symptoms, syndrome types, syndromes, diseases, treatment rules, a prescription and traditional Chinese medicines and can reflect internal logic correlation.
8. The system of claim 7, wherein the graph data structure is mined by: firstly, selecting a corresponding minimum support parameter as a filtering condition according to the node type, and mining on G (Z) by adopting a frequent subgraph mining algorithm to obtain frequent nodes and frequent edges; then constructing a frequent subtree by using the frequent edge; and finally, expanding the frequent subtrees to form frequent subgraphs, namely mining the traditional Chinese medicine syndrome differentiation treatment mode corresponding to the conditions.
9. The system of claim 7, wherein the method for setting the minimum support parameter for the symptom attribute to which the symptom node belongs comprises: firstly, obtaining symptom attributes to which the symptom nodes belong, and sorting the symptom values from large to small according to the occurrence frequency of each symptom value corresponding to the symptom attributes to obtain a symptom value sequence L; sequentially selecting each element in the symptom value sequence L from the first element of the symptom value sequence L, and accumulating and summing the occurrence frequencies corresponding to the selected elements until the accumulation frequency exceeds a preset threshold value; and then, taking the appearance frequency corresponding to the element extracted from the symptom value sequence L for the last time as the minimum support degree parameter of the symptom attribute to which the symptom node belongs.
10. The system of claim 6, wherein the mining condition further comprises a 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 true CN113744886A (en) | 2021-12-03 |
| CN113744886B 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 | TCM Intelligent Syndrome Differentiation Auxiliary Decision-Making Method 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 | TCM Intelligent Syndrome Differentiation Auxiliary Decision-Making Method 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 |
|---|
| ICHIGAKU TAKIGAWA ET AL.: "Graph mining: procedure, application to drug discovery and recent advances", 《DRUG DISCOVERY TODAY》, vol. 18, no. 1, pages 50 - 57 * |
| 任晋宇等: "基于gSpan改进算法的中医辨证论治模式挖掘研究", 《中国中医药信息杂志》, vol. 28, no. 10, pages 22 - 28 * |
| 张焕生等: "基于图的数据挖掘算法在中医方剂中的应用", 《河北工程技术高等专科学校学报》, no. 03, pages 59 - 62 * |
| 窦立君等: "频繁闭图挖掘算法在中医方剂中的应用", 《吉林大学学报(理学版)》, vol. 50, no. 06, pages 1223 - 1227 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113744886B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108389614B (en) | A method for constructing medical image atlas based on image segmentation and convolutional neural network | |
| CN106844723B (en) | Medical knowledge base construction method based on question answering system | |
| CN110189831A (en) | A method and system for constructing medical record knowledge graph based on dynamic graph sequence | |
| CN113161001B (en) | Improved LDA-based process path mining method | |
| CN109830302B (en) | Medication pattern mining method, device and electronic device | |
| CN114003734A (en) | Breast cancer risk factor knowledge system model, knowledge map system and construction method | |
| CN116383413A (en) | Knowledge graph updating method and system based on medical data extraction | |
| WO2021238436A1 (en) | Multi-drug sharing query method, mobile terminal and storage medium | |
| CN111312354A (en) | Enhancement system for entity recognition and labeling of breast medical records based on multi-agent reinforcement learning | |
| CN112541086A (en) | Knowledge graph construction method for cerebral apoplexy | |
| US20210202111A1 (en) | Method of classifying medical records | |
| CN111667891A (en) | Cohort identification method and device applied to disease-specific clinical trials | |
| CN110277172A (en) | A clinical medication behavior analysis system based on efficient negative sequence mining mode and its working method | |
| Luo et al. | An analysis of FMA using structural self-bisimilarity | |
| CN112466462B (en) | An EMR Information Association and Evolution Method Based on Graph Deep Learning | |
| CN110246590A (en) | A kind of construction method of blood disease knowledge mapping database | |
| CN111460173B (en) | A method for constructing a disease ontology model of thyroid cancer | |
| CN119149756A (en) | Medical knowledge graph database construction method, device and medium based on information creation system | |
| CN110569372B (en) | Construction method of heart disease big data knowledge graph system | |
| Wang | Construction of a Clinical Trial Data Anomaly Detection and Risk Warning System based on Knowledge Graph | |
| CN112287113A (en) | Standardization System of Tuina Terminology | |
| Lu et al. | Data mining techniques in health informatics: a case study from breast cancer research | |
| CN119004036A (en) | Statistical analysis method, device, equipment and storage medium for clinical patients | |
| CN118039179A (en) | Digital management system and method for traditional Chinese medicine diagnosis and treatment based on AI | |
| Gong et al. | An interpretable artificial intelligence model of Chinese medicine treatment based on XGBoost algorithm |
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 |