icd-11 coding retrieval method based on natural semantic processing and knowledge graph

A technology of ICD-11 and knowledge graph, applied in natural language data processing, semantic analysis, electronic digital data processing, etc., can solve problems such as incompatibility, wrong combination, cumbersome operation, etc., and reduce manpower consumption cost and communication cost , Ensure a high degree of consistency and effective management decisions

Active Publication Date: 2022-07-19
SHAN DONG MSUN HEALTH TECH GRP CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] But the inventor finds that the retrieval of ICD codes can only be retrieved by keywords or pinyin brevity codes at present. For ICD-11, only the codes of each part in the diagnosis can be retrieved, and then combined together, which is inconvenient to use and Inaccurate; on the one hand, due to the incompatibility between clinical terms and ICD-11 standard diagnostic coding terms, on the other hand, the retrieval of each part is very cumbersome for clinicians and coders, and a diagnosis needs to be searched many times to obtain Combines an encoded result and is prone to wrong combinations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • icd-11 coding retrieval method based on natural semantic processing and knowledge graph
  • icd-11 coding retrieval method based on natural semantic processing and knowledge graph
  • icd-11 coding retrieval method based on natural semantic processing and knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] like Figure 1-15 As shown, Embodiment 1 of the present disclosure provides an ICD-11 code retrieval method based on natural semantic processing and knowledge graph, including the following steps:

[0050] S1: Natural language processing of freely written clinical diagnoses.

[0051] Perform entity identification and entity relationship identification on the input original clinical diagnosis, and mark entities and their entity types, such as disease abnormalities, anatomical parts, organ tissues, properties, classification, staging, etiology, clinical manifestations, microorganisms, chemical substances And so on, and then mark out the decoration and restriction relationships between entities.

example

[0052] Example: acute left-sided Escherichia coli pyelonephritis.

[0053] This embodiment marks the entity and the relationship between entities for the diagnosis, such as figure 1 shown.

[0054] Entity marked for this diagnosis: ① renal pelvis, entity type is anatomical site; ② Escherichia coli, entity type is microorganism; ③ nephritis, entity type is disease or abnormality; ④ left, entity type is orientation; ⑤ acute, entity type Type is nature.

[0055] There are four groups of entity relationships, which are: "renal pelvis" as an anatomical modifier to limit disease abnormalities: nephritis; "left" as an orientation modifier to limit anatomical sites: renal pelvis; "acute" as a period modifier to limit disease abnormalities: nephritis; "Bacteria" as microbial (causative) modifiers to limit disease abnormalities: nephritis.

[0056] The entity and type recognition uses the entity concept description dictionary in the self-maintained medical knowledge graph and the ter...

Embodiment 2

[0177] Embodiment 2 of the present disclosure provides an ICD-11 code retrieval system based on natural semantic processing and knowledge graph, including:

[0178] The data acquisition module is configured to: acquire freely written clinical diagnosis text data;

[0179] The entity recognition module is configured to: perform natural language processing on the acquired text data, obtain the entity and entity relationship recognition result, and mark the entity and the entity type to which it belongs;

[0180] The knowledge graph labeling module is configured to: label other entities directly related to the entity on the medical knowledge graph, and record the relationship weight coefficient;

[0181] The candidate code search module is configured to: combine the entity relationship and the relationship weight coefficient on the medical knowledge graph to search for the candidate code through the tree structure of the standard diagnosis entity and entity relationship;

[0182...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present disclosure provides an ICD-11 coding retrieval method based on natural semantic processing and knowledge graph, which obtains freely written clinical diagnosis text data; performs natural language processing on the obtained text data, obtains entity and entity relationship recognition results, and marks them out. Entity and the entity type to which it belongs; mark other entities directly linked to the entity on the medical knowledge graph, record the relationship weight coefficient; combine the entity relationship and relationship weight coefficient on the medical knowledge graph, through the standard diagnosis of the entity and entity relationship tree structure Searching for candidate codes; retrieving and screening the combinations of candidate codes according to ICD-11 coding rules, and selecting the most reasonable combination codes as the ICD-11 diagnostic codes; the present disclosure realizes the intelligence of the retrieval of the ICD-11 diagnostic codes, and solves the problem of There are no coders or insufficient coders in medical institutions, which reduces labor costs and communication costs.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, in particular to an ICD-11 code retrieval method based on natural semantic processing and knowledge graph. Background technique [0002] The statements in this section merely provide background related to the present disclosure and do not necessarily constitute prior art. [0003] The International Classification of Diseases (ICD), as an international classification standard for diseases and related health problems, is an important part of the health information standard system. It has been more than 100 years since its inception, and it has undergone several revisions during this period, from initially only used for statistics on causes of death, to a statistical classification involving all diseases and causes of death, including injuries and poisoning and their external causes. Disease classification is to classify diseases according to certain characteristics according to ce...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/295G06F40/30G16H50/70
CPCG06F40/295G06F40/30G16H50/70
Inventor 桑波孙钊高希余樊昭磊李森李福友
Owner SHAN DONG MSUN HEALTH TECH GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap