KR20170101658A - System for generating shareable medical knowledge and method thereof - Google Patents

Abstract

A system and a method for generating shareable medical knowledge are disclosed. A concept control part of the system performs a control operation to select a concept of a clinical model through a user interface providing an intelli-sense function and controls provision of syntax artifacts used to generate a standardized-medical logic module. An ontology mapping part provides mutual mapping information between the concept of the selected clinical model, a standard data model and standard term information. The medical logic module generator obtains mutual mapping information among the concept of the clinical model, a module of the standard data model and the standard term information with respect to the concept of the clinical module, which is selected through the user interface, through the concept control part and the ontology mapping part and generates a standardized-medical logic module corresponding to the concept of the clinical module by using the syntax artifacts corresponding to the concept of the clinical model.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a system and method for generating shareable medical knowledge,

The present invention relates to a system and method for generating shareable medical knowledge.

The Clinical Decision Support System (CDSS) is an effective service model that creates a coordinated path between patients and physicians by generating timely, accurate recommendations, alerts, and urge. The accuracy and effectiveness of these recommendations and warnings depends on the latest information base of the CDSS. However, the key barrier to implementing CDSS is to create, enhance, and manage knowledge bases and propagate existing knowledge of CDSS.

The technical solution to these barriers is to create a shareable and interoperable knowledge base. The HL7 (Health Level 7) community has proposed a standardized representation of knowledge rules in the form of a Medical Logic Module (MLM) using the Arden Syntax.

On the other hand, the main barrier in knowledge collection tools is the heterogeneity of the clinical information model. The CDSS community has recommended a standardized information model to address the heterogeneity of this information model. The use of the standard terms of the standard data model vMR (virtual medical record) and the SNOMED CT (standardized nomenclature of medicine clinical terms) has improved the sharing of the knowledge base, which has led to the introduction of legacy hospital management and information systems , HMIS) has become easier to integrate. On the other hand, the complexity of the Arden syntax has increased to beyond its own complexity, and the dependence of the vMR schema classes and doctors who need to remember the SNOMED CT concept has increased. In order to solve this complexity problem and to improve doctors' work on MLM generation, a user-friendly environment is required.

The present invention provides a system and method for generating shared medical knowledge that allows physicians to easily generate medical knowledge while generating increased medical knowledge such as sharing possibility, scalability and usability do.

According to an aspect of the present invention,

The concept of controlling the provision of syntactic artifacts used for the conceptual selection of a clinical model through a user interface providing an intelli-sense function and for the standardized medical logic module generation A control unit; An ontology mapping unit for providing mutual mapping information between a concept of a selected clinical model, a standard data model, and standard term information; And acquiring mutual mapping information between the concept of the clinical model, the model of the standard model, and the standard term information through the concept control section and the ontology mapping section with respect to the concept of the clinical model selected through the user interface, And a medical logic module generator for generating a standardized medical logic module corresponding to the concept of the clinical model using a syntax artifact corresponding to the concept of the model.

Here, a mapping storage unit for storing and managing mutual mapping information between a concept of a clinical model, a standard data model, and standard term information provided by the ontology mapping unit; A storage layer for providing different types of concepts and artifacts used in rule generation corresponding to the concept of the clinical model and in the standardized medical logic module generation process; And performing a contextual selection using a tree of intelligence-sense function and a clinical model through the user interface. In the process of generating a medical logic module, the concept of the clinical model, the standard data model, the standard term information, And a query management unit for providing the facts.

In addition, the concept control unit may include a clinical model concept controller for providing a tree of a clinical model through the user interface to perform control so that a concept of a clinical model can be selected; An intelligent-sense controller that provides configurable values for the selected concept in the immediate-execution window for accurate value selection for the concept of the clinical model; And an artifact controller that provides a syntax artifact to be used during conversion of the concept into a medical logic module.

The ontology mapping unit may further include: a first mapper for providing mapping information between a concept of the clinical model and a standard data model; A second mapper providing mapping information between the concept of the clinical model and standard term information; And a third mapper providing mapping information between the standard data model and standard term information.

