CN110059195A - A kind of medical test knowledge mapping construction method based on LIS - Google Patents
A kind of medical test knowledge mapping construction method based on LIS Download PDFInfo
- Publication number
- CN110059195A CN110059195A CN201910284604.6A CN201910284604A CN110059195A CN 110059195 A CN110059195 A CN 110059195A CN 201910284604 A CN201910284604 A CN 201910284604A CN 110059195 A CN110059195 A CN 110059195A
- Authority
- CN
- China
- Prior art keywords
- entity
- medical test
- lis
- knowledge
- knowledge mapping
- 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
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
Abstract
The invention discloses a kind of medical test knowledge mapping construction method based on LIS, comprising: conceptual level design, instance layer study and LIS knowledge mapping application;Specifically, being designed using the true record in LIS system as knowledge base to the concept set of ken, the form expression of concept and conceptual relation is emphasized;It is true that the medical test to match with conceptual level is extracted from a large amount of LIS system record, medical test entity and relationship is extracted, and store in the form of triple, to obtain final medical test knowledge mapping;And medical test knowledge mapping is applied to examine two aspects of inquiry and reasonable check.Medical test knowledge mapping is constructed based on the truthful data in medical test document and LIS, and perfect general medical knowledge map can preferably serve high-level artificial intelligence medical applications;Meanwhile the nonproductive poll tool as doctor, the working efficiency of doctor is improved, and open up LIS systematic difference scene.
Description
Technical field
The present invention relates to knowledge mappings to create technical field, more particularly to a kind of medical test knowledge graph based on LIS
Compose construction method.
Background technique
The information of clinical laboratory's information system (laboratory information system LIS) realization clinical labororatory
Acquisition, storage, processing, transmission, inquiry, provide analysis and diagnosis is supported, assist laboratory physician to inspection application form and sample into
Row pretreatment, the automatic collection of inspection data or directly enters, inspection data processing etc..In LIS comprising patient essential information,
Every inspection data and examine diagnostic result etc., record medicine entity and its association, as patient's entity, essential information entity,
Examine entity, diagnosis entity etc. entities and its between relationship, wherein including that a large amount of medical test is true.Therefore, deeply
Excavating the medical test fact knowledge in LIS system will play a significant role for medical laboratory work improved efficiency.Knowledge mapping
It is the knowledge representation method of a kind of description entity and its connection, it is intended to describe the concept of objective world, entity, event and therebetween
Relationship there are knowledge semantic, data easily be associated with, easy characteristics such as expansion, be widely used in medical domain, occur a variety of
Medical knowledge map.But existing medical knowledge map is known from disclosed medical literature and Medical Dictionary handbook to obtain
Know, is not related to the building of medical test knowledge mapping and application based on LIS system proof of genuineness data.Therefore, with inspection
It tests based on the actual LIS record of section, by the help of expert, and with reference to international clinical term, constructs medical test knowledge
Map, by the good Structure of Knowledge Representation of knowledge mapping, high speed information inquiry and profound level relation inference the advantages that,
Medical test knowledge mapping is applied to examine two aspects of inquiry and reasonable check, can be used as the nonproductive poll tool of doctor,
The working efficiency of doctor is improved, LIS systematic difference scene is also opened up.
Summary of the invention
The object of the present invention is to provide a kind of methods based on LIS creation medical test knowledge mapping, utilize medical test
Truthful data in document and LIS constructs medical test knowledge mapping, general medical knowledge map is improved, to effectively assist
The work of doctor, improves the working efficiency of doctor, and is applied to inspection inquiry and legitimate check, and developing LIS system is answered
Use scene.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of medical test knowledge mapping construction method based on LIS, comprising the following steps:
S1: conceptual level design
S11: design medical test entity E, i.e., the medicine entity that can be uniquely identified in LIS system, comprising examining patient real
Body, essential information entity, pre- diagnosis entity and inspection entity;
S12: building entitative concept tree, the level Four entity that tissue medical test entity is included in the form of conceptional tree are general
It reads;
S13: defining medical test entity relationship R, and medical test entity relationship is expressed as different medical tests in inspection
The medical facts connection i.e. R { Ei, Ej } occurred between entity;Wherein, Ei and Ej respectively indicates two different medical tests
Entity;S14: define the medical test knowledge mapping G based on LIS system, included in clinical examination information by metadata
Composition, form be<Ei, R, Ej>;
S2: instance layer study
S21: formulating Knowledge Extraction rule, wherein for unstructured text data in LIS system, in Knowledge Extraction rule
On, it is handled by natural language processing technique;
S22: the entity in LIS data is carried out entity according to conceptual level by the Knowledge Extraction rule formulated according to step S21
Link, thus constructs instance layer;
S23: entity, relationship and entity triple are added in instance layer.The instance layer is counted according to conceptual level
According to instantiation as a result, being made of the triple of medical test entity and relationship;
S24: the triple store that step S23 is obtained forms medical test knowledge mapping in Neo4j chart database.
S3:LIS knowledge mapping applies S31: LIS knowledge mapping being applied to examine inquiry, realizes knowledge based map
Any element searches for other relevant information in triple;S32: LIS knowledge mapping is applied to reasonable check, is closed by reasoning
Multiple inspection projects that connection discovery clinician is opened are with the presence or absence of repetition, hence into warning and the state that reports an error.
Compared to the prior art, the invention has the following advantages: improving general medical knowledge map, and by knowledge
The advantages that relation inference of the good Structure of Knowledge Representation of map, the information inquiry of high speed and profound level, medical test is known
Application of the graphic chart is known in examining two aspects of inquiry and reasonable check, opens up LIS systematic difference scene;Auxiliary as doctor is looked into
Inquiry tool improves the working efficiency of doctor.Invention is further described in detail with reference to the accompanying drawings and embodiments;But this hair
A kind of bright medical test knowledge mapping construction method based on LIS is not limited to the embodiment.
Detailed description of the invention
Fig. 1 is the schematic diagram based on medical test knowledge mapping conceptual level design (part);
Fig. 2 is the schematic diagram based on medical test knowledge mapping hierarchical structure;
Fig. 3 is the schematic diagram of medical test knowledge mapping conceptual level structure;
Fig. 4 is the visual schematic diagram of medical test knowledge mapping;
Fig. 5 is the schematic diagram of the inquiry application of medical test knowledge;
Fig. 6 is the schematic diagram of the reasonable check application of medical test knowledge.
Specific embodiment
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, those skilled in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
The present embodiment, by taking the blood routine examination in medical test as an example, table 1 is the LIS record of a patient.
The blood routine examination of 1 patient Zhang San of table records
Referring to FIG. 1 to FIG. 4, a kind of medical test knowledge mapping construction method based on LIS of the invention, including with
Lower step: (1) conceptual level designs;(2) instance layer learns;(3) application of LIS knowledge mapping.
Step 1, conceptual level designs.
In medical test knowledge mapping building module, first have to do is exactly to be designed to its conceptual level, to obtain
Concept template on to entire map just can be carried out next step instance layer learning procedure based on this.Therefore, conceptual level design is to know
Know the essential first step in map construction.
Step 11: medical test entity design
The formal definitions of medical test entity are provided first.
It defines 1 (medical test entity E): medical test entity E and refers to the medicine that can uniquely identify in LIS system reality
Body.Medical test entity E includes examining patient's entity, essential information entity, pre- diagnosis entity and examining entity these fourth types concept.
The level Four entitative concept for being included with the form tissue medical test entity of conceptional tree.Level-one entitative concept (i.e. root
Node) it is medical test entity, secondary entity concept includes essential information, and patient examines, diagnoses entity in advance;Three-level entity is general
Thought is inspection etc., and level Four entitative concept is inspection project etc..In addition, other specific concepts are put into corresponding high-level concept
Child node in.Blood routine, liver function are such as checked that class instance is placed in the child node for examining this high-level concept of entity.
Step 12: the design of medical test entity relationship
The formal definitions of medical test entity relationship are provided first.
Define 2 (the relationship R of medical test entity): medical test relations of fact indicates that different medical tests are real in the inspection
The medical facts connection i.e. R { Ei, Ej } occurred between body, wherein Ei, Ej are medical test entity.Each medicine relations of fact is equal
There is the field of unique identification.
According to LIS system informations, following several clinical medical inspection relations of fact types are designed, are specifically included:
(1) subclass_of relationship: the membership between presentation-entity A and entity B.
(2) instance_of relationship: the example relationship between presentation-entity A and entity B, i.e. entity B are one of entity A
Example.
(3) attribute_of relationship: presentation-entity A is the attribute value of entity B.
(4) diagnosis relationship: indicate that patient's entity A possesses diagnostic result entity B.
(5) diseases relationship: indicate between name of disease entity A and patient's entity B there are disease relationships.
(6) it detect relationship: indicates to examine entity subtype entity A and patient's entity B is detection relationship.
On the basis of defining above-mentioned clinical medical inspection entity and medicine relations of fact, the medicine based on LIS system
Examine the formal definitions of knowledge mapping as follows:
Define 3 (medical test knowledge mapping G): medical test knowledge mapping includes a large amount of clinical examination information, these
Information by a rule<Ei, R, Ej>form metadata formed.Wherein Ei, Ej respectively indicate two different medical tests
Entity.
In summary, the medical test knowledge mapping conceptual level that the present invention creates includes level Four entitative concept, conceptual level knot
Structure such as Fig. 3.
Step 2, instance layer learns.
Step 21: formulating Knowledge Extraction rule
From LIS system record in structuring and semi-structured data carry out Knowledge Extraction, wherein for non-in LIS system
Structured text data, such as pre- diagnosis, due to its format freedom, in Knowledge Extraction rule, by natural language processing
Technology is handled;
Step 22: construction instance layer
According to prepared Knowledge Extraction rule, the entity in LIS data is subjected to entity link according to conceptual level, thus
Construct instance layer.According to table 1, the LIS data record of patient " Zhang San " is mapped to the conceptual level of Fig. 1, realizes example
Change.For example, patient's " Zhang San " case attribute value " 46364062 " is mapped to patient's entity class, the reality of patient's entity is realized
Exampleization.Equally, the name of " Zhang San ", gender and age are mapped to " essential information " entity, realize instantiation.With it is such
It pushes away, other LIS data records of patient " Zhang San " may map in the tree-like concept map of Fig. 1, realize medical test concept
The primary instantiation of figure.
Step 3: building medical test knowledge mapping
Entity, relationship and entity triple are added in instance layer E.The instance layer is that data reality is carried out according to conceptual level
Exampleization as a result, be made of the triple of medical test entity and relationship, and by triple store in Neo4j chart database
In, form medical test knowledge mapping.
Step 3, the application of LIS knowledge mapping.
After the medical test knowledge mapping for having constructed certain scale, the application scenarios of knowledge mapping are further inquired into, and are opened up
Show that medical knowledge map is applied of both inspection inquiry and reasonable check.
It is inquired for examining, it is able to achieve any element in knowledge based map triple and searches for other relevant information.
Inspection project entity associated with " esophageal neoplasm " pre- diagnosis entity and sample entity are illustrated as shown in Figure 5, and further
Illustrate the attribute and its value for examining project entity.For reasonable check, it is similar to duplicate checking and error correction, can find clinician
The multiple inspection projects opened are with the presence or absence of repetition.It illustrates as shown in Figure 6, when " WBC " examines item and " PLT " to examine item simultaneously
It is present in the inspection project that doctor is opened, medical test knowledge mapping is associated with by reasoning, into warning and the state that reports an error.
The medical test knowledge mapping that the present invention constructs has good Structure of Knowledge Representation, the information of high speed is inquired and deep
The advantages that relation inference of level, improves the working efficiency of doctor as the nonproductive poll tool of doctor, and has opened up LIS system
The application scenarios of system.Since LIS data have timeliness, the time is more long, and patient assessment's record is more, and therefore, medical test is known
Know map needs to be continuously updated and safeguard, new data is also one of the work following herein with the update of merging of former data.
The above is only a specific embodiment of the present invention, but the design concept of the present invention is not limited to this, all to utilize this
Design makes a non-material change to the present invention, and should all belong to behavior that violates the scope of protection of the present invention.
Claims (1)
1. a kind of medical test knowledge mapping construction method and system based on LIS, which comprises the steps of:
S1: conceptual level design
S11: design medical test entity E, i.e., the medicine entity that can be uniquely identified in LIS system, including examine patient's entity, base
This information entity, pre- diagnosis entity and inspection entity;
S12: building entitative concept tree, the level Four entitative concept that tissue medical test entity is included in the form of conceptional tree;
S13: defining medical test entity relationship R, and medical test entity relationship is expressed as different medical test entities in inspection
Between occurred medical facts connection i.e. R { Ei, Ej };Wherein, Ei and Ej respectively indicates two different medical test entities;
S14: defining the medical test knowledge mapping G based on LIS system, wherein included clinical examination information is by metadata group
It is<Ei at, form, R, Ej>;S2: instance layer learns S21: Knowledge Extraction rule is formulated, wherein for non-structural in LIS system
Change text data, in Knowledge Extraction rule, is handled by natural language processing technique;
S2: instance layer study
S21: formulating Knowledge Extraction rule, wherein for unstructured text data in LIS system, in Knowledge Extraction rule,
It is handled by natural language processing technique;
S22: the entity in LIS data is carried out chain of entities according to conceptual level by the Knowledge Extraction rule formulated according to step S21
It connects, thus constructs instance layer;
S23: entity, relationship and entity triple are added in instance layer;The instance layer is that data reality is carried out according to conceptual level
Exampleization as a result, being made of the triple of medical test entity and relationship;
S24: the triple store that step S23 is obtained forms medical test knowledge mapping in Neo4j chart database;
The application of S3:LIS knowledge mapping
S31: LIS knowledge mapping being applied to examine inquiry, realizes that any element search is other in knowledge based map triple
Relevant information;
S32: being applied to reasonable check for LIS knowledge mapping, is associated with multiple inspection items that discovery clinician is opened by reasoning
Mesh is with the presence or absence of repetition, hence into warning and the state that reports an error.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284604.6A CN110059195A (en) | 2019-04-10 | 2019-04-10 | A kind of medical test knowledge mapping construction method based on LIS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284604.6A CN110059195A (en) | 2019-04-10 | 2019-04-10 | A kind of medical test knowledge mapping construction method based on LIS |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110059195A true CN110059195A (en) | 2019-07-26 |
Family
ID=67318686
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910284604.6A Pending CN110059195A (en) | 2019-04-10 | 2019-04-10 | A kind of medical test knowledge mapping construction method based on LIS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110059195A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
CN111291568A (en) * | 2020-03-06 | 2020-06-16 | 西南交通大学 | Automatic entity relationship labeling method applied to medical texts |
CN111651614A (en) * | 2020-07-16 | 2020-09-11 | 宁波方太厨具有限公司 | Method and system for constructing medicated diet knowledge graph, electronic equipment and storage medium |
CN111986799A (en) * | 2020-07-06 | 2020-11-24 | 北京欧应信息技术有限公司 | Orthopedics knowledge graph construction system taking joint movement function as core |
CN112466463A (en) * | 2020-12-10 | 2021-03-09 | 求臻医学科技(北京)有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
CN112966123A (en) * | 2021-03-02 | 2021-06-15 | 山东健康医疗大数据有限公司 | Medical health knowledge map system oriented to specific disease field |
EP3844683A4 (en) * | 2019-11-05 | 2021-12-15 | Pomicell Ltd. | A system and method for generating and interacting with interactive multilayered data models |
EP4068121A4 (en) * | 2019-11-25 | 2023-04-26 | BOE Technology Group Co., Ltd. | Method and apparatus for acquiring character, page processing method, method for constructing knowledge graph, and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180089383A1 (en) * | 2016-09-29 | 2018-03-29 | International Business Machines Corporation | Container-Based Knowledge Graphs for Determining Entity Relations in Medical Text |
CN108427735A (en) * | 2018-02-28 | 2018-08-21 | 东华大学 | Clinical knowledge map construction method based on electronic health record |
CN109145120A (en) * | 2018-07-02 | 2019-01-04 | 北京妙医佳信息技术有限公司 | The Relation extraction method and system of medical health domain knowledge map |
CN109299285A (en) * | 2018-09-11 | 2019-02-01 | 中国医学科学院医学信息研究所 | A kind of pharmacogenomics knowledge mapping construction method and system |
-
2019
- 2019-04-10 CN CN201910284604.6A patent/CN110059195A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180089383A1 (en) * | 2016-09-29 | 2018-03-29 | International Business Machines Corporation | Container-Based Knowledge Graphs for Determining Entity Relations in Medical Text |
CN108427735A (en) * | 2018-02-28 | 2018-08-21 | 东华大学 | Clinical knowledge map construction method based on electronic health record |
CN109145120A (en) * | 2018-07-02 | 2019-01-04 | 北京妙医佳信息技术有限公司 | The Relation extraction method and system of medical health domain knowledge map |
CN109299285A (en) * | 2018-09-11 | 2019-02-01 | 中国医学科学院医学信息研究所 | A kind of pharmacogenomics knowledge mapping construction method and system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
CN110990579B (en) * | 2019-10-30 | 2022-12-02 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
EP3844683A4 (en) * | 2019-11-05 | 2021-12-15 | Pomicell Ltd. | A system and method for generating and interacting with interactive multilayered data models |
EP4068121A4 (en) * | 2019-11-25 | 2023-04-26 | BOE Technology Group Co., Ltd. | Method and apparatus for acquiring character, page processing method, method for constructing knowledge graph, and medium |
CN111291568A (en) * | 2020-03-06 | 2020-06-16 | 西南交通大学 | Automatic entity relationship labeling method applied to medical texts |
CN111291568B (en) * | 2020-03-06 | 2023-03-31 | 西南交通大学 | Automatic entity relationship labeling method applied to medical texts |
CN111986799A (en) * | 2020-07-06 | 2020-11-24 | 北京欧应信息技术有限公司 | Orthopedics knowledge graph construction system taking joint movement function as core |
CN111651614A (en) * | 2020-07-16 | 2020-09-11 | 宁波方太厨具有限公司 | Method and system for constructing medicated diet knowledge graph, electronic equipment and storage medium |
CN112466463A (en) * | 2020-12-10 | 2021-03-09 | 求臻医学科技(北京)有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
CN112466463B (en) * | 2020-12-10 | 2023-08-18 | 求臻医学科技(浙江)有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
CN112966123A (en) * | 2021-03-02 | 2021-06-15 | 山东健康医疗大数据有限公司 | Medical health knowledge map system oriented to specific disease field |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110059195A (en) | A kind of medical test knowledge mapping construction method based on LIS | |
US20240152542A1 (en) | Ontology mapping method and apparatus | |
US11625424B2 (en) | Ontology aligner method, semantic matching method and apparatus | |
Pearl | The foundations of causal inference | |
CN109543047A (en) | A kind of knowledge mapping construction method based on medical field website | |
CN108427735A (en) | Clinical knowledge map construction method based on electronic health record | |
CN110036383A (en) | Knowledge based engineering electronic health record Automatic signature extraction | |
Li | Lom: A lexicon-based ontology mapping tool | |
Abdul Manaf et al. | The current state of SKOS vocabularies on the web | |
CN110600121B (en) | Knowledge graph-based primary etiology diagnosis method | |
AU2015258752A1 (en) | Putative ontology generating method and apparatus | |
US20170061001A1 (en) | Ontology browser and grouping method and apparatus | |
CN112420212B (en) | Method for constructing brain stroke traditional Chinese medicine knowledge graph | |
WO2012128435A1 (en) | Significance parameter extraction method and its clinical decision support system for differential diagnosis of abdominal diseases based on entropy rough approximation technology | |
Zhang et al. | OIM-SM: A method for ontology integration based on semantic mapping | |
CN114091675A (en) | Traceability reasoning method and system | |
Cui | Competency evaluation of plant character ontologies against domain literature | |
Sahay et al. | A methodological approach for ontologising and aligning health level seven (hl7) applications | |
Diederich et al. | Creating domain specific metadata for scientific data and knowledge bases | |
CN115344713A (en) | Disease prediction method based on disease diagnosis standard knowledge graph | |
Rachmawati et al. | The Comparison between Bayes and Certainty Factor Method of Expert System in Early Diagnosis of Dengue Infection | |
Velios et al. | Typed properties and negative typed properties: dealing with type observations and negative statements in the CIDOC CRM | |
Keivanloo et al. | Clone detection meets semantic web-based transitive closure computation | |
Thiéblin et al. | Cross-querying LOD data sets using complex alignments: an experiment using AgronomicTaxon, Agrovoc, DBpedia and TAXREF-LD | |
Capurro et al. | Clinicaltime: Identification of patients with acute kidney injury using temporal abstractions and temporal pattern matching |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |