CN111444333B - Coding mapping method for insurance medicine and clinical medicine - Google Patents
Coding mapping method for insurance medicine and clinical medicine Download PDFInfo
- Publication number
- CN111444333B CN111444333B CN202010335743.XA CN202010335743A CN111444333B CN 111444333 B CN111444333 B CN 111444333B CN 202010335743 A CN202010335743 A CN 202010335743A CN 111444333 B CN111444333 B CN 111444333B
- Authority
- CN
- China
- Prior art keywords
- medical
- insurance
- clinical
- terms
- catalog
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides an insurance medicine and clinical medicine coding mapping method, which comprises the following steps: step (1), forming an original insurance medical term and rule base according to classification of insurance diseases; step (2), carrying out preliminary extraction on diseases and symptoms related to the classified insurance medical terms and rules, and step (3), filtering an original insurance medical rule base, and collecting the obtained key indexes into an insurance medical catalog base; step (4), forming a clinical medical dictionary library; and (5) transmitting the insurance medical indexes into a clinical medical database for screening step by step according to the catalogue grade, and (6) after checking by an expert, forming an insurance medical-clinical medical coding mapping dictionary library. The invention solves the definition barrier between insurance medicine and clinical medicine, fully utilizes the existing clinical medical data and adapts to the current situation of commercial insurance industry; industry data standards are standardized, so that both suppliers and consumers in the business protection industry can be reasonably dependent in two core periods in the future.
Description
Technical Field
The invention relates to the technical field of data processing methods, in particular to an encoding and mapping method of insurance medicine and clinical medicine.
Background
At present, the medical resource interconnection and intercommunication are promoted, the health service capability is a necessary path for the innovation of the deepened public hospitals which is promoted by the China, and the requirements of commercial insurance institutions on medical big data can be huge as third party markets of medical services. However, the existence of the industry barriers, such as the difference between the definitions of insurance medicine and clinical medicine, makes the application of clinical medical data at the insurance business end very difficult, prevents the commercial insurance institutions from using the medical health big data to perform standard pricing and wind control supervision on related products, and also makes the medical service side unable to reasonably allocate medical resources by means of the function of the commercial insurance as a medical guarantee third support. Therefore, breaking the definition barriers of insurance medicine and clinical medicine, forming a mapping rule from clinical medicine to insurance medicine in many-to-many, and providing decision support for fine pricing of insurance products, medical abuse and medical insurance fraud wind control is particularly important.
At present, the existence of insurance medicine and clinical medicine defines barriers, so clinical medical disease diagnosis cannot completely adapt to the requirements of nuclear protection and claim settlement of a commercial insurance business end, disputes about insurance business occur many times in the market due to the existence of the ambiguity, and the commercial process is difficult to efficiently utilize medical data of an applicant to carry out decision support and product iteration.
Disclosure of Invention
The technical problem solved by the invention is to provide a coding mapping method for insurance medicine and clinical medicine so as to solve the problems in the background technology.
The technical problems solved by the invention are realized by adopting the following technical scheme: an insurance medical and clinical medical coding mapping method comprises the following steps:
step (1), researching the current health risk market status, and forming an original insurance medical term and rule base classified according to diseases and symptoms based on the current market status;
step (2), carrying out preliminary extraction on the classified insurance medical terms and diseases and symptoms related to the rules, namely introducing stop word filtering to insurance rule terms in two-core and health notification books, submitting the filtered rule terms to manual auditing, finally forming a set of insurance medical terms for each insurance medical disease term and each insurance rule term thereof, submitting each preliminarily extracted insurance medical term subjected to attribute classification to relevant clinical medical specialists for rechecking, and thus completing the steps of filtering original insurance medical terms and rule base redundant information and extracting key terms;
step (3) after filtering the original insurance medical terms and rule base, further structuring the obtained key term set to form an insurance medical catalog base, wherein the specific operation scheme is as follows:
a. in order to ensure that the association mapping between the subsequent medical directory library and the clinical medical dictionary library is more accurate and reasonable, the tree-like hierarchical structure which is the same as that in the clinical medical dictionary library needs to be formed, namely, the main directory, the primary directory, the secondary directory and the tertiary directory are formed according to the drill-down logic such as anatomies, etiologies, operation types and disease types. More precisely, the main catalog and the primary catalog establish catalog indexes for disease types based on anatomies and etiologies, and the secondary catalog is formed by superposing treatment modes (including treatment means of operation and non-operation) on the basis of the diagnosis classification of the primary catalog, and the significance is that the comparability between disease groups is increased, the difference in groups is reduced and the cross complementation is reduced. The final three-level catalogue combines different treatment modes under the same etiology diagnosis (the first-level catalogue is the same). It should be noted that although the directory structure is shown as extending from the main directory to the tertiary directory, in the stage of forming the directory library, the directory structure is formed by induction of the corresponding parts of the basic tertiary directory from bottom to top according to the treatment mode, etiology and anatomy. The directory structure is the directory structure of the insurance medical directory library.
b. Because the description in the space-time dimension is not involved in the clinical medical coding system, the terms marked with the tag of the space-time dimension attribute in the original sets are firstly eliminated, and secondly, because the three-level catalogue at the bottom layer of the clinical medical dictionary library is a disease type combination catalogue, the catalogue comprises specific clinical disease diagnosis and related treatment modes, but no clinical indication information related to the clinical disease or clinical complications information generated by treatment is further involved. It is also necessary to exclude the term labeled with clinical indication attributes from the original collection. Finally, the method mainly aims at the clinical diagnosis terms, operation terms and non-operation treatment means terms in the rest original sets.
c. The terms in each of the insurance medical disorders and the collection thereof are rearranged and combined to form a description conforming to the hierarchical logic of the insurance medical catalog. In other words, for each of the safe medical conditions and terms in the collection thereof, we wish to be able to represent them as a combination of safe medical conditions conforming to the three-level catalog of the safe medical catalog library, since the three-level catalog is the underlying catalog of the safe medical catalog library, once the three-level catalog is determined, its corresponding two-level catalog, one-level catalog and master catalog can also be determined, and the three-level catalog of the safe medical catalog is formatted as "specific clinical diagnosis name+specific treatment modality". Of course, because the requirements and definitions of each safe medical condition for clinical diagnosis, treatment modality are different according to their business needs, it is not possible to combine terms in the collection thereof to represent each safe medical condition conforming to the three-level catalog of the safe medical catalog library, the three-level catalog conforms to the two-level catalog and the master catalog, and can only be rearranged to the two-level catalog of the following detailed catalog, but can only be rearranged to the very small number of the three-level catalog: since insurance medical condition terms are not all related to clinical diagnostic terms, the insurance medical condition terms can be broadly classified into the following three types according to the above-described arrangement of original insurance medical terms and rule bases: disease diagnosis, surgery, functional manifestations. The strategy of rearrangement combinations also varies for different types of insurance medical condition terms. Firstly, for the safety medical disease terms of the disease diagnosis type, because the terms of the safety medical disease terms already contain diagnosis information, only the corresponding operation terms and non-operation treatment means terms are extracted from the corresponding safety medical terms, so that the safety medical disease type combination conforming to the three-level catalog format can be formed; for the operation type of insurance medical condition terms, it is necessary to extract the conforming clinical diagnostic terms from the corresponding set of insurance medical terms, but it is noted that there are two possible cases where the first is that the set contains specific clinical diagnostic terms, in which case the combination of insurance medical condition types conforming to the three-level catalog format can be directly formed, and the second is that the set does not contain specific clinical diagnostic terms, or only the site where the disease occurs is briefly mentioned, or is summarized directly in terms of the disease. Such cases only adapt to the format requirements of the secondary catalog and (master catalog/primary catalog) in the insurance medical catalog library; for functional performance type insurance medical condition terms, it is desirable to extract conforming clinical diagnostic terms, surgical terms, and non-surgical therapeutic terms from their corresponding collection of insurance medical terms. Similarly, this type of insurance medical condition term may only be able to fit the partial format requirements of the first three levels of the insurance medical catalog. While the fit of different types of insurance medical condition terms to the insurance medical catalog is irregular, based on the commonality of insurance medical and clinical medicine and the objective nature of the disease (the disease is an abnormal vital activity process of an organism under damaging effects of a certain cause, is a specific abnormal pathological condition and affects part or all of the organism, it is generally interpreted as a "body condition" and accompanied by specific symptoms and medical signs), the insurance medical condition terms can always find their corresponding location in at least one hierarchical catalog of the insurance medical catalog.
So far, an insurance medical catalog library is formed, and covers the key disease fields and the treatment mode information of the main stream focused on the current health risk market.
Step (4), forming a clinical medical dictionary base based on a technology of grouping the big data disease seeds and an ICD-10 coding three-code integrated system;
step (5), transmitting the insurance medical indexes into a clinical medical database to be screened and matched step by step according to catalog grades, wherein the clinical medical dictionary database is generated based on big data disease types in groups and has a tree structure, namely, the disease types are combined from anatomy, etiology and operation type into a hierarchical structure, and the hierarchical structure extends from a main catalog to a tertiary catalog;
and (6) after the expert auditing, forming an insurance medical-clinical medical coding mapping dictionary library, wherein the dictionary library realizes the association mapping of the etiology, operation type and non-operation treatment means information concerned in the insurance medical and the clinical medical coding.
In the step (1), major disease information specified by each health insurance institution insurance product term, related wind control means, health notification books and insurance prison is researched; and classifying and summarizing the original insurance medical terms and diseases in the rule base according to the serious diseases, moderate diseases, mild diseases and basic diseases with the future serious disease risks mentioned in the health notice, and marking corresponding disease classification labels.
The collection of insurance medical terms in the step (2) comprises clinical diagnosis terms, operation terms, clinical indication terms and non-operation treatment means terms which may exist; for each insurance medical term, attribute tags of corresponding information are marked.
The clinical medical dictionary library in the step (5) is generated based on the big data disease seed group, and has a tree structure, namely, the hierarchical structure of the disease seed combination extends from the main catalog to the tertiary catalog from the anatomy, the etiology and the operation mode. While the insurance medical directory base has the same tree-like hierarchical structure as the clinical dictionary base. Therefore, the catalogues at two ends can be matched in a one-to-one correspondence manner, for example, for a certain insurance medical disease term A, the query path of the insurance medical disease term A can be obtained through an insurance medical catalog library, namely, the query path of the A is (main catalog: name, primary catalog: name, secondary catalog: name, tertiary catalog: name), the query path of the A is used as the query condition of a clinical dictionary library, the query is gradually screened according to catalog grade, and a clinical medical term set related to the insurance medical disease term A can be obtained after query is carried out; each insurance medical term corresponds to one or more clinical medical terms; and submitting the matched data to clinical medical professionals for review.
Compared with the prior art, the invention has the beneficial effects that: the invention 1 solves the definition barrier between insurance medicine and clinical medicine, fully utilizes the existing clinical medical data, and adapts to the requirements of commercial insurance industry; industry data standards are standardized, so that both suppliers and consumers in the business protection industry can be reasonably dependent in two core periods in the future.
Drawings
Fig. 1 is a schematic diagram of a system of the present invention.
Fig. 2 is a diagram of a clinical-insurance medical disease mapping dictionary library representative of the present invention.
Fig. 3 is a schematic diagram of the redundant information filtering key term extraction expert review of the present invention.
FIG. 4 is a schematic diagram of the key term set structuring process of the present invention.
FIG. 5 is a schematic diagram of a review of a clinical-insurance medical big data matching patent of the present invention
FIG. 6 is a schematic diagram of the grouping of the insurance medical big data sources of the present invention
Detailed Description
The invention is further described below with reference to specific embodiments in order to make the implementation, creation characteristics, achievement of the purpose and effect of the invention easy to understand.
An insurance medical and clinical medical coding mapping method comprises the following steps:
the method comprises the steps of (1) researching the current situation of the current health insurance market, mainly researching information of major diseases and the like specified by insurance product clauses, related wind control means, health notices and insurance authorities of each health insurance institution, forming an original insurance medical term and rule base based on the current situation of the market, classifying and summarizing the original insurance medical term and the diseases in the rule base according to major diseases, middle diseases, light diseases and basic diseases with future major disease illness risks mentioned in the health notices according to classification of the insurance diseases, and marking corresponding disease classification labels.
Step (2), carrying out preliminary extraction on the classified insurance medical terms and diseases and symptoms related in the rules, namely introducing stop words into the insurance rules for filtering, and filtering irrelevant language assisting words, turning words and other descriptive words irrelevant to the medical terms; submitting the filtered rule terms to manual review, and finally forming a set of insurance medical terms for each insurance medical disease term and the insurance rule terms thereof, wherein the set comprises a plurality of terms with different attributes besides the insurance medical disease terms, including clinical diagnosis terms, operation terms, clinical indication terms, non-operation treatment terms and terms required in a time-space dimension (such as diagnosis in a mental department of a three-dimensional hospital after 180 days of diagnosis is required, and the like). For the insurance medical terms in each set, attribute tags of corresponding information are marked. And finally submitting each preliminarily extracted insurance medical term subjected to attribute classification to relevant clinical medical specialists for review. Thus, the steps of filtering the redundant information of the original insurance medical terms and the rule base and extracting the key terms are completed.
Step (3) after filtering the original insurance medical terms and rule base, further structuring the obtained key term set to form an insurance medical catalog base, wherein the specific operation scheme is as follows:
a. in order to ensure that the association mapping between the subsequent medical directory library and the clinical medical dictionary library is more accurate and reasonable, the tree-like hierarchical structure which is the same as that in the clinical medical dictionary library needs to be formed, namely, the main directory, the primary directory, the secondary directory and the tertiary directory are formed according to the drill-down logic such as anatomies, etiologies, operation types and disease types. More precisely, the main catalog and the primary catalog establish catalog indexes for disease types based on anatomies and etiologies, and the secondary catalog is formed by superposing treatment modes (including treatment means of operation and non-operation) on the basis of the diagnosis classification of the primary catalog, and the significance is that the comparability between disease groups is increased, the difference in groups is reduced and the cross complementation is reduced. The final three-level catalogue combines different treatment modes under the same etiology diagnosis (the first-level catalogue is the same). It should be noted that although the directory structure is shown as extending from the main directory to the tertiary directory, in the stage of forming the directory library, the directory structure is formed by induction of the corresponding parts of the basic tertiary directory from bottom to top according to the treatment mode, etiology and anatomy. The directory structure is the directory structure of the insurance medical directory library.
b. Because the description in the space-time dimension is not involved in the clinical medical coding system, the terms marked with the tag of the space-time dimension attribute in the original sets are firstly eliminated, and secondly, because the three-level catalogue at the bottom layer of the clinical medical dictionary library is a disease type combination catalogue, the catalogue comprises specific clinical disease diagnosis and related treatment modes, but no clinical indication information related to the clinical disease or clinical complications information generated by treatment is further involved. It is also necessary to exclude the term labeled with clinical indication attributes from the original collection. Finally, the method mainly aims at the clinical diagnosis terms, operation terms and non-operation treatment means terms in the rest original sets.
c. The terms in each of the insurance medical disorders and the collection thereof are rearranged and combined to form a description conforming to the hierarchical logic of the insurance medical catalog. In other words, for each of the safe medical conditions and terms in the collection thereof, we wish to be able to represent them as a combination of safe medical conditions conforming to the three-level catalog of the safe medical catalog library, since the three-level catalog is the underlying catalog of the safe medical catalog library, once the three-level catalog is determined, its corresponding two-level catalog, one-level catalog and master catalog can also be determined, and the three-level catalog of the safe medical catalog is formatted as "specific clinical diagnosis name+specific treatment modality". Of course, because the requirements and definitions of each safe medical condition for clinical diagnosis, treatment modality are different according to their business needs, it is not possible to combine terms in the collection thereof to represent each safe medical condition conforming to the three-level catalog of the safe medical catalog library, the three-level catalog conforms to the two-level catalog and the master catalog, and can only be rearranged to the two-level catalog of the following detailed catalog, but can only be rearranged to the very small number of the three-level catalog: since insurance medical condition terms are not all related to clinical diagnostic terms, the insurance medical condition terms can be broadly classified into the following three types according to the above-described arrangement of original insurance medical terms and rule bases: disease diagnosis, surgery, functional manifestations. The strategy of rearrangement combinations also varies for different types of insurance medical condition terms. Firstly, for the safety medical disease terms of the disease diagnosis type, because the terms of the safety medical disease terms already contain diagnosis information, only the corresponding operation terms and non-operation treatment means terms are extracted from the corresponding safety medical terms, so that the safety medical disease type combination conforming to the three-level catalog format can be formed; for the operation type of insurance medical condition terms, it is necessary to extract the conforming clinical diagnostic terms from the corresponding set of insurance medical terms, but it is noted that there are two possible cases where the first is that the set contains specific clinical diagnostic terms, in which case the combination of insurance medical condition types conforming to the three-level catalog format can be directly formed, and the second is that the set does not contain specific clinical diagnostic terms, or only the site where the disease occurs is briefly mentioned, or is summarized directly in terms of the disease. Such cases only adapt to the format requirements of the secondary catalog and (master catalog/primary catalog) in the insurance medical catalog library; for functional performance type insurance medical condition terms, it is desirable to extract conforming clinical diagnostic terms, surgical terms, and non-surgical therapeutic terms from their corresponding collection of insurance medical terms. Similarly, this type of insurance medical condition term may only be able to fit the partial format requirements of the first three levels of the insurance medical catalog. While the fit of different types of insurance medical condition terms to the insurance medical catalog is irregular, based on the commonality of insurance medical and clinical medicine and the objective nature of the disease (the disease is an abnormal vital activity process of an organism under damaging effects of a certain cause, is a specific abnormal pathological condition and affects part or all of the organism, it is generally interpreted as a "body condition" and accompanied by specific symptoms and medical signs), the insurance medical condition terms can always find their corresponding location in at least one hierarchical catalog of the insurance medical catalog.
Thus, an insurance medical catalog library is formed, and covers the key disease fields and the treatment mode information of the main stream focused on the health risk market.
In addition, the insurance medical-clinical medical coding mapping has a compacted scientific research basis. The clinical medicine code is derived from a clinical medicine dictionary library of Shanghai city health committee, the current clinical medicine diseases and operation classification are summarized to form the clinical medicine dictionary library, and the clinical medicine dictionary library is provided by the Shanghai city health committee through three-code integration of a clinical version, a medical insurance version and a national standard version of an international disease classification coding system (ICD-10), classifying the clinical medicine diseases and operation, and simultaneously combining clinical revision surgery and operation (ICD-9-CM-3) coding and realizing disease classification based on a big data technology. There are two main technical key points, and the technical difficulties of the clinical medical dictionary library are as follows: firstly, the conversion rules of ICD-10 clinical codes, medical insurance codes and national standard codes are required to be specified; and secondly, based on a general equilibrium theory, carrying out exhaustion and clustering on disease diagnosis and treatment modes in massive clinical medical data by using a big data technology, maximizing and covering diagnosis and operation modes related to clinical medical treatment, classifying cases similar to clinical processes and similar in resource consumption into one type, quickly forming groups, improving the grouping rate of the disease seeds obtained according to a big data grouping method by 14% compared with the grouping rate of the traditional DRGs groups, reaching 97.41%, excluding part of extreme cases which are not grouped, basically covering clinical medical diagnosis behaviors by using the big data disease seeds, and objectively fitting medical cost. So far, a clinical medical dictionary library is formed based on a big data disease grouping technology and an ICD-10 coding three-code integrated system.
And (4) carrying out many-to-association mapping on the insurance medical disease terms and the collection thereof in the insurance medical catalog library and the clinical medical dictionary library according to the hierarchical correspondence, wherein the specific operation mode is as follows:
since the clinical dictionary library is generated based on big data disease seed group, it has tree structure, i.e. hierarchy structure of anatomy, etiology, operation type, disease seed combination extends from main catalog to tertiary catalog. While the insurance medical directory base has the same tree-like hierarchical structure as the clinical dictionary base. Therefore, the catalogues at two ends can be matched in a one-to-one correspondence manner, and for a certain insurance medical disease term A, the query path of the insurance medical disease term A can be obtained through an insurance medical catalog library, namely, the query path of the A is (main catalog: name, primary catalog: name, secondary catalog: name, tertiary catalog: name), the query path of the A is used as the query condition of a clinical dictionary library, the query path is gradually screened according to catalog grade, a clinical medical term set associated with the insurance medical disease term A can be obtained after query is carried out, morphological codes corresponding to each clinical medical term in the set are returned, disease codes, positions of the disease codes in various-level catalogues of large data disease types are grouped, and corresponding average cost in groups are obtained. It should be noted that, due to the original terms, a part of the insurance medical disease terms cannot meet the requirements of the third-level catalogue of the insurance medical catalogue library or the requirements of the rest of the certain-level catalogues, so that the names of the part of the insurance medical disease terms corresponding to the certain-level catalogues in the insurance medical catalogue library may be empty, and therefore, when the corresponding insurance medical dictionary library is queried, the list levels with the empty names are not required to be additionally limited, but all the insurance medical disease terms are returned. To this end, each insurance medical condition term corresponds to one or more clinical medical terms. To further avoid systematic risks. And submitting the matched data to clinical medical professionals for review.
And (5) after the expert auditing, forming an insurance medical-clinical medical coding mapping dictionary library, wherein the dictionary library realizes the association mapping of the information such as etiology, operation type and non-operation treatment means and the like which are concerned in the insurance medical and clinical medical coding.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. A coding mapping method for insurance medicine and clinical medicine is characterized in that: the method comprises the following steps:
step (1), researching the current health risk market status, and forming an original insurance medical term and rule base classified according to diseases and symptoms based on the current market status;
step (2), carrying out preliminary extraction on the classified insurance medical terms and diseases and symptoms related to the rules, namely introducing stop word filtering to insurance rule terms in two-core and health notification books, submitting the filtered rule terms to manual auditing, finally forming a set of insurance medical terms for each insurance medical disease term and each insurance rule term thereof, submitting each preliminarily extracted insurance medical term subjected to attribute classification to relevant clinical medical specialists for rechecking, and thus completing the steps of filtering original insurance medical terms and rule base redundant information and extracting key terms;
step (3), filtering the original insurance medical terms and rule base, and collecting the obtained key terms into an insurance medical catalog base; the insurance medical catalog library covers the key disease fields and clinical indication information of the main stream of interest in the current health risk market;
step (4), forming a clinical medical dictionary base based on a technology of grouping the big data disease seeds and an ICD-10 coding three-code integrated system;
step (5), the insurance medical terms are transmitted into a clinical medical dictionary library to be screened step by step according to the catalog grade, and the clinical medical dictionary library is generated based on the grouping of big data disease types and has a tree structure, namely, the disease types are combined into a hierarchical structure from a main catalog to a tertiary catalog from anatomy, etiology and operation;
and (6) after the expert auditing, forming an insurance medical-clinical medical coding mapping dictionary library, wherein the dictionary library realizes the multi-to-multi-association mapping of the etiology, operation type and non-operation treatment means information concerned in the insurance medical and the clinical medical coding.
2. The method for encoding and mapping insurance medical and clinical medicine according to claim 1, wherein: in the step (1), major disease information specified by each health insurance institution insurance product term, related wind control means, health notification books and insurance prison is researched; and classifying and summarizing the original insurance medical terms and diseases in the rule base according to the serious diseases, moderate diseases, mild diseases and basic diseases with the future serious disease risks mentioned in the health notice, and marking corresponding disease classification labels.
3. The method for encoding and mapping insurance medical and clinical medicine according to claim 1, wherein: the collection of insurance medical terms in the step (2) comprises clinical diagnosis terms, operation terms, clinical indication terms and non-operation treatment means terms which may exist; for each insurance medical term, attribute tags of corresponding information are marked.
4. The method for encoding and mapping insurance medical and clinical medicine according to claim 1, wherein: in the step (5), for a certain insurance medical disease term a, a query path of the insurance medical disease term a can be obtained through an insurance medical catalog library, that is, the query path of the insurance medical disease term a is (a main catalog: a name, a primary catalog: a name, a secondary catalog: a name, a tertiary catalog: a name), the query path of the insurance medical disease term a is used as a query condition of a clinical dictionary library, and is gradually screened according to catalog grades, a clinical medical term set associated with the insurance medical disease term a can be obtained after query is carried out, morphological codes and disease codes corresponding to each clinical medical term in the set are returned, and positions of each level catalog in a big data disease type group and corresponding average cost in the group are obtained; each insurance medical term corresponds to one or more clinical medical terms; and submitting the matched data to clinical medical professionals for review.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010335743.XA CN111444333B (en) | 2020-04-25 | 2020-04-25 | Coding mapping method for insurance medicine and clinical medicine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010335743.XA CN111444333B (en) | 2020-04-25 | 2020-04-25 | Coding mapping method for insurance medicine and clinical medicine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111444333A CN111444333A (en) | 2020-07-24 |
| CN111444333B true CN111444333B (en) | 2023-08-11 |
Family
ID=71654685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010335743.XA Active CN111444333B (en) | 2020-04-25 | 2020-04-25 | Coding mapping method for insurance medicine and clinical medicine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111444333B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329450A (en) * | 2020-07-29 | 2021-02-05 | 好人生（上海）健康科技有限公司 | Insurance medical code mapping dictionary table production method |
| CN112052667B (en) * | 2020-09-27 | 2024-05-03 | 沈阳东软智能医疗科技研究院有限公司 | Method, device and equipment for realizing medical coding mapping |
| CN114783623B (en) * | 2022-06-24 | 2022-08-26 | 北京惠每云科技有限公司 | Medical rule extraction method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574103A (en) * | 2015-12-11 | 2016-05-11 | 浙江大学 | Method and system for automatically establishing medical term mapping relationship based on word segmentation and coding |
| CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
| CN107577826A (en) * | 2017-10-25 | 2018-01-12 | 山东众阳软件有限公司 | Classification of diseases coding method and system based on raw diagnostic data |
| CN109408820A (en) * | 2018-10-17 | 2019-03-01 | 长沙瀚云信息科技有限公司 | A kind of medical terminology mapped system and method, equipment and storage medium |
| CN109615533A (en) * | 2018-10-24 | 2019-04-12 | 平安健康保险股份有限公司 | Hospital efficiency analysis method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020128861A1 (en) * | 2001-01-05 | 2002-09-12 | Lau Lee Min | Mapping clinical data with a health data dictionary |
| WO2003079142A2 (en) * | 2002-02-22 | 2003-09-25 | The Regence Group | Claims clinical code editing and procedure management tool |
| US20050027566A1 (en) * | 2003-07-09 | 2005-02-03 | Haskell Robert Emmons | Terminology management system |
| WO2017180483A1 (en) * | 2016-04-11 | 2017-10-19 | Amgine Technologies (Us), Inc. | Insurance evaluation engine |
| US11488713B2 (en) * | 2017-08-15 | 2022-11-01 | Computer Technology Associates, Inc. | Disease specific ontology-guided rule engine and machine learning for enhanced critical care decision support |
| US11636949B2 (en) * | 2018-08-10 | 2023-04-25 | Kahun Medical Ltd. | Hybrid knowledge graph for healthcare applications |
-
2020
- 2020-04-25 CN CN202010335743.XA patent/CN111444333B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574103A (en) * | 2015-12-11 | 2016-05-11 | 浙江大学 | Method and system for automatically establishing medical term mapping relationship based on word segmentation and coding |
| CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
| CN107577826A (en) * | 2017-10-25 | 2018-01-12 | 山东众阳软件有限公司 | Classification of diseases coding method and system based on raw diagnostic data |
| CN109408820A (en) * | 2018-10-17 | 2019-03-01 | 长沙瀚云信息科技有限公司 | A kind of medical terminology mapped system and method, equipment and storage medium |
| CN109615533A (en) * | 2018-10-24 | 2019-04-12 | 平安健康保险股份有限公司 | Hospital efficiency analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111444333A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444333B (en) | Coding mapping method for insurance medicine and clinical medicine | |
| US8086468B2 (en) | Method for computerising and standardizing medical information | |
| Lindquist | VigiBase, the WHO global ICSR database system: basic facts | |
| CN104765947B (en) | A kind of potential drug adverse reaction data digging method towards big data | |
| Salvador-Carulla et al. | Developing a tool for mapping adult mental health care provision in Europe: the REMAST research protocol and its contribution to better integrated care | |
| Dubuc et al. | Development of integrated care pathways: toward a care management system to meet the needs of frail and disabled community-dwelling older people | |
| CN112164460A (en) | Intelligent disease auxiliary diagnosis system based on medical knowledge map | |
| US20170109502A1 (en) | System and method for clinical trial candidate matching | |
| US20140095209A1 (en) | System and method for mitigating the risk of hemolytic transfusion reactions | |
| Diao et al. | Automated ICD coding for primary diagnosis via clinically interpretable machine learning | |
| Van Kempen et al. | Diagnosis of frailty after a comprehensive geriatric assessment: differences between family physicians and geriatricians | |
| Godden et al. | The use of acute hospital services by elderly residents of nursing and residential care homes | |
| Sears et al. | Identification of work-related injuries in a state trauma registry | |
| Baldwin | Linked record medical information systems | |
| Gambarte et al. | A practical approach to advanced terminology services in health information systems | |
| Kurbasic et al. | The advantages and limitations of international classification of diseases, injuries and causes of death from aspect of existing health care system of Bosnia and Herzegovina | |
| Ashoori et al. | A model to predict the sequential behavior of healthy blood donors using data mining | |
| Karmel et al. | Transitions from hospital to residential aged care in Australia | |
| CN111210881B (en) | Dynamic generation method for insurance disease spectrum detection based on medical big data | |
| US20150356130A1 (en) | Database management system | |
| Makaram et al. | Lessons learned from hip fracture registries–From the Scottish perspective to global practice | |
| Heslop et al. | An analysis of high-cost users at an Australian public health service organization | |
| Lavergne | Identifying distinct geographic health service environments in British Columbia, Canada: cluster analysis of population-based administrative data | |
| CN112732673A (en) | System for realizing analysis and processing of chronic disease quality control data based on big data | |
| Xiao et al. | Developing a standard protocol for clinical data exchange and analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |