WO2019136580A1

WO2019136580A1 - Method and system for constructing structured clinical diagnosis term set

Info

Publication number: WO2019136580A1
Application number: PCT/CN2018/071843
Authority: WO
Inventors: 刘莉
Original assignee: 深圳市第二人民医院
Priority date: 2018-01-09
Filing date: 2018-01-09
Publication date: 2019-07-18

Abstract

Disclosed are a method and system for constructing a structured clinical diagnosis term set. The method comprises the following steps: pre-constructing a term set hierarchical structure; importing multiple pieces of term set basic information; determining the distribution position of each piece of term set basic information in the term set hierarchical structure; determining a mapping relationship between different pieces of term set basic information based on the distribution positions of the different pieces of term set basic information in the term set hierarchical structure and according to a pre-set matching rule and/or the relevance of the term set basic information in existing clinical diagnosis information; and storing the imported term set basic information according to the respective distribution positions thereof in the term set hierarchical structure and the mapping relationship therebetween. The present invention facilitates clinical diagnosis by a doctor, and the refined management of diagnosis information by a hospital.

Description

Structured clinical diagnosis terminology set construction method and system thereof

Technical field

The invention relates to a method for constructing a structured clinical diagnosis terminology and a system thereof.

Background technique

For standardization work and subsequent data statistics, clinicians often need to refer to existing standard diagnostic terms or routine diagnostic terms when giving diagnostic information. In response to this demand, there is no reference or management method for diagnostic terms that can be used exclusively by clinicians in the prior art, and some hospitals will classify international diseases (International Classification of Diseases (ICD) is placed in the Hospital Information System (HIS) for use by clinicians. Although ICD is the most widely used internationally, it was originally set for the classification of death causes. Although the disease classification statistics were introduced in the sixth revision, the design principle is based on statistics, and the clinicians are in actual medical treatment. It is sometimes difficult to find ICD-related diagnostic information at work, and a descriptive diagnosis has to be added to the hospital information system. Different clinicians often have large differences in descriptive diagnosis of the same disease, which brings certain differences to hospital management. difficult.

technical problem

In recent years, with the requirements of medical reform, and in order to strengthen the quality of hospital construction, the National Health and Family Planning Commission has promulgated the "Guidelines for Service Capabilities of Tertiary General Hospitals", "Guidelines for Evaluation of High-Level Hospitals", "Guidelines for Payment of 320 Single Diseases", etc. Relevant documents, the above guidelines are all formulated by doctors. Among them, the types of diseases and the degree of difficulty are defined in detail. According to the requirements of these guidelines, the statistics need to be translated into ICD codes, but in the process of coding translation, Some of the diseases involved cannot be distinguished by coding, such as "refractory heart failure", "refractory hypertension", "large pelvic mass resection" and so on.

Technical solution

The present invention is directed to the above problems, and develops a structured clinical diagnosis terminology set construction method and system thereof which are convenient for doctors to diagnose clinically and facilitate the hospital to finely manage the diagnostic information.

The technical means of the present invention are as follows:

A method for constructing a structured clinical diagnosis terminology includes the following steps:

Pre-establishing a term set hierarchy; the term set hierarchy has at least five levels, each level representing a basic set of term sets;

Import multiple terminology basic information;

Determining a distribution location of each term set basic information in the term set hierarchy;

Determining the relevance of the basic information of the different term sets in the hierarchy of the term set according to the relevance matching rule and/or the relevance of the term set basic information in the existing clinical diagnosis information Mapping relationship;

The basic information of the imported term set is stored according to the respective distribution positions and mutual mapping relationships in the term set hierarchy;

Further, the five levels include: a first level, a second level, a third level, a fourth level, and a fifth level; the basic information of the term set includes at least medical gross anatomical information, disease site or organ information, disease Nature information, disease type information, and disease clinical diagnosis information; the first level is used to indicate the general anatomical position classification information involved in the disease, the second level is used to indicate the diseased part or organ information, and the third level is used. For indicating disease property information, the fourth level is for indicating disease type information, and the fifth level is for indicating disease clinical diagnosis information;

Further, after the imported term set basic information is stored according to the distribution position and the mutual mapping relationship in the term set hierarchy, the basic information of the term set in each level is encoded;

Further, the step of assigning the basic information of the term set in each level to the coding step specifically includes:

For any level, the basic information of the term set in the hierarchy is sequentially encoded using an 8-bit encoding form;

Further, the mapping relationship is a tree mapping relationship, and the root node of the tree mapping relationship is any medical gross anatomical information in the first level;

The disease type information corresponds to the disease type information specified by the first three codes of the international disease classification ICD version;

Further, the preset matching rule generates or adopts a preset matching algorithm according to the input information; the relevance of the term set basic information in the existing clinical diagnosis information refers to the basic information of the term set in the existing clinical diagnosis information. Co-occurrence frequency

Further, the step of importing the basic information of the plurality of term sets is:

The medical gross anatomical information database, the disease site or organ information database, the disease property information database, the disease type information database, and the disease clinical diagnosis information database are respectively introduced into the medical gross anatomical information, the diseased part or organ information, the disease property information, and the disease type information. , clinical diagnosis information of the disease;

Importing general medical anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information from the terminology basic information database; the terminology basic information database is based on a plurality of terminology basic information according to medical gross anatomy Information, disease site or organ information, disease property information, disease type information, disease clinical diagnosis information are classified and stored; and/or

The medical general anatomical information, the diseased part or organ information, the disease property information, the disease type information, and the disease clinical diagnosis information are extracted from the existing clinical diagnosis information and then imported.

A structured clinical diagnostic terminology building system comprising:

a building block for pre-building a term set hierarchy; the term set hierarchy has at least five levels, each level being used to represent a basic term of a term set;

Import module for importing basic information of multiple term sets;

a determining module, configured to determine a distribution position of each term set basic information in the term set hierarchy;

a processing module, configured to determine, according to a preset matching rule and/or a relevance of the term set basic information in the existing clinical diagnosis information, based on a distribution position of the basic information of different term sets in the term set hierarchy a mapping relationship between the basic information of the term set;

And a storage module, configured to store the imported term set basic information according to respective distribution positions and mutual mapping relationships in the term set hierarchy;

Further, the system further includes an encoding module, configured to: after the storage module stores the imported terminology basic information according to respective distribution positions and mutual mapping relationships in the term set hierarchy, The terminology set basic information gives the encoding an encoding.

Beneficial effect

Due to the adoption of the above technical solution, the structured clinical diagnosis terminology construction method and system thereof provided by the invention have clear hierarchical structure of terminology, are convenient for doctors to diagnose clinically and are beneficial to the hospital for fine management of diagnostic information, and can be applied not only to outpatient clinics. The doctor and the resident doctor refer to the clinical diagnosis, and it is convenient for the hospital to manage the key diseases and difficult diseases, and it is also beneficial to the daily diagnosis and statistics of the hospital, the examination of the competent department, and the personal statistics of the doctor. For each piece of clinical diagnosis information, the construction method of this embodiment can ensure that it only corresponds to one term set hierarchy; the clinical diagnosis terminology constructed by the embodiment can realize clear data expression and flexible data retrieval; creative configuration The third level is more representative of the disease nature information shared by diseases in different disciplines.

DRAWINGS

1 is a flow chart showing a method for constructing a structured clinical diagnosis term set according to Embodiment 1 of the present invention;

2 is a flow chart showing a method for constructing a structured clinical diagnosis term set according to Embodiment 2 of the present invention;

3 is a structural block diagram of a structured clinical diagnosis terminology constructing system according to Embodiment 3 of the present invention;

4 is a structural block diagram of a structured clinical diagnosis terminology building system according to Embodiment 4 of the present invention;

5 and FIG. 6 are diagrams showing an example of a hierarchical structure of the term set according to the present invention;

7 and 8 are exemplary diagrams of the set of clinical diagnostic terms of the present invention.

Embodiments of the invention

The present invention will be further described in detail below in conjunction with the drawings and specific embodiments. The specific embodiments described in the specification are to be construed as illustrative only and not limiting. The embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.

The present invention provides a method for constructing a structured clinical diagnosis terminology. FIG. 1 is a flowchart of a method for constructing a structured clinical diagnosis terminology according to Embodiment 1 of the present invention; as shown in FIG. 1, the constructing method may include:

Step 101: Pre-establish a term set hierarchy; the term set hierarchy has at least 5 levels, each level is used to represent a term set basic information; the term set hierarchy may have 5 levels in this embodiment. FIG. 5 and FIG. 6 are exemplary diagrams of the term set hierarchy of the present invention, and FIG. 7 and FIG. 8 are exemplary diagrams of the clinical diagnosis term set of the present invention, as shown in FIG. 5 and FIG. 6 . As shown in FIG. 7 and FIG. 8 , preferably, the five levels include: a first level, a second level, a third level, a fourth level, and a fifth level; and the basic information of the term set includes at least a medical general anatomy Information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information; the first level is used to represent the general anatomical location classification information involved in the disease, and the second level is used to indicate the disease site or Organ information, the third level is used to indicate disease property information, the fourth level is used to indicate disease type information, and the fifth level is used to represent disease clinical diagnosis information; The levels of the first level, the second level, the third level, the fourth level, and the fifth level are from high to low, top to bottom; the medical gross anatomical information herein may include: head and neck, eye, nose, nose and throat, Heart chest, gastrointestinal, urinary system, reproductive system, endocrine system, limbs and spine; the location or organ information here can be part of the body and organs, such as the brain, midbrain, cerebellum, internal capsule, skull , esophagus, throat, upper respiratory tract, etc.; the nature of the disease here may be infarction, hemorrhage, malformation, etc.; preferably, the disease type information herein may correspond to the disease type information specified in the first three codes of the ICD version of the International Classification of Diseases, The international disease classification ICD version specifically refers to the national standard version; specifically, it may include lung cancer, myocardial infarction, etc.; the clinical diagnosis information of the disease herein may specifically be the severity of the disease, such as the size of the tumor, and defined by the clinician. Empirical terms such as the degree of disease;

Step 102: Import basic information of multiple term sets;

Step 103: Determine a distribution position of each term set basic information in the term set hierarchy;

Step 104: Determine different term sets according to the relevance of the preset matching rule and/or the term set basic information in the existing clinical diagnosis information based on the distribution position of the basic term information of the different term sets in the term set hierarchy. The mapping relationship between the basic information; preferably, the mapping relationship may be a tree mapping relationship, and the root node of the tree mapping relationship may be any medical gross anatomical information in the first level, that is, the tree mapping relationship Taking the medical gross anatomical information in the first level as the highest level, in the case where the term set hierarchy has five levels, the clinical diagnosis information of the disease in the fifth level is regarded as the lowest level leaf node, the second level The disease site or organ information, the disease information of the third level, and the disease type information of the fourth level are in the middle nodes of the intermediate level; after determining the mapping relationship, setting a medical gross anatomical information in the first level as The root node, the plurality of intermediate nodes in the second level all correspond to the root node, and respectively follow the determined mapping Corresponding to the respective lower intermediate nodes, similarly, the plurality of intermediate nodes in the third hierarchy respectively correspond to the respective upper intermediate nodes and the next intermediate nodes according to the determined mapping relationship, and multiple intermediates in the fourth hierarchy The nodes respectively correspond to the respective upper intermediate nodes and the next horizontal leaf nodes according to the determined mapping relationship, and the plurality of leaf nodes in the fifth level respectively correspond to the respective upper intermediate nodes according to the determined mapping relationship; preferably, the nodes The preset matching rule may be generated according to the input information, where the input information may be input by a clinical diagnostic expert, and the preset matching rule may also adopt a preset matching algorithm; the term set basic information is in the existing clinical diagnosis information. Correlation degree refers to the co-occurrence frequency of the basic information of the term set in the existing clinical diagnosis information. In actual application, a common frequency threshold is set, for example, a certain disease site or organ information such as lung, and information about the nature of a disease. If the virus is infected, the frequency co-occurring in the existing clinical diagnosis information is higher than the co-occurrence frequency threshold, then it is considered as the second When the disease site or organ information in the hierarchy is lung, there is a mapping relationship between the disease property information in the third level and the virus infection, and the mapping relationship between the basic information of other term sets is determined in the same manner;

Step 105: The basic information of the imported term set is stored according to the distribution position and the mutual mapping relationship in the term set hierarchy; if the Excel table is used as the storage method of the term set, specifically, the table may be The information represented by the first level, the second level, the third level, the fourth level, and the fifth level are sequentially stored in columns according to the mapping relationship.

Through the construction method of the structured clinical diagnosis terminology of the present embodiment, the terminology set has a clear hierarchical structure, which is convenient for the doctor to diagnose the diagnosis and facilitate the hospital to finely manage the diagnosis information, and can be applied not only to the outpatient doctor and the resident doctor for clinical diagnosis. It is also convenient for the hospital to manage key diseases and difficult diseases, and it is also conducive to the daily diagnosis and statistics of the hospital, the inspection of the competent authorities, and the personal statistics of the doctors. For each piece of clinical diagnosis information, the construction method of this embodiment can ensure that it only corresponds to one term set hierarchy; the clinical diagnosis terminology constructed by the embodiment can realize clear data expression and flexible data retrieval; creative configuration The third level is more representative of the disease nature information shared by diseases in different disciplines.

2 is a flow chart of a method for constructing a structured clinical diagnosis terminology according to Embodiment 2 of the present invention, which is a preferred embodiment further improved on the basis of Embodiment 1 and the above preferred embodiment thereof. Further, FIG. 2 As shown in the embodiment, after the basic information of the imported term set is stored according to the distribution position and the mutual mapping relationship in the term set hierarchy (step 105), the present embodiment may further include:

Step 106: Encoding the term set basic information in each level; preferably, the specific encoding implementation may sequentially encode the basic information of the term set in the hierarchy using an 8-bit encoding form for any one level, for example, the encoding may be from 10000001 At the beginning, this coding method dilutes the coding, does not require the coding of the coder, and can solve the problem that the newly discovered disease coding in the ICD version of the International Classification of Diseases is insufficient. The coding can be automatically generated by the computer, which is beneficial to the subsequent multi-dimensional statistics. Specifically, since the coding of each level is independent, the search and statistics functions can be implemented for each level, thereby facilitating statistics of the whole hospital, departments, doctors. The completed diseases, difficult diseases, etc., are also convenient for statistical analysis of the same disease types in different departments of the hospital, such as infection, bleeding, infarction and so on.

The present invention further provides a preferred embodiment that is further improved on the basis of the embodiment 1. Further, the importing the plurality of term set basic information (step 102) may be:

The medical gross anatomical information database, the disease site or organ information database, the disease property information database, the disease type information database, and the disease clinical diagnosis information database are respectively introduced into the medical gross anatomical information, the diseased part or organ information, the disease property information, and the disease type information. The clinical diagnosis information of the disease; the medical gross anatomical information database here can be screened and statistically obtained according to relevant medical standards and existing clinical diagnosis information, and the database of the disease site or organ information can be obtained in the same manner;

Extracting medical gross anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information from existing clinical diagnosis information; further, extracting medical gross anatomical information and disease from existing clinical diagnosis information After the step or organ information, the disease property information, the disease type information, and the disease clinical diagnosis information step, the method further includes:

Step A: determining whether the extracted information is a standard diagnostic term or a conventional diagnostic term;

Step B: In the case where the extracted information is not a standard diagnostic term or a conventional diagnostic term, the standard diagnostic term or the conventional diagnostic term equivalent to the extracted information is substituted; that is, when obtained from the existing diagnostic information Medical general anatomical information, disease site or organ information, disease property information, disease type information, disease clinical diagnosis information, etc. are not standard diagnostic terms or routine diagnostic terms, and standard diagnostic terms that are synonymous or equivalent to the obtained information or The conventional diagnostic term replaces the information, and the replaced standard diagnostic term or the conventional diagnostic term is used as the basic information of the obtained term set, and then the subsequent steps 103 and 104 are performed; the standard diagnostic term can be related The terminology in the medical standard, which can be a commonly used term in the medical field.

The structured clinical diagnosis term set construction method of the present invention may be executed by a processor, a memory, or the like, or may be executed by a computer, a server, or the like.

The present invention also provides a structured clinical diagnosis terminology set construction system, and FIG. 3 is a structural block diagram of a structured clinical diagnosis terminology construction system according to Embodiment 3 of the present invention. As shown in FIG. 3, the system may include:

The building module 11 is configured to pre-build a term set hierarchy; the term set hierarchy has at least 5 levels, each level is used to represent a term set basic information; FIG. 5 and FIG. 6 are the term set of the present invention. FIG. 7 and FIG. 8 are diagrams showing an example of the clinical diagnosis term set of the present invention. As shown in FIG. 5, FIG. 6, FIG. 7, and FIG. 8, preferably, the five levels include: The first level, the second level, the third level, the fourth level and the fifth level; the basic information of the term set includes at least medical gross anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information. The first level is used to indicate general anatomical position classification information involved in the disease, the second level is used to indicate the diseased part or organ information, the third level is used to indicate disease property information, and the fourth level is Used to indicate disease type information, and the fifth level is used to indicate clinical diagnosis information of the disease;

The import module 12 is configured to import basic information of multiple term sets;

a determining module 13 configured to determine a distribution position of each term set basic information in the term set hierarchy;

The processing module 14 is configured to determine a mapping relationship between basic information of different term sets according to a preset matching rule and/or a correlation degree of the term set basic information in the existing clinical diagnosis information; the building module 11 and the import module 12. The determining module 13 and the processing module 14 may use a processor, a DSP, an FPGA, a CPU, or the above-mentioned devices integrated in a computer or a server.

And a storage module 15 configured to store the imported term set basic information according to respective distribution positions and mutual mapping relationships in the term set hierarchy; the storage module 15 may use the memory or the storage integrated in the computer or the server device;

4 is a flowchart of a method for constructing a structured clinical diagnosis terminology according to Embodiment 4 of the present invention, which is a preferred embodiment further improved on the basis of Embodiment 3. Further, as shown in FIG. 4, the system is as shown in FIG. An encoding module 16 may be further included, after the storage module 14 stores the imported term set basic information according to respective distribution positions and mutual mapping relationships in the term set hierarchy, the term set in each level. The basic information encodes the code.

The present invention also provides a preferred embodiment which is further improved on the basis of Embodiment 3. Further, the introduction module 12 can respectively obtain a medical gross anatomical information database, a disease site or organ information database, a disease property information database, and disease type information. The database and the disease clinical diagnosis information database are respectively introduced into medical gross anatomical information, disease site or organ information, disease property information, disease type information, and medical gross anatomical information, disease site or organ information, and disease property information are imported from the terminology basic information database. , disease type information, disease clinical diagnosis information; the term set basic information database classifies multiple terminology basic information according to medical gross anatomical information, disease site or organ information, disease property information, disease type information, disease clinical diagnosis information The medical anatomical information, the diseased part or organ information, the disease property information, the disease type information, and the disease clinical diagnosis information are stored and/or imported from the existing clinical diagnosis information. For medical gross anatomical information, specifically the classification information of the general anatomical position involved in the disease; human anatomy can be divided into gross anatomy (also known as giant anatomy) and microscopic anatomy; gross anatomy is to observe and describe the human body with the naked eye. Anatomy of the morphological structure.

The invention can be used alone as a structured clinical diagnosis terminology building system, and the system can construct a set of clinical diagnostic terms for doctors' work and hospital management, or can be built into the hospital management system.

The above is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any technical person skilled in the art within the technical scope disclosed by the present invention, the technical solution according to the present invention Equivalent substitutions or modifications of the inventive concept are intended to be included within the scope of the invention.

Claims

A method for constructing a structured clinical diagnosis terminology, characterized in that the method comprises the following steps:

Pre-establishing a term set hierarchy; the term set hierarchy has at least five levels, each level representing a basic set of term sets;

Import multiple terminology basic information;

Determining a distribution location of each term set basic information in the term set hierarchy;

Determining the relevance of the basic information of the different term sets in the hierarchy of the term set according to the relevance matching rule and/or the relevance of the term set basic information in the existing clinical diagnosis information Mapping relationship;

The imported term set basic information is stored according to their respective distribution positions in the term set hierarchy and mutual mapping relationship.
The structured clinical diagnosis term set construction method according to claim 1, wherein the five levels comprise: a first level, a second level, a third level, a fourth level, and a fifth level; The basic information includes at least medical gross anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information; the first level is used to represent general anatomical classification information related to the disease, and the second The level is used to indicate the diseased part or organ information, the third level is used to indicate disease property information, the fourth level is used to indicate disease type information, and the fifth level is used to indicate disease clinical diagnosis information.
The structured clinical diagnosis term set construction method according to claim 1 or 2, wherein after the imported terminology basic information is stored according to respective distribution positions in the term set hierarchy and mutual mapping relationship, The term set basic information in each level is assigned to the code.
The structured clinical diagnosis term set construction method according to claim 3, wherein the step of assigning the basic information of the term set in each level to the coding step comprises:

For any level, the basic information of the term set in the hierarchy is sequentially encoded using an 8-bit encoding format.
The structured clinical diagnosis term set construction method according to claim 2, wherein the mapping relationship is a tree mapping relationship, and the root node of the tree mapping relationship is any medical gross anatomical information in the first level. ;

The disease type information corresponds to the disease type information specified by the first three codes of the international disease classification ICD version.
The structured clinical diagnosis term set construction method according to claim 1, wherein the preset matching rule generates or adopts a preset matching algorithm according to the input information; and the term set basic information is in the existing clinical diagnosis information. Relevance refers to the co-occurrence frequency of the basic information of the term set in the existing clinical diagnosis information.
The structured clinical diagnosis term set construction method according to claim 2, wherein the step of importing the plurality of term sets basic information is:

The medical gross anatomical information database, the disease site or organ information database, the disease property information database, the disease type information database, and the disease clinical diagnosis information database are respectively introduced into the medical gross anatomical information, the diseased part or organ information, the disease property information, and the disease type information. , clinical diagnosis information of the disease;

Importing general medical anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information from the terminology basic information database; the terminology basic information database is based on a plurality of terminology basic information according to medical gross anatomy Information, disease site or organ information, disease property information, disease type information, disease clinical diagnosis information are classified and stored; and/or

The medical general anatomical information, the diseased part or organ information, the disease property information, the disease type information, and the disease clinical diagnosis information are extracted from the existing clinical diagnosis information and then imported.
A structured clinical diagnostic terminology building system, characterized in that the system comprises:

a building block for pre-building a term set hierarchy; the term set hierarchy has at least five levels, each level being used to represent a basic term of a term set;

Import module for importing basic information of multiple term sets;

a determining module, configured to determine a distribution position of each term set basic information in the term set hierarchy;

a processing module, configured to determine, according to a preset matching rule and/or a relevance of the term set basic information in the existing clinical diagnosis information, based on a distribution position of the basic information of different term sets in the term set hierarchy a mapping relationship between the basic information of the term set;

And a storage module, configured to store the imported term set basic information according to respective distribution positions and mutual mapping relationships in the term set hierarchy.
The structured clinical diagnosis term set construction system according to claim 8, wherein said five levels comprise: a first level, a second level, a third level, a fourth level, and a fifth level; The basic information includes at least medical gross anatomical information, disease site or organ information, disease property information, disease type information, and disease clinical diagnosis information; the first level is used to represent general anatomical classification information related to the disease, and the second The level is used to indicate the diseased part or organ information, the third level is used to indicate disease property information, the fourth level is used to indicate disease type information, and the fifth level is used to indicate disease clinical diagnosis information.
The structured clinical diagnosis terminology set construction system according to claim 8, wherein the system further comprises an encoding module, configured to, in the storage module, import the terminology set basic information according to the respective terminology hierarchy. After the distribution locations and the mutual mapping relationships are stored, the basic information of the term set in each hierarchy is encoded and encoded.