The mapping storage unit may further include: a first mapping storage unit for storing and managing mapping information between a concept of the clinical model and a standard data model, the mapping information being provided by the first mapper; A second mapping storage for storing and managing mapping information between the concept of the clinical model and standard term information provided by the second mapper; And a third mapping storage unit for storing and managing mapping information between the standard data model and standard term information provided by the third mapper.

In addition, the storage layer unit may include a domain ontology for managing concepts and code information corresponding to standard terminology information; A standard data model ontology that manages the information used to fetch the standard data model and the corresponding mapping between the standard term information and the clinical model; A clinical model ontology that manages the tree information of the clinical model and manages the information used to select concepts from the tree of clinical models during rule generation and the corresponding mapping of clinical models and standard data models and standard terminology information; And an artifact storage for managing the syntax artifacts used during the creation of the medical logic module.

The query management unit may include a first query manager for providing query information required by the third mapping storage unit through a query of standard term information managed in the domain ontology; A second query manager for providing query information required by the artifact controller through a query of a syntax artifact managed in the artifact storage; A third query manager for providing query information required by the first mapping storage unit through querying of tree information and mapping information of a clinical model managed in the clinical model ontology; And a fourth query manager for providing query information required by the first mapper through a query of a standard data model and mapping information managed in the standard data model ontology.

In the case of the concept selection of the clinical model through the intelligence-sense function of the user interface, the query management unit queries the query information requested by the mapping storage unit through the storage layer unit, To the user.

The query management unit may query the query information requested by the mapping storage unit through the storage layer when the medical logic module corresponding to the selected clinical model is requested through the user interface, To the mapper.

The standardized medical logic module is a Medical Login Module (MLM) based on HL7 Arden Syntax, and the syntax artifact is a Syntactic Artifact based on HL7 Arden Syntax.

Also, the clinical model is HL7 DCM (Domain Clinical Model), the standard data model is HL7 vMR (virtual medical record), and the standard term information is HL7 SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) .

According to another aspect of the present invention,

CLAIMS What is claimed is: 1. A method of generating a standardized medical logic module corresponding to a medical knowledge, the method comprising: acquiring concept information of a clinical model through a user interface; Obtaining standard data models and standard terminology information mapped to concepts of the obtained clinical model; Obtaining a syntactic artifact corresponding to a concept of the obtained clinical model, a standard data model, and standard English information; And generating a standardized medical logic module corresponding to the concept of the obtained clinical model using the obtained syntax artifacts.

Here, the step of acquiring the concept information of the clinical model includes the steps of: providing a tree of the clinical model through a user interface providing an intell-sense function; And selecting a concept of the clinical model from the user via a tree of provided clinical models.

Also, the step of obtaining the standard data model and the standard term information may include obtaining information of a standard data model that is mapped to a concept of the selected clinical model; And obtaining information of a standard term that is mapped to information of a standard data model to be obtained.

Also, before the step of obtaining the concept information of the clinical model, providing a tree of clinical models through the user interface; Obtaining a standard data model and standard term information mapped to a concept of a clinical model selected by a user through a tree of the clinical model; And providing concept information of the clinical model together with the standard data model and standard term information obtained through the user interface.

According to the present invention, doctors can very easily select the necessary concepts and their values, thereby reducing the effort of physicians to remember all the concepts.

In addition, increased medical knowledge such as shareability, scalability, and usability can be generated.

1 is a configuration block diagram of a medical knowledge generation system according to an embodiment of the present invention.
2 is a diagram showing a mapping relationship between a DCM and a vMR used in a medical knowledge generation system according to an embodiment of the present invention, a mapping between a DCM and a SNOMED CT, and a mapping relationship between a vMR and a SNOMED CT.
3 is a flowchart of a method of providing an intelligent-sense function according to an embodiment of the present invention.
4 is a flowchart of an MLM generation method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

During patient care, the CDSS helps doctors diagnose the disease and provide treatment instructions for these diagnoses. The latest knowledge base is a major issue of CDSS, and this should continue to be improved using domain knowledge collection. The sharing of knowledge between different medical institutions saves doctors time by the use of knowledge generated in the form of the Arden Syntax MLM. The standardized representation of the knowledge of the Arden syntax MLM is tedious for physicians. Thus, the main motivation of the system according to the present invention is to provide a user-friendly environment that enables doctors to easily generate shareable knowledge.

