CN112966123A - Medical health knowledge map system oriented to specific disease field - Google Patents
Medical health knowledge map system oriented to specific disease field Download PDFInfo
- Publication number
- CN112966123A CN112966123A CN202110252977.2A CN202110252977A CN112966123A CN 112966123 A CN112966123 A CN 112966123A CN 202110252977 A CN202110252977 A CN 202110252977A CN 112966123 A CN112966123 A CN 112966123A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- tool
- doctor
- mapping
- map
- 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.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 39
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 39
- 230000036541 health Effects 0.000 title claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 21
- 230000010354 integration Effects 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims description 35
- 238000013499 data model Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 10
- 238000002372 labelling Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 239000003814 drug Substances 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a medical health knowledge map system for the field of specific diseases, which relates to the technical field of data processing and comprises the following components: the data acquisition module is used for acquiring the electronic medical record of the hospital according to the requirements of doctors; the concept map building module is used for building a concept knowledge map according to the acquired electronic medical record by means of a tool set used in the work of a doctor; the example map building module is used for extracting entities, events and relations from the electronic medical record by means of a tool set used in doctor work and building an example knowledge map; and the integration module is used for fusing the nodes of the concept knowledge graph and the example knowledge graph by means of a tool set used in the doctor work to obtain the knowledge graphs of a plurality of specific disease fields. The invention can construct knowledge maps in a plurality of specific disease fields, improves the accuracy of construction of the medical health knowledge maps, and has the advantages of reutilization and expandability.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a medical health knowledge map system for the field of specific diseases.
Background
Since 2012, knowledge-graphs have been the focus of research, and this concept was originally proposed by google to enhance the semantic comprehension of its search engines. The definition of a knowledge-graph is a graph-based data structure, consisting of nodes (entities) and labeled edges (relationships between entities). Generally, a knowledge-graph having only Concept nodes is defined as a Concept knowledge-graph (Concept KnowledgeGraph: CKG), a knowledge-graph having Instance nodes and event nodes is defined as an Instance knowledge-graph (Instance KnowledgeGraph: IKG), and CKG and IKG are included as a fact knowledge-graph (Factual KnowledgeGraph: FKG).
The construction system architecture of the conventional knowledge graph mainly comprises knowledge representation, knowledge graph construction tools such as information extraction and fusion tools, and knowledge storage and application. However, conventional strategies cannot be applied directly to domain-specific profiles, let alone to construct more specialized disease-domain-specific-oriented profiles. One of the reasons is that building a professional disease-specific knowledge graph requires extracting specific entities and relationships from specific data sources and building a specialized semantic network for different diseases.
Current medical health knowledge maps generally cover a broad field of medical knowledge, all proteins (UniProt), as many drugs as possible (drug bank), many drugs known and their interactions between them (Sider), and a large number of integrated knowledge maps, such as Bio2RDF and LinkedLifeData.
As is well known in the medical field, on the one hand, there are various diseases, many complex concepts and relationships, requiring the physician to provide a large amount of detailed prior knowledge to help identify them, and more importantly, the actual needs of the physician for different diseases may vary; on the other hand, the difficulty of data acquisition and the lack of prior knowledge from the disease domain, it is very difficult to construct a medical health knowledge map covering all the disease domains at once.
Disclosure of Invention
Aiming at the requirements and the defects of the prior art development, the invention provides a medical health knowledge map system for the specific disease field.
The invention relates to a medical health knowledge map system for the field of specific diseases, which solves the technical problems by adopting the following technical scheme:
a medical health knowledge map system oriented to a specific disease field comprises a structural framework and a data processing system, wherein the structural framework comprises:
the data acquisition module is used for acquiring the electronic medical record of the hospital according to the requirements of doctors;
the concept map building module is used for building a concept knowledge map according to the acquired electronic medical record by means of a tool set used in the work of a doctor;
the example map building module is used for extracting entities, events and relations from the electronic medical record by means of a tool set used in doctor work and building an example knowledge map;
and the integration module is used for fusing the nodes of the concept knowledge graph and the example knowledge graph by means of a tool set used in the doctor work to obtain the knowledge graphs of a plurality of specific disease fields.
Optionally, the electronic medical record of the hospital concerned includes clinical data of a professional hospital for treating a specific disease, diagnosis data and treatment data of a chief physician and above, and the data is divided into structured data and unstructured data.
Further optionally, the tool set used in the work of the related doctor comprises a doctor input tool, a doctor annotation tool, a rule base tool and an ER-OWL mapping tool;
the concept map building module builds a concept knowledge map by means of a doctor input tool, a rule base tool and an ER-OWL mapping tool;
and the example map building module builds the example map by means of a doctor labeling tool, a rule base tool and an ER-OWL mapping tool.
