Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Operation classification coding method based on original operation data

A coding method and surgical technology, which is applied in the fields of artificial intelligence and medical informatization, can solve problems such as differences in coding results, non-uniform standard surgical coding standards, and uneven understanding, achieving rapid classification, saving human resources, and fast coding speed Effect

Inactive Publication Date: 2020-05-22
SHAN DONG MSUN HEALTH TECH GRP CO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] (1) Hospital coding personnel have uneven understanding of standard surgical coding, resulting in differences in coding results
[0004] The coding and classification work of surgical coding in hospitals is done manually, because of the limited manpower (even many hospitals do not have coders), the quality of coders is uneven, and the coders' interpretation of standards and the degree of grasp of the huge content of coding dictionaries uneven
Therefore, the number of manual code matching in the hospital is limited every day, and there are some cases of misjudgment
The coding thickness and judgment standards of coders also vary from person to person. These problems will be very obvious when the data of different hospitals are reported, reviewed, and communicated together. period, the encoding results also differ
[0005] (2) The actual operation performed by the doctor's personalization and custom input is not fully compatible with the standard operation coding library
The above-mentioned various reasons lead to great troubles in the actual business of the hospital when most doctors use the program to select the operation or write the operation by the doctor himself when filling out the operation.
[0007] (3) The standard operation coding standards in each hospital are not uniform
[0010] The imperfection and inconsistency of medical information greatly restrict the construction of medical information platforms and medical information warehouses

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
  • Operation classification coding method based on original operation data
  • Operation classification coding method based on original operation data
  • Operation classification coding method based on original operation data

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0071] Example 1: Assume that the operation input by the doctor obtained in step 1 is cesarean section through the lower uterine segment, and the result of cesarean section lower uterine segment is obtained after step 2 (in order to eliminate the influence of punctuation marks on matching, the system replaces Punctuation marks, the standard surgery used for training in step 4 also removes all punctuation marks), the processing results of step 2 go through step 3, no corresponding standard surgery is found, and enter step 4. In step four, the calculation result of the two-way surgical data entity recognition model is 0.5831, and then enters the neural entity relationship discriminant network calculation to obtain the result of the standard surgery with the highest relationship as 0.999974.1x00 low uterine segment cesarean section. From this example, it can be found that the doctor's random writing order and a small amount of excess words for some operations will not affect the c...

example 2

[0072] Example 2: Assume that the operation inputted by the doctor obtained in step 1 is closed reduction and PFNA internal fixation of femoral fracture, and closed reduction and PFNA internal fixation of femoral fracture is obtained after step 2 (there are no special characters or punctuation marks, so step 2 is not performed. treatment), after step three, if no corresponding standard operation is found, go to step four. In step four, the calculation result of the two-way surgical data entity recognition model is 0.8013, and then enters the neural entity relationship discriminant network calculation to obtain the standard surgery with the highest relationship. The PFNA mentioned in this example is a new type of intramedullary nail. From this example, it can be found that some concepts not mentioned in detail in the standard diagnosis written by the doctor during the operation can be automatically identified by the system.

[0073] Deployment scheme of surgical automatic codin...

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 invention relates to the technical field of medical informatization and the technical field of artificial intelligence, in particular to an operation classification encoding method and system based on original operation data. The method comprises following steps: recieving orginal operation data; preprocessing the input original operation data; carrying out retrieval and judgment by using an international operation standard classification code ICD-9-CM-3; inquiring a hospital admission record, a disease course record and a hospital discharge record; and encoding according to the preprocessed original operation data and the acquired information in the medical record of the patient by using a bidirectional operation data entity identification model and a neural entity weight relationshipdiscrimination network, and outputting an encoding result and an accuracy evaluation result. Compared with manual coding, automatic coding is more efficient and faster, classification is stable, large-batch coding and classification of original medical records can be achieved in a short time, and data can be quickly prepared and sorted for big data application and artificial intelligence in the medical field.

Description

technical field [0001] The present invention relates to the field of medical information technology and artificial intelligence technology, in particular to a surgical classification coding method and system based on raw surgical data. Background technique [0002] With the continuous deepening of the national medical reform and the comprehensive medical layout. The informatization of medical data greatly limits the improvement of medical reform and medical services in all aspects. In the period of comprehensive development of medical big data and artificial intelligence, medical data informatization has begun to show signs, and it has begun to provide auxiliary decision-making and information support for the diagnosis and treatment process, which can help doctors improve efficiency and greatly reduce the work of doctors. In the evolutionary history of medical informatization, the standardization of medical data has always been a difficult problem to be solved and improved....

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 Applications(China)
IPC IPC(8): G06F40/126G06F40/295G06F40/103G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 桑波吴军高希余李福友李森蔡相鹏李亮张述睿
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
Eureka Blog
Learn More
PatSnap group products