The vMR-based knowledge collection tool was developed to generate the Arden Syntax MLM using the ADEN Syntax and Test Environment IDE in CDSS. The system uses an interface that creates a standard vMR to integrate with an external database. However, only a skilled physician using the Arden syntax and vMR can create rules using these systems, and doctors unfamiliar with vMR and Arden syntax are difficult to create rules using such a system. The Arden Syntax IDE can improve integration with other clinical information systems by using its own terminology instead of the standard terminology when creating MLMs.

The above-mentioned Arden Syntax MLM is a major source of generating shared clinical knowledge, but it is a complex and tedious task for physicians due to its complex syntax and structure. One of the limitations of these systems is the absence of a user-friendly environment for creating and managing Arden Syntax MLMs. Most of these systems lack standard data models and standard terminology. MLM requires standard data models and standard terminology to improve the integration of the knowledge base of legacy systems in hospitals and healthcare institutions. On the other hand, the complexity of the MLM can be increased by integrating standard data models and terms into the collection tool.

Doctors often face difficulties when writing MLMs using the complex syntax and structure of the Arden syntax. Therefore, a user-friendly environment should be able to help doctors create and manage MLM's medical knowledge base. The system of the present invention provides a concept of complex Arden syntax and its structure. Doctors do not need to have expert knowledge of the Arden syntax and do not have to remember all of the MLM slots. The doctors automatically generate the corresponding MLMs as long as the physicians have a fairly easy approach to the meta information needed for the rule, the facts they need, and the judgment of the rule. The system provides intelli-sense functionality from the immediate window and the clinical model tree on the interface during the creation of facts and conclusions in the prescribed slots. This capability makes it very easy for physicians to choose the concepts and values they need, and reduces the need for physicians to remember all the concepts.

The automatic generation of MLM through the immediate execution window and the intelligent-sense function and the clinical model tree are performed by the Domain Clinical Model (DCM) and the Semantic Reconciliation model (SRM). DCM defines the subdomain of clinical information that is commonly used in a particular clinical area and which is currently being addressed by the HNC (Head and Neck Cancer) domain concept in a collaborating hospital. We have used appropriate CIMP (Clinical Information Modeling Process) based on researching semantics in concept, created ontology, and verified semantics.

On the other hand, SRM based on mapping between DCM concept and SNOMED CT increases sharing possibilities, mapping between SNOMED CT and vMR data model for intelligence-sense increases sharing and scalability, and vMR data model and DCM concept Mapping increases user-friendliness and shareability. The doctors select the necessary concept from the DCM tree or IntelliSense window to fetch the values set from the SNOMED CT.

Hereinafter, a medical knowledge generation system according to an embodiment of the present invention will be described in detail.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have.

1 is a configuration block diagram of a medical knowledge generation system according to an embodiment of the present invention.

1, the medical knowledge generation system 10 according to an embodiment of the present invention includes a user interface 100, a concept control unit 200, an ontology mapping unit 300, a mapping storage unit 400 A storage layer unit 500, a query management unit 600, an MLM generator 700, and an MLM storage unit 800.

The user interface 100 provides the functionality of a user-friendly interface. That is, the user interface 100 provides an easy-to-use environment for doctors to translate their knowledge, experiences, and practices into the Arden syntax MLM.

The user interface 100 provides a DCM tree to select the desired concepts and enables doctors to make contextual choices of concepts and values as needed through an intelligent-sense immediate execution window.

The MLM is created using the standard data model vMR and the standard term SNOMED CT, which hides the complex vMR data model classes and their attributes so that doctors do not have to remember all the complex syntax and structure of the MLM. That is, the doctors only have to select the necessary concept using the clinical model tree provided through the user interface 100.

The concept control unit 200 forms facts, conclusions, conditions, etc. that constitute rules through different combinations of different concepts, configurations, processors and values.

The rules are expressed in the Arden Syntax MLM and have a standard structure and structure. Accordingly, a concept control unit 200 is needed to handle all types of concepts and configurations.

To this end, the concept control unit 200 includes a DCM concept controller 210, an Intelli-sense controller 220, and an Arden Artifacts controller 230.

The DCM concept controller 210 controls the DCM tree provided through the user interface 100 so that the expert can select a necessary concept.

The intelligent-sense controller 220 fetches the configurable values for the selected concept in the immediate execution window and provides it to the expert to select the correct value for the concept.

The Arden Artifacts controller 230 controls the system 10 to fetch the appropriate and correct artifacts of the Arden syntax while converting the rules into the Arden syntax MLM.

Meanwhile, the concept control unit 200 uses a different type of mapper and repository to handle corresponding concepts during rule generation and MLM generation.

The ontology mapping unit 300 provides three types of mapping used by the concept control unit 200 to handle the concept. For example, as shown in FIG. 2, ontology mapper 300 provides a mapping between DCM and vMR, a mapping between DCM and SNOMED CT, and a mapping between vMR and SNOMED CT. This mapping can be performed through SRM.

To this end, the ontology mapping unit 300 includes a DCM-vMR mapper 310, a DCM-SNOMED mapper 320, and a vMR-SNOMED mapper 330.

Referring to Figure 2, the relationship of the mapping 301 between DCM and vMR is shown. Understanding and remembering both vMR schema classes and their attributes will be a tedious task for doctors. Thus, in the user interface 100, DCM concepts are provided to physicians instead of vMR schema classes and attributes. The DCM concept is mapped to the corresponding vMR classes and attributes with the support of a team of doctors and knowledge engineers. This mapping (301) between DCM and vMR achieves the goal of user friendliness and shareability, and these mappings (301) are provided by DCM-vMR mapper (310).

Referring to Figure 2, the relationship of the mapping 302 between DCM and SNOMED CT is shown. The use of standard information models and terminology improves the scalability and shareability of knowledge collection tools. In the SRM model, the DCM concept has been mapped to the SNOMED CT concept to achieve a shareability target. In the user interface 100, when the doctors select the required DCM concept, at the back-end, the selected DCM concept is represented by the SNOMED CT code. This mapping 302 is performed by the DCM-SNOMED mapper 320.

Referring to FIG. 2, the relationship of the mapping 303 between vMR and SNOMED CT is shown. With this type of mapping 303, the goals of sharing and intelligence-sense can be achieved. The DCM concept coverage can be negotiated in any situation, for example, in situations where doctors need to select a "missing value" from the SNOMED CT. In this case, the medical knowledge generation system 10 according to the embodiment of the present invention provides an intelligent-sense function in the immediate execution window, which provides the configurable values of the DCM concept selected from the SNOMED CT, . The vMR schema classes and their attributes are mapped to the corresponding top-level concept of SNOMED CT and are demonstrated by doctors and domain experts in the HL7 community. These mappings 303 are processed by the vMR-SNOMED mapper 330.

The mapping storage unit 400 stores mapping information used in the ontology mapping unit 300. These mappings need to be continuously accessed in real time by the mapping storage unit 400 at rule creation.

The mapping storage unit 400 includes a DCM-vMR mapping storage unit 410 for storing DCM-vMR mapping information used by the DCM-vMR mapper 310, a DCM- A DCM-SNOMED mapping storage 420 for storing SNMED mapping information, and a vMR-SNOMED mapping storage 430 for storing vMR-SNOMED mapping information used by the vMR-SNOMED mapper 330.

The mappings stored and managed in the mapping storage unit 400 are also needed for the contextual selection from the intelligent-sense window as well as the MLM generation process.

The storage layer 500 provides different types of concepts and artifacts used in rule generation and MLM generation.

To this end, the storage layer 500 includes a domain ontology 510, a vMR ontology 520, a DCM ontology 530, and an artifact repository 540.

The domain ontology 510 manages values that can be set for each concept to improve performance in the intelligent-sense search process. In particular, the domain ontology 510 manages the SNOMED CT concept and code information.

The vMR ontology 520 manages the information used to fetch the corresponding mapping between vMR and SNOMED CT and DCM.

The DCM ontology 530 manages the DCM tree information and manages the information used to select concepts from the DCM tree and fetch the corresponding mappings between DCM and vMR and SNOMED CT during rule generation. This DCM ontology 530 is constructed with the most understandable and usable concept in legacy HMIS (Hospital Management and Information System). Physicians will find it very easy to use the concept of the DCM ontology (117).

Artifact store 540 manages the Arden Syntax artifacts used during MLM generation.

The query management unit 600 manages queries used in the internal process of performing contextual selection using the intelligence-sense function and the DCM tree.

This query manager 600 is also used during MLM generation and includes four submodules to process different queries at different times: the SNOMED query manager 610, the artifacts query manager 620, the DCM query manager 630, And a vMR query manager 640.

The SNOMED query manager 610 is used in the contextual selection process of the intelligent-sense function process for fetching configurable values from the domain ontology 510. The SNOMED query manager 510 also manages queries to fetch the SNOMED CT concept and code during MLM generation.

Artifacts query manager 520 loads the Arden Syntax artifacts used during MLM generation from artifacts repository 540.

The DCM query manager 530 loads the DCM tree through the DCM ontology 530 and is used to select concepts from the DCM tree and fetch the corresponding mappings of the DCM and vMR and SNOMED CT during rule generation.

The vMR query manager 540 is used to provide an intelligent-sense function when generating MLMs via the vMR ontology 520 and in providing corresponding mappings between vMR and SNOMED CT and DCM.

The MLM generator 700 generates an MLM corresponding to the DCM concept generated through the user interface 100 by physicians according to the standard structure and syntax of the rule, and stores the generated MLM in the MLM storage 800 .

The complex process of the MLM generator 700 converting rules into MLMs is performed automatically and is carried out hidden by physicians. The MLM generator 700 combines the SNOMED CT code and the vMR schema classes into the generated MLM to improve interoperability and shareability of the knowledge base.

As described above, the clinical medical knowledge generation system 10 according to the embodiment of the present invention provides a multi-model and user-friendly environment for generating a shareable knowledge base. The system 10 provides a concept for the standard vMR data model and SNOMED CT by using SRM and DCM. The doctor does not need to remember both the vMR schema and the SNOMED CT concept used to create the rule. The system 10 is equipped with an intelligent-sense function to remind the SNOMED CT concept and the DCM concept. The physician uses the intelligent-sensor window to easily select the necessary concepts and their corresponding values. This increases physician work efficiency and reduces errors during MLM generation. When a physician uses the intelligence-sense and DCM concepts to create rules according to their knowledge, the system 10 uses the standard data model vMR and SNOMED CT codes to transform the rules into the Arden syntax MLM through a hidden process. Thus, the physician does not need to understand or understand the entire syntax and artifacts of the Arden syntax MLM.

Hereinafter, an intelligent-sense function providing method according to an embodiment of the present invention will be described with reference to the drawings.

3 is a flowchart of a method of providing an intelligent-sense function according to an embodiment of the present invention.

Referring to FIG. 3, a doctor or an expert (hereinafter, referred to as 'user') who wishes to generate a rule for generating and providing shareable medical knowledge through the medical knowledge generation system 10 according to an embodiment of the present invention, The DCM concept controller 220 provides a DCM tree through the user interface 100 (S110).

When the user selects the DCM concept through the user interface 100 (S120), the intelligent-sense controller 210 fetches the vMR information mapped to the selected DCM (S130).

Hereinafter, a process in which the intelligent-sense controller 210 fetches the vMR information mapped to the selected DCM will be described.

The intelligent-sense controller 210 requests mapping information between the DCM and the vMR to the DCM-vMR mapper 310. The DCM-vMR mapper 310 requests the mapping information to the DCM-vMR mapping storage 410 do.

The DCM-vMR mapping storage unit 410 requests DCM information and vMR information to the DCM query manager 630 and the vMR query manager 640, respectively, in order to know the mapping information between the DCM and the vMR.

Thus, the DCM query manager 630 queries the DCM information from the DCM ontology 530 and passes the DCM information to the intelligent-sense controller 210, which queries the vMR ontology 520 for vMR information, - sense controller (210).

Through this process, the intelligent-sense controller 210 can fetch the vMR information mapped to the selected DCM.

Next, the intelligent-sense controller 210 fetches the SNOMED information to be mapped with the vMR to be fetched in the step S130 (S140).

Hereinafter, the process of fetching the SNOMED information to which the intelligent-sense controller 210 is mapped with the vMR will be described.

The intelligent-sense controller 210 requests the vMR-SNOMED mapper 330 for mapping information between vMR and SNOMED and the vMR-SNOMED mapper 330 requests the vMR-SNOMED mapping storage 430 for mapping information do.

The vMR-SNOMED mapping storage 430 requests SNOMED information to the SNOMED query manager 610 to know the mapping information between vMR and SNOMED.

Accordingly, the SNOMED query manager 610 queries SNOMED information from the domain ontology 510 and transmits the SNOMED information to the intelligent-sense controller 210.

Through this process, the intelligent-sense controller 210 can fetch the SNOMED information to be mapped to the vMR.

Thereafter, the intelligent-sense controller 210 uses the vMR information matched with the DCM concept selected by the user using the vMR information fetched in step S130 and the SNOMED information fetched in step S140, and the SNOMED information (S150).

Through this process, even if a user, that is, a doctor or an expert, is not familiar with vMR and SNOMED, the selection of the DCM concept through the DCM tree provided through the user interface 100 facilitates the contextual selection of necessary rules and values .

Next, a method of generating MLM corresponding to medical knowledge according to an embodiment of the present invention will be described with reference to the drawings.

4 is a flowchart of an MLM generation method according to an embodiment of the present invention.

Referring to FIG. 4, when a user accesses the user interface 100 (S200) and requests a DCM concept, that is, a MLM generation corresponding to a rule (S210), the MLM generator 700 transmits DCM and vMR mapping information (S220).

Hereinafter, a process in which the MLM generator 700 fetches the mapping information of the DCM and the vMR will be described.

The MLM generator 700 requests the DCM concept controller 220 to fetch the mapping information of the DCM and the vMR and the DCM concept controller 220 requests the DCM-vMR mapper 310 of the mapping information between the DCM and the vMR .

Thereafter, the DCM-vMR mapper 310 requests the corresponding mapping information to the DCM-vMR mapping storage 410, and the DCM-vMR mapping storage 410 stores the DCM- And requests the manager 630 and the vMR query manager 640 for DCM information and vMR information, respectively.

The DCM query manager 630 queries the DCM information from the DCM ontology 530 and passes the DCM information to the vMR-SNOMED mapper 330 which queries the vMR information from the vMR ontology 520 to obtain vMR- To the mapper 330.

The vMR-SNOMED mapper 330 then provides the DCM information and the vMR information, which are respectively transmitted from the DCM query manager 630 and the vMR query manager 640, to the MLM generator 700 as matching information of the DCM and vMR.

Through this process, the MLM generator 700 can fetch the mapping information of the DCM and the vMR.

Next, the MLM generator 700 fetches vMR and SNOMED mapping information (S230).

Hereinafter, a process of MLM generator 700 fetching the mapping information of vMR and SNOMED will be described.

The vMR-SNOMED mapper 330 requests the vMR-SNOMED mapping storage 430 to store the mapping information between the vMR and the SNOMED received from the vMR query manager 640.

The vMR-SNOMED mapping storage 430 requests SNOMED information from the SNOMED query manager 610 to know the mapping information between vMR and SNOMED.

Accordingly, the SNOMED query manager 610 queries SNOMED information from the domain ontology 510 and transmits the SNOMED information to the MLM generator 700.

Through this process, the MLM generator 700 can fetch mapping information of vMR and SNOMED.

Next, the MLM generator 700 fetches the Aden artifacts to generate the selected rule as the MLM (S240). More specifically, the MLM generator 700 requests the Arden artifact controller 230 to use the Arden syntax artifacts used to convert the selected rules into MLMs. The arithmetic artifact controller 230 requests the artifacts query manager 620 for the arithmetic syntax effect factor and the artifacts query manager 620 fetches the corresponding arithmetic syntax artifacts from the artifacts store 540, (700).

Through this process, the MLM generator 700 can fetch the Arden syntax artifacts corresponding to the selected rule.

Thereafter, the MLM generator 700 generates a corresponding rule using the vMR mapping information, the vMR and the SNOMED mapping information, and the Arden syntax artifacts with the matched DCM (S250) to the MLM storage unit 800 (S260).

In this way, even if the user, that is, the doctor or the expert, is not familiar with the complex Arden syntax structure, it is possible to easily generate the Arden syntax MLM using the standard data model vMR and the SNOMED CT code.

3 and 4, if the user wishes to generate the MLM immediately after selecting the DCM concept through the user interface 100, the steps S220 and S230 may be repeatedly performed at steps S130 and S140, Information can be omitted.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It belongs to the scope of right.

Claims (17)

The concept of controlling the provision of syntactic artifacts used for the conceptual selection of a clinical model through a user interface providing an intelli-sense function and for the standardized medical logic module generation A control unit;
An ontology mapping unit for providing mutual mapping information between a concept of a selected clinical model, a standard data model, and standard term information; And
Acquiring mutual mapping information between the concept of the clinical model, the model of the standard model, and the standard term information through the concept control section and the ontology mapping section with respect to the concept of the clinical model selected through the user interface, A medical logic module generator for generating a standardized medical logic module corresponding to the concept of the clinical model using a syntax artifact corresponding to the concept of the clinical model
The medical knowledge generating system comprising: The method according to claim 1,
A mapping storage unit for storing and managing mutual mapping information between a concept of a clinical model, a standard data model, and standard term information provided by the ontology mapping unit;
A storage layer for providing different types of concepts and artifacts used in rule generation corresponding to the concept of the clinical model and in the standardized medical logic module generation process; And
Performing a contextual selection using a tree of intelligent-sense function and a clinical model through the user interface, and generating a medical logic module by using the concept of the clinical model, the standard data model, the standard term information, A query management unit
Wherein the medical knowledge generation system further comprises: 3. The method of claim 2,
The concept control unit,
A clinical model concept controller for providing a tree of a clinical model through the user interface and performing control so that a concept of the clinical model can be selected;
An intelligent-sense controller that provides configurable values for the selected concept in the immediate-execution window for accurate value selection for the concept of the clinical model; And
An artifact controller that provides a syntax artifact to be used during conversion of the concept into a medical logic module
The medical knowledge generating system comprising: The method of claim 3,
The ontology mapping unit,
A first mapper providing mapping information between a concept of the clinical model and a standard data model;
A second mapper providing mapping information between the concept of the clinical model and standard term information; And
A third mapper providing mapping information between the standard data model and standard term information
The medical knowledge generating system comprising: 5. The method of claim 4,
The mapping storage unit,
A first mapping storage for storing and managing mapping information between a concept of the clinical model and a standard data model, the mapping information being provided by the first mapper;
A second mapping storage for storing and managing mapping information between the concept of the clinical model and standard term information provided by the second mapper; And
A third mapping storage unit for storing and managing mapping information between the standard data model and standard term information provided by the third mapper,
The medical knowledge generating system comprising: 6. The method of claim 5,
The storage layer,
A domain ontology for managing concepts and code information corresponding to standard term information;
A standard data model ontology that manages the information used to fetch the standard data model and the corresponding mapping between the standard term information and the clinical model;
A clinical model ontology that manages the tree information of the clinical model and manages the information used to select concepts from the tree of clinical models during rule generation and the corresponding mapping of clinical models and standard data models and standard terminology information; And
An artifact storage unit for managing the syntax artifacts used during the generation of the medical logic module
The medical knowledge generating system comprising: The method according to claim 6,
The query management unit,
A first query manager for providing query information required by the third mapping storage unit through a query of standard term information managed in the domain ontology;
A second query manager for providing query information required by the artifact controller through a query of a syntax artifact managed in the artifact storage;
A third query manager for providing query information required by the first mapping storage unit through querying of tree information and mapping information of a clinical model managed in the clinical model ontology; And
A fourth query manager for providing query information required by the first mapper through a query of a standard data model and mapping information managed in the standard data model ontology,
The medical knowledge generating system comprising: 8. The method of claim 7,
In the case of the concept selection of the clinical model through the intelligent-sense function of the user interface, the query management unit queries the query information requested by the mapping storage unit through the storage layer unit and provides the query information to the intelligent- The medical knowledge generation system comprising: 8. The method of claim 7,
Wherein the query management unit queries the query information requested by the mapping storage unit through the storage layer when the medical logic module corresponding to the selected clinical model is requested through the user interface and transmits the query information to the third mapper of the ontology mapping unit The medical knowledge generation system comprising: 10. The method according to any one of claims 1 to 9,
The standardized medical logic module is a Medical Login Module (MLM) based on HL7 Arden Syntax,
The Syntax Artifacts are syntactic artifacts based on the HL7 Arden Syntax
Wherein the medical knowledge generating system comprises: 11. The method of claim 10,
The clinical model is HL7 DCM (Domain Clinical Model)
The standard data model is HL7 vMR (virtual medical record)
The standard term information is HL7 SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms)
Wherein the medical knowledge generating system comprises: A method for generating a standardized medical logic module, the medical knowledge generating system corresponding to medical knowledge,
Acquiring concept information of a clinical model through a user interface;
Obtaining standard data models and standard terminology information mapped to concepts of the obtained clinical model;
Obtaining a syntactic artifact corresponding to a concept of the obtained clinical model, a standard data model, and standard English information; And
Generating a standardized medical logic module corresponding to the concept of the obtained clinical model using the obtained syntax artifacts
/ RTI > 13. The method of claim 12,
Wherein the step of acquiring concept information of the clinical model comprises:
Providing a tree of clinical models through a user interface providing intell-sense functionality; And
Selecting a concept of a clinical model from a user through a tree of provided clinical models
/ RTI > 14. The method of claim 13,
Wherein the step of obtaining the standard data model and standard term information comprises:
Obtaining information of a standard data model that is mapped to a concept of a selected clinical model; And
Obtaining information of a standard term mapped to information of a standard data model to be obtained
/ RTI > 14. The method of claim 13,
Before obtaining the concept information of the clinical model,
Providing a tree of clinical models through the user interface;
Obtaining a standard data model and standard term information mapped to a concept of a clinical model selected by a user through a tree of the clinical model; And
Providing concept information of the clinical model with the standard data model and standard term information obtained through the user interface
≪ / RTI > 16. The method according to any one of claims 21 to 15,
The standardized medical logic module is a Medical Login Module (MLM) based on HL7 Arden Syntax,
The Syntax Artifacts are syntactic artifacts based on the HL7 Arden Syntax
≪ / RTI > 17. The method of claim 16,
The clinical model is HL7 DCM (Domain Clinical Model)
The standard data model is HL7 vMR (virtual medical record)
The standard term information is HL7 SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms)
≪ / RTI >

Images