Apparatus and method for generating standardized medical terms

Abstract

This operating method of a device operated by at least one processor comprises the steps of: acquiring at least one new term to be added to a medical terminology standard, and a post-coordinated expression written on the basis of a core term registered in the medical terminology standard in order to express the new term; extracting a core term constituting the post-coordinated expression, and an attribute-value pair corresponding to relationship information; and using an attribute-value pair included in the post-coordinated expression so as to generate relationship information for the new term, and inheriting, from the relationship information for the core term, relationship information not changed by the post-coordinated expression, to the new term, so as to generate a relationship table of the new term.

Description

Medical standard term generation device and method

[0001] The present disclosure relates to the creation of medical standard terminology.

[0002] Healthcare institutions establish electronic health records (EHRs) and electronic medical records (EMRs) and store medical data such as diagnoses, medications, treatment plans, medical images, functional tests, lab tests, and visit histories.

[0003] Standardizing medical terminology has become increasingly important for various purposes, including clinical research, medical data analysis using AI models, and ensuring interoperability of medical information. Using standardized medical terminology in EHRs enables the creation of consistent and accurate medical records, provides patients with reliable medical services, ensures interoperability between medical institutions, facilitates the exchange of clinical information, and is effective for large-scale data research.

[0004] SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) is a representative international standard terminology. It encompasses all terms used in clinical settings and is designed to structure concepts for computerized processing. Clinical information utilizing SNOMED CT concepts can be expressed in pre-coordinated expressions and post-coordinated expressions. SNOMED CT supports the creation of detailed concepts at the clinical terminology level, thereby enriching clinical expressions. To this end, SNOMED International provides a concept authoring platform. However, most concepts require manual creation, which requires significant effort and time to generate large-scale new terms.

[0005] The present disclosure relates to a medical standard term generation device and method.

[0006] According to one embodiment, a method of operating a device operated by at least one processor comprises the steps of: obtaining at least one new term to be added to a medical terminology standard, and a post-coordinated expression written to express the new term based on core terms registered in the medical terminology standard; extracting core terms constituting the post-coordinated expression and attribute-value pairs corresponding to relationship information; and generating relationship information of the new term using the attribute-value pairs included in the post-coordinated expression, and inheriting relationship information of the core terms, which is not changed by the post-coordinated expression, to the new term to generate a relationship table of the new term.

[0007] The above method of operation may further include a step of generating a concept table of the new term by generating a code for the new term.

[0008] The above operating method may further include a step of determining representative terms and synonyms using the new term and generating a description table of the new term.

[0009] The above method of operation may further include a step of adding the concept table, the description table and the relationship table of the new term to the database of the medical terminology standard.

[0010] The above operating method may further include a step of setting the core term as a parent relationship of the new term.

[0011] The above medical terminology standard may include SNOMED CT.

[0012] A device according to one embodiment comprises a memory and a processor that executes instructions stored in the memory. The processor is configured to obtain a work table including at least one new term to be added to a medical terminology standard and a post-coordination expression, generate code for the new term, determine a representative term and a synonym using the new term, extract a core term constituting the post-coordination expression and an attribute-value pair corresponding to relationship information, set the core term as a parent relationship of the new term, generate relationship information of the new term using the attribute-value pair included in the post-coordination expression, and generate relationship information of the new term by inheriting relationship information of the core term that is not changed by the post-coordination expression among the relationship information. The medical terminology standard includes SNOMED CT.

[0013] The processor may be implemented to generate a concept table including codes for the new term, generate a description table including the representative term and its synonyms, and generate a relationship table including relationship information of the new term.

[0014] The processor may be implemented to add the concept table, the description table and the relationship table of the new term to the database of the medical terminology standard.

[0015] The above post-combination expression may be a data structure created to express the new term based on the core term registered in the medical terminology standard.

[0016] According to an embodiment, a user can add to the medical terminology standard by inputting detailed terms and post-combination expressions at the desired clinical terminology level, and as a result, a large number of new terms can be added to the medical terminology standard, thereby enriching clinical expressions.

[0017] According to an embodiment, new terms modeled as relationships of post-coordinate expressions can be managed as relationships between objects in a database, thereby improving search freedom and management convenience.

[0018] According to the embodiment, consistent and accurate medical records can be created through medical standard terminology at the clinical terminology level, and highly reliable medical services can be provided.

[0019] In an example, the use of standard medical terminology at the clinical terminology level in clinical research and medical data analysis using artificial intelligence models can contribute to the activation of large-scale data research.

[0020] FIG. 1 is a drawing illustrating a device for generating medical standard terms according to one embodiment.

[0021] FIGS. 2 to 5 are diagrams illustrating the creation of a relationship table of new terms according to one embodiment.

[0022] Figure 6 is a flowchart of a method for generating medical standard terms according to one embodiment.

[0023] Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts irrelevant to the description are omitted for clarity of explanation, and similar parts are designated with similar reference numerals throughout the specification.

[0024] In the description, when a part is said to "include" a component, this does not exclude other components, but rather implies that other components may be included, unless otherwise specifically stated. Furthermore, terms such as "part," "unit," and "module" used in the specification mean a unit that processes at least one function or operation, which may be implemented using hardware, software, or a combination of hardware and software.

[0025] The device may include one or more processors, a memory for loading a computer program executed by the processor, a storage device for storing the computer program and various data, and a communication interface. In addition, the device may further include various components. The processor is a device that controls the operation of the device and may be various types of processors that process instructions included in a computer program, and may be configured to include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), or any other type of processor well known in the art of the present disclosure. The memory stores various data, commands, and / or information. The memory can load a corresponding computer program from a storage device so that the commands described to execute the operations of the present disclosure are processed by the processor. The memory may be, for example, a ROM (read only memory), a RAM (random access memory), etc. The storage device can non-temporarily store a computer program and various data. The storage device may be configured to include non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present disclosure pertains. The communication interface may be a wired / wireless communication module that supports wired / wireless communication.A computer program comprises instructions that are executed by a processor and are stored in a non-transitory computer readable storage medium, the instructions causing the processor to perform the operations of the present disclosure.

[0026] FIG. 1 is a drawing illustrating a device for generating medical standard terms according to one embodiment.

[0027] Referring to FIG. 1, a device (100) for generating standard medical terms (simply referred to as a device) performs an operation according to the present disclosure by at least one processor. The device (100) automatically generates new standard terms that are not registered in the standard medical terminology database (10) as new terms in accordance with the standard medical terminology system using post-coordinated expressions. The device (100) can add new standard terms to the standard medical terminology database (10). New terms can be generated to provide more detailed clinical expressions than existing terms registered in the standard medical terminology database (10). New terms can have different values ​​from the attributes of existing terms, or different attributes and values ​​from the existing terms. In the present disclosure, SNOMED CT (Systematized Nomenclature Of Medicine Clinical Terms) is used as an example of a standard medical terminology.

[0028] Terms are managed by codes, and a term can be expressed by at least one of a term code and a term name. In the description, terms, term codes, and term names may not be strictly distinguished. SNOMED CT terms can be simply called standard terms, registered terms, concept terms, or concepts.

[0029] SNOMED CT consists of three tables: Concept, Description, and Relationship. SNOMED CT concepts represent systematically organized clinical meanings through hierarchical hierarchies. The concept table manages the concept code (SCTID) of each semantic unit, and the description table explains the concept code in human-readable terms, namely a single fully specified name (FSN) and synonyms. The relationship table defines the relationships between concepts, the relationships between concepts and description terms, and the attributes of concept terms. The concept table and description table are linked through the relationship table.

[0030] The device (100) obtains a work table (20) containing new terms to be registered in the medical terminology standard and post-combination expressions for the new terms, and generates new standard terms based on relationships with core (focus) terms included in the post-combination expressions. The generation of new standard terms may mean the generation of concept tables, description tables, and relationship tables according to the logic of SNOMED CT. Here, core terms are concept terms registered in the medical terminology standard.

[0031] Post-combination refers to creating new conceptual terms by modifying the values ​​of attributes of core terms or adding new attributes and values ​​to core terms. A post-combination expression is a data structure that expresses the desired post-combination in a computer-processable grammatical structure. New terms modeled through the relationships of post-combination expressions are managed not as individual items but as relationships among objects stored in the database, improving search freedom and management convenience.

[0032] Below, we describe in detail how to create new standard terms.

[0033] The device (100) can obtain a work table (20) containing new terms and post-combination expressions. If a medical institution requires detailed clinical-level terms, the work table (20) can be created and transmitted to the device (100). The new terms may be local terms used in the medical institution. The terms used in the medical institution may be clinical terms used to record medical data such as diagnoses, medications, and surgeries in electronic health records (EHR) and electronic medical records (EMR).

[0034] The work table (20) may include, for example, a new term desired by the user, 'Severe avascular necrosis of knee (disorder)', and a post-combination expression for expressing the new term by changing the properties and values ​​of the core terms, as shown in Table 1. The work table (20) may include an identifier of the new term. The identifier of the new term may be a local identifier, and any identifier may be assigned. Here, the work table (20) may include a plurality of new terms and their post-combination expressions, and the description will be given using one new term as an example.

[0035] New term Severe avascular necrosis of knee (disorder)Postcombination expression397758007|Avascular necrosis of bone (disorder)|:363698007 |Finding site (attribute)| = 304679005|Bone structure of knee joint region (body structure)|, 246112005|Severity (attribute)| = 24484000|Severe (severity modifier) ​​(qualifier value)|

[0036] A post-coordinate expression can be composed of a core term that is a parent of a new term and at least one attribute-value pair that represents relationship information. For example, a core term and an attribute-value pair can be separated by a colon (:), attribute-value pairs can be separated by a comma (,), and an attribute and a value can be connected by an equal sign (=). The core term, attribute, and value can be expressed by their respective codes (SCTID) and names (FSN). The core term, attribute, and value can be selected from a medical terminology standard database (10).

[0037] For example, if a user wants to express the site (Finding site) and severity in more detail than the already registered term 'Avascular necrosis of bone (disorder)' through the new term 'Severe avascular necrosis of knee (disorder)', the post-coordination expression in Table 1 can be used. That is, the post-coordination expression in Table 1 expresses the attribute-value pairs to be changed or added in the core term, where the first attribute is 'Finding site (attribute)' with SCTID 363698007 and its value is 'Bone structure of knee joint region (body structure)' with SCTID 304679005, and the second attribute is 'Severity (attribute)' with SCTID 246112005 and its value is 'Severe (severity modifier) ​​(qualifier value)' with SCTID 24484000.

[0038] A post-combination expression can be created by a user who requests the creation of a new standard term. Alternatively, the device (100) may input a new term and a core term, and based on the differences found by comparing the two terms (e.g., severe, knee), recommend at least some information that can express the difference, for example, 'Severity (attribute)', 'Finding site (attribute)', to fit the domain (e.g., disorder), and when an attribute concept is selected, recommend value concepts that can be selected from the range of the attribute. The device (100) may combine the selected information or the input information according to the grammatical structure to create a post-combination expression for creating a new term based on the core term. The device (100) may check the validity of the post-combination expression based on the post-combination creation criteria according to the hierarchical structure of the standard and visually display the error part.

[0039] The device (100) can create a new concept by generating a concept code (SCTID) for a new term in the work table (20) in a designated manner. The device (100) can store the concept code (e.g., xxxxxxxxx01) of the new term in the concept table. At this time, the device (100) can store the concept code of the new term and the new term (Severe avascular necrosis of knee (disorder)) in the concept table for subsequent work, as shown in Table 2.

[0040] Concept Code (SCTID)Concept Term (Fully Specified Name, FSN)397758007Avascular necrosis of bone (disorder)… … xxxxxxxx01Severe avascular necrosis of knee (disorder)

[0041] The device (100) can register a new term 'Severe avascular necrosis of knee (disorder)' with a concept code as a representative term (fully specified name) and register some keywords constituting the new term as synonyms to create a description table of the new term. For example, the value 'Severe avascular necrosis of knee' before the '(' delimiter in the new term can be registered as a synonym.

[0042] The device (100) can check the validity of the post-combination expression extracted from the work table (20), and then input the relationship information (is-a relationship, attribute) of the new term into the relationship table using the post-combination expression. The device (100) can extract the core terms and attribute-value pairs that constitute the post-combination expression, and can create a relationship table of the new term by creating a relationship (parent relationship, child relationship) with the core terms, inheriting the attributes of the core terms, and changing the attributes of the core terms. The device (100) can register the core term as a parent relationship (superior relationship) of the new term (e.g., creating an is-a relationship). The device (100) can create the relationship information of the new term by changing the attributes or values ​​of the core term using the attribute-value pairs of the post-combination expression. The device (100) can inherit attributes of the relationship information of the core term, excluding the is-a relationship, to the new term.

[0043] The device (100) can complete the task of generating new terms as new standard terms after checking the validity of records created in the relationship table. The device (100) can expand the medical terminology standard database (10) by adding the concept table, description table, and relationship table created for the new terms to the medical terminology standard database (10).

[0044] FIGS. 2 to 5 are diagrams illustrating the creation of a relationship table of new terms according to one embodiment.

[0045] Referring to FIG. 2, the device (100) sets the core term 397758007 Avascular necrosis of bone (disorder) as the parent relationship of the new term based on the post-combination expression extracted from the work table (20). The relationship table (200) records attribute-value (range) pairs (no. 1, no. 2, etc.) which are relationship information of the core term. Here, the relationship table (200) is a structure for the convenience of explanation, and data does not necessarily need to be stored in this form.

[0046] Referring to FIG. 3, the device (100) inputs the first attribute (363698007 Finding site (attribute)) and value (304679005 Bone structure of knee joint region (body structure)) of the post-combination expression into the relationship table (200-1). Through this, a new term can be created with a concept that has the same first attribute as the core term, but a different value.

[0047] Referring to FIG. 4, the device (100) inputs the second attribute (246112005 Severity (attribute)) and value (24484000 Severe (severity modifier) ​​(qualifier value)) of the post-combination expression into the relationship table (200-2). Through this, a new term can be created as a concept having new attributes and values ​​that the core term does not have.

[0048] Referring to FIG. 5, the device (100) inherits the relationship information of the core terms that are not changed by the post-combination expression (e.g., 116676008 associated morphology (attribute) and 86217007 Avascular necrosis (morphologic abnormality)) to the new terms and inputs them into the relationship table (200-3).

[0049] In this way, the device (100) can automatically generate relationship information of new terms by using a post-combination expression for generating new terms based on core terms.

[0050] Figure 6 is a flowchart of a method for generating medical standard terms according to one embodiment.

[0051] Referring to FIG. 6, the device (100) obtains at least one new term to be added to the medical terminology standard, and a post-combination expression written to express the new term based on the core term registered in the medical terminology standard (S110). The relationship information may include at least one attribute-value pair. The post-combination expression may be written by a user who requests the creation of a new standard term. Alternatively, the device (100) may receive a new term and a core term, compare the two terms, and based on the differences discovered, recommend relationship information (attributes or values) that can be changed in the core term, and combine the selected information or the input information according to the grammatical structure to create a post-combination expression.

[0052] The device (100) generates a code for a new term in a specified manner and creates a concept table of the new term including the code (S120).

[0053] The device (100) determines representative terms and synonyms using new terms, and generates a description table of new terms including the representative terms and synonyms (S130). The device (100) determines the new terms as representative terms (FSN), and determines synonyms composed of some keywords constituting the new terms, thereby generating a description table including the representative terms and synonyms.

[0054] The device (100) extracts key terms that constitute a post-combination expression and attribute-value pairs corresponding to relationship information (S140).

[0055] The device (100) sets the core term as the parent relationship (superior relationship) of the new term (S150). The new term is set as the child relationship (subordinate relationship) of the core term.

[0056] The device (100) generates relationship information of a new term using the attribute-value pairs included in the post-combination expression, and creates a relationship table of the new term by inheriting relationship information of the core term that has not been changed by the post-combination expression to the new term (S160).

[0057] The device (100) adds a concept table, a description table, and a relationship table of new terms to the medical terminology standard database (S170).

[0058] In this way, according to the embodiment, the user can easily register and use detailed terms at the level of clinical terms in the medical terminology standard.

[0059] According to an embodiment, new terms modeled as relationships of post-coordinate expressions can be managed as relationships between objects in a database, thereby improving search freedom and management convenience.

[0060] According to the embodiment, consistent and accurate medical records can be created through medical standard terminology at the clinical terminology level, and highly reliable medical services can be provided.

[0061] In an example, the use of standard medical terminology at the clinical terminology level in clinical research and medical data analysis using artificial intelligence models can contribute to the activation of large-scale data research.

[0062] The embodiments of the present disclosure described above are not implemented only through devices and methods, but may also be implemented through a program that realizes a function corresponding to the configuration of the embodiments of the present disclosure or a recording medium on which the program is recorded.

[0063] Although the embodiments of the present disclosure have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concepts of the present disclosure defined in the following claims also fall within the scope of the present disclosure.

Claims

1. A method of operating a device operated by at least one processor, A step of obtaining at least one new term to be added to a medical terminology standard, and a post-combination expression written to express the new term based on core terms registered in the medical terminology standard; A step of extracting the key terms that constitute the above post-combination expression and the attribute-value pairs corresponding to the relationship information, and A step of generating relationship information of the new term using the attribute-value pairs included in the post-combination expression, and generating a relationship table of the new term by inheriting relationship information that is not changed by the post-combination expression among the relationship information of the core term to the new term. A method of operation including:

2. In paragraph 1, A step of generating a concept table of the new term by generating a code for the new term. A method of operation that further includes:

3. In paragraph 2, A step of creating a description table of the new term by determining representative terms and synonyms using the new term. A method of operation that further includes:

4. In paragraph 3, A step of adding the concept table, the description table, and the relationship table of the new term to the database of the medical terminology standard. A method of operation that further includes:

5. In paragraph 1, A step of setting the above core term as a parent relationship of the above new term. A method of operation that further includes:

6. In paragraph 1, The above medical terminology standard includes SNOMED CT, a method of operation.

7. Memory, and A processor that executes instructions stored in the above memory, The above processor Obtain a worktable containing at least one new term to be added to the medical terminology standard and a post-coordination expression, Generate code for the above new term, Using the new terms above, determine representative terms and synonyms, Extract the key terms that make up the above post-combination expression and the attribute-value pairs corresponding to the relationship information, Set the above core term as the parent relationship of the above new term, Generate relationship information of the new term using the attribute-value pairs included in the above post-combination expression, It is implemented to generate relationship information of the new term by inheriting relationship information that is not changed by the post-combination expression among the relationship information of the above core terms to the new term, The above medical terminology standard includes devices such as SNOMED CT.

8. In paragraph 7, The above processor Create a concept table containing codes for the above new terms, Create a description table containing the above representative terms and synonyms, A device implemented to generate a relationship table containing relationship information of the above new terms.

9. In paragraph 8, The above processor A device implemented to add the concept table, the description table and the relationship table of the new term to the database of the medical terminology standard.

10. In paragraph 7, The above post-combination expression is a device that is a data structure created to express the new term based on the core term registered in the medical terminology standard.

Images