Further optionally, the specific operation of constructing the concept knowledge graph is as follows:
firstly, based on an electronic medical record of a hospital, a conceptual diagram construction module uses a doctor input tool to construct a universal medical word stock based on UMLS and a specific medical word stock in a specific disease field, wherein medical knowledge in the UMLS is stored in a database based on an ER data model;
and then, based on an ER-OWL mapping tool, mapping the structural data based on the ER data model in the UMLS into nodes based on an RDF data model, and constructing a conceptual knowledge graph based on the mapping nodes.
Further optionally, the doctor customizes a mapping rule of the ER-OWL mapping tool through a rule base tool, and the mapping rule specifically specifies a mapping relationship between a column of the ER data model and a node of the RDF data model in the mapping process.
Further optionally, the specific operation of constructing the example knowledge graph is as follows:
firstly, an instance graph constructing module labels unstructured data by means of a doctor labeling tool and stores labeling results in an entity corpus and a relation corpus;
and then, the instance knowledge graph construction module sequentially performs entity extraction and event extraction on the unstructured data based on the entity corpus, and further performs relation extraction based on the relation corpus, so that the instance knowledge graph is finally constructed.
Further optionally, with the support of a rule base tool and an entity corpus, the instance atlas construction module adopts an LSTM-CRF model/CRF model to extract entities and relationships.
Further optionally, in the process of constructing the example knowledge graph, the extracted entities and relationships are used as a training set of a machine learning method, so that the entities and relationships in different specific disease fields are extracted based on electronic medical records of hospitals.
Compared with the prior art, the medical health knowledge map system for the specific disease field has the beneficial effects that:
(1) the invention constructs the concept knowledge graph and the example knowledge graph by utilizing the electronic medical record of the hospital and the tool set used in the doctor work, and the nodes of the concept knowledge graph and the example knowledge graph are fused to construct the knowledge graph in the specific disease field, so that the accuracy of the construction of the medical health knowledge graph can be improved;
(2) the medical health knowledge map system can expand the specific disease field according to the acquired electronic medical records, has the advantages of reutilization and expandability, and can gradually cover the medical health knowledge map in the disease field.
Drawings
FIG. 1 is an architectural connection diagram of the present invention.
FIG. 2 is a schematic flow chart of the invention for constructing a knowledge graph;
FIG. 3 is a schematic flow diagram of the construction of a concept and example knowledge graph in accordance with the present invention.
The reference information in the drawings indicates:
1. the system comprises a data acquisition module 2, a concept map construction module 3, an example map construction module 4 and an integration module.
Detailed Description
In order to make the technical scheme, the technical problems to be solved and the technical effects of the present invention more clearly apparent, the following technical scheme of the present invention is clearly and completely described with reference to the specific embodiments.
The first embodiment is as follows:
with reference to fig. 1, 2 and 3, the present embodiment provides a medical health knowledge graph system for a specific disease field, which includes: the system comprises a data acquisition module 1, a concept map construction module 2, an example map construction module 3 and an integration module 4.
The data acquisition module 1 is used for acquiring electronic medical records of a hospital according to the requirements of doctors. The electronic medical record of a hospital comprises clinical data of a professional hospital for treating a specific disease, diagnosis data and treatment data of a chief physician and above levels, wherein the data is divided into structured data and unstructured data.
And the concept map construction module 2 is used for constructing a concept knowledge map according to the acquired electronic medical record by means of a tool set used in the work of a doctor. At this time, the tool set used in the doctor's work includes a doctor input tool, a rule base tool, and an ER-OWL mapping tool.
The specific operation of constructing the concept knowledge graph comprises the following steps:
firstly, based on an electronic medical record of a hospital, a conceptual diagram constructing module 2 constructs a universal medical word stock based on UMLS and a specific medical word stock in a specific disease field by using a doctor input tool, wherein medical knowledge in the UMLS is stored in a database based on an ER data model;
and then, based on an ER-OWL mapping tool, mapping the structural data based on the ER data model in the UMLS into nodes based on an RDF data model, and constructing a conceptual knowledge graph based on the mapping nodes.
In the process, a doctor customizes the mapping rule of the ER-OWL mapping tool through a rule base tool, and the mapping rule specifically specifies the mapping relation between the column of the ER data model and the node of the RDF data model in the mapping process.
And the example map construction module 3 is used for extracting entities, events and relations from the electronic medical record by means of a tool set used in the doctor work and constructing an example knowledge map. At this time, the tool set used in the doctor work comprises a doctor annotation tool, a rule base tool and an ER-OWL mapping tool.
The specific operation of constructing the example knowledge graph is as follows:
firstly, the instance atlas construction module 3 labels unstructured data by means of a doctor labeling tool and stores labeling results in an entity corpus and a relation corpus;
subsequently, under the support of a rule base tool and an entity corpus, the instance knowledge graph construction module 3 adopts an LSTM-CRF model to sequentially perform entity extraction and event extraction on unstructured data, further performs relationship extraction based on a relationship corpus, and finally completes construction of an instance knowledge graph.
In the process of constructing the example knowledge graph, the extracted entities and relations can be used as a training set of a machine learning method, so that the entities and relations in different specific disease fields can be extracted based on electronic medical records of hospitals.
And the integration module 4 is used for fusing the nodes of the concept knowledge graph and the example knowledge graph by means of a tool set used in the doctor work to obtain the knowledge graphs of a plurality of specific disease fields.
In summary, the medical health knowledge map system for the specific disease field is adopted, the electronic medical record of a hospital and the tool set used in the doctor work are utilized to construct the concept knowledge map and the example knowledge map, the node fusion of the concept knowledge map and the example knowledge map is fused, the knowledge map in the specific disease field is constructed, and the accuracy of the construction of the medical health knowledge map can be improved.
Based on the above embodiments of the present invention, those skilled in the art should make any improvements and modifications to the present invention without departing from the principle of the present invention, and therefore, the present invention should fall into the protection scope of the present invention.
Claims (8)
1. A medical health knowledge map system oriented to a specific disease field is characterized in that a structural framework of the system comprises:
the data acquisition module is used for acquiring the electronic medical record of the hospital according to the requirements of doctors;
the concept map building module is used for building a concept knowledge map according to the acquired electronic medical record by means of a tool set used in the work of a doctor;
the example map building module is used for extracting entities, events and relations from the electronic medical record by means of a tool set used in doctor work and building an example knowledge map;
and the integration module is used for fusing the nodes of the concept knowledge graph and the example knowledge graph by means of a tool set used in the doctor work to obtain the knowledge graphs of a plurality of specific disease fields.
2. The disease-specific medical health knowledge mapping system of claim 1, wherein the electronic medical record of the hospital comprises clinical data of a professional hospital for treating a specific disease, diagnosis data and treatment data of a chief physician and above, and the data is divided into structured data and unstructured data.
3. The disease-specific domain oriented medical health knowledge mapping system of claim 2, wherein the set of tools used in the doctor's work includes a doctor input tool, a doctor annotation tool, a rule base tool, an ER-OWL mapping tool;
the concept map building module builds a concept knowledge map by means of the doctor input tool, the rule base tool and the ER-OWL mapping tool;
and the example map building module builds an example map by means of the doctor labeling tool, the rule base tool and the ER-OWL mapping tool.
4. The system of claim 3, wherein the specific operations of constructing the concept knowledge graph are as follows:
firstly, based on the electronic medical record of the hospital, the concept graph constructing module uses the doctor input tool to construct a universal medical word stock based on UMLS and a specific medical word stock of a specific disease field, wherein medical knowledge in the UMLS is stored in a database based on an ER data model;
and then, based on an ER-OWL mapping tool, mapping the structural data based on the ER data model in the UMLS into nodes based on an RDF data model, and constructing a conceptual knowledge graph based on the mapping nodes.
5. The disease-specific area oriented medical health knowledge mapping system of claim 4, wherein the mapping rules of the ER-OWL mapping tool are customized by the doctor through the rule base tool, and the mapping rules specify the mapping relationship between the columns of the ER data model and the nodes of the RDF data model during the mapping process.
6. The system of claim 5, wherein the specific operations of constructing the example knowledge graph are as follows:
firstly, the instance atlas construction module labels unstructured data by means of the doctor labeling tool and stores labeling results in an entity corpus and a relation corpus;
and then, the example map construction module sequentially performs entity extraction and event extraction on the unstructured data based on the entity corpus, and further performs relation extraction based on the relation corpus, so that the construction of the example knowledge map is finally completed.
7. The system of claim 6, wherein the instance atlas module uses LSTM-CRF model/CRF model to extract entities and relationships with the support of rule base tools and entity corpus.
8. The system of claim 6, wherein the extracted entities and relationships are used as a training set of machine learning methods in constructing the instance knowledge graph to extract entities and relationships in different disease-specific domains based on electronic medical records of hospitals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252977.2A CN112966123A (en) | 2021-03-02 | 2021-03-02 | Medical health knowledge map system oriented to specific disease field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252977.2A CN112966123A (en) | 2021-03-02 | 2021-03-02 | Medical health knowledge map system oriented to specific disease field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112966123A true CN112966123A (en) | 2021-06-15 |
Family
ID=76277346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110252977.2A Pending CN112966123A (en) | 2021-03-02 | 2021-03-02 | Medical health knowledge map system oriented to specific disease field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112966123A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN115036034A (en) * | 2022-08-11 | 2022-09-09 | 之江实验室 | Similar patient identification method and system based on patient characterization map |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427735A (en) * | 2018-02-28 | 2018-08-21 | 东华大学 | Clinical knowledge map construction method based on electronic health record |
| CN110059195A (en) * | 2019-04-10 | 2019-07-26 | 华侨大学 | A kind of medical test knowledge mapping construction method based on LIS |
| CN110866124A (en) * | 2019-11-06 | 2020-03-06 | 北京诺道认知医学科技有限公司 | Medical knowledge graph fusion method and device based on multiple data sources |
| CN110929040A (en) * | 2019-10-30 | 2020-03-27 | 清华大学 | Knowledge graph construction method and device for specific medical field |
| CN110968650A (en) * | 2019-10-30 | 2020-04-07 | 清华大学 | Medical field knowledge graph construction method based on doctor assistance |
| CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
| CN112002411A (en) * | 2020-08-20 | 2020-11-27 | 杭州电子科技大学 | Cardiovascular and cerebrovascular disease knowledge map question-answering method based on electronic medical record |
-
2021
- 2021-03-02 CN CN202110252977.2A patent/CN112966123A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427735A (en) * | 2018-02-28 | 2018-08-21 | 东华大学 | Clinical knowledge map construction method based on electronic health record |
| CN110059195A (en) * | 2019-04-10 | 2019-07-26 | 华侨大学 | A kind of medical test knowledge mapping construction method based on LIS |
| CN110929040A (en) * | 2019-10-30 | 2020-03-27 | 清华大学 | Knowledge graph construction method and device for specific medical field |
| CN110968650A (en) * | 2019-10-30 | 2020-04-07 | 清华大学 | Medical field knowledge graph construction method based on doctor assistance |
| CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
| CN110866124A (en) * | 2019-11-06 | 2020-03-06 | 北京诺道认知医学科技有限公司 | Medical knowledge graph fusion method and device based on multiple data sources |
| CN112002411A (en) * | 2020-08-20 | 2020-11-27 | 杭州电子科技大学 | Cardiovascular and cerebrovascular disease knowledge map question-answering method based on electronic medical record |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN115036034A (en) * | 2022-08-11 | 2022-09-09 | 之江实验室 | Similar patient identification method and system based on patient characterization map |
| CN115036034B (en) * | 2022-08-11 | 2022-11-08 | 之江实验室 | Similar patient identification method and system based on patient characterization map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111061841B (en) | Knowledge graph construction method and device | |
| WO2020147758A1 (en) | Drug recommendation method and apparatus, medium, and electronic device | |
| CN110459320B (en) | Knowledge graph-based auxiliary diagnosis and treatment system | |
| CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
| US20130311483A1 (en) | Method and system for accurate medical-code translation | |
| Fette et al. | Information extraction from unstructured electronic health records and integration into a data warehouse | |
| CN112966123A (en) | Medical health knowledge map system oriented to specific disease field | |
| Ghiasvand et al. | Learning for clinical named entity recognition without manual annotations | |
| La-Ongsri et al. | Incorporating ontology-based semantics into conceptual modelling | |
| Agrawal et al. | Detecting modeling inconsistencies in SNOMED CT using a machine learning technique | |
| Lin et al. | An exploratory study using an openEHR 2-level modeling approach to represent common data elements | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| Sarkar | Methods in biomedical informatics: a pragmatic approach | |
| Sheng et al. | DEKGB: an extensible framework for health knowledge graph | |
| Agrawal et al. | A machine learning approach for quality assurance of snomed ct | |
| Kadhim et al. | A multi-intelligent agent system for automatic construction of rule-based expert system | |
| CN115295165A (en) | Knowledge graph system for medical science and decision-making auxiliary method thereof | |
| EP3937105A1 (en) | Methods and systems for user data processing | |
| Memarzadeh et al. | A graph database approach for temporal modeling of disease progression | |
| Tran et al. | Scaling out and evaluation of obsecan, an automated section annotator for semi-structured clinical documents, on a large VA clinical corpus | |
| Zubke et al. | Using openEHR archetypes for automated extraction of numerical information from clinical narratives | |
| US20230169265A1 (en) | Methods and systems for user data processing | |
| CN116737945B (en) | Mapping method for EMR knowledge map of patient | |
| CN110851459B (en) | Searching method and device, storage medium and server | |
| Tajouo et al. | Procedure for the Contextual, Textual and Ontological Construction of Specialized Knowledge Bases |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210615 |
|
| RJ01 | Rejection of invention patent application after publication |