Structured processing method for cross-type breast tumor clinical document

A technology of breast tumors and processing methods, which is applied in the field of structured processing of breast tumor clinical documents, can solve the problems of complex medical information and difficulty in meeting the structural requirements of cross-type clinical documents, etc., and achieve simple implementation and solve structured processing problems , saving manpower and time

Inactive Publication Date: 2017-12-01
DONGHUA UNIV +1
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Medical information is more complex and more flexible, and different types of clinical document reports have their own language characteri

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
  • Structured processing method for cross-type breast tumor clinical document
  • Structured processing method for cross-type breast tumor clinical document
  • Structured processing method for cross-type breast tumor clinical document

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Below in conjunction with specific embodiment, further illustrate the present invention.

[0026] combine figure 1 , the present invention carries out structured processing for unstructured Chinese breast cross-type clinical documents, the steps are: (1) preprocessing the clinical texts, including segmenting short texts and performing word segmentation on the short texts;

[0027] (2) Partial corpus annotation for single-type reports for word segmentation results; (3) Entity recognition for cross-type reports using semi-supervised learning; (4) Extracting structured results such as organization, location, features, and feature values.

[0028] The breast ultrasound text contains the following information, as shown in Table 1:

[0029] Table 1 Chinese breast ultrasound sample data case

[0030]

[0031] The mammogram text contains the following information, as shown in Table 2:

[0032] Table 2 Chinese mammogram sample data case

[0033]

[0034] An analysis of...

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 provides a structured processing method for a cross-type breast tumor clinical document. The method comprises the steps of 1: preprocessing a text of the breast tumor clinical document: segmenting the short text and performing word segmentation on the segmented short text; 2: for a word segmentation result, performing partial corpus tagging of a single-type report; 3: by adopting corpora of the single-type report, realizing cross-type entity identification; and 4: extracting a structured result, which comprises an organization, a position, a characteristic and an eigenvalue. According to the method provided by the invention, the deficiencies in the prior art are overcome; the extraction of structured information is automatically formed, so that the manpower and time are saved; the method is not limited to the report type and can be applied to characteristic identification and text structuring of different reports; the structured processing problem of Chinese cross-type clinical documents is solved; and the method is simple to realize, high in processing speed and high in processing result accuracy.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for structured processing of breast tumor clinical documents based on cross-type semi-supervised learning. Background technique [0002] Due to the rapid development of computer technology in recent years, the electronic storage of information in various industries has become more and more popular, especially medical data. Nowadays, patients' medical records have gradually been converted to electronic medical records, replacing handwritten paper medical records. At present, hospitals have accumulated a large number of electronic medical records. Although compared with traditional paper medical records, electronic medical records are easier to collect and analyze data. The inspection information in the report is all medical records stored in natural language. In order to facilitate data management and obtain useful information from it, natural language...

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
IPC IPC(8): G06F17/27G06F19/00
CPCG06F40/211G06F40/284
Inventor 陈德华车楠楠朱立峰乐嘉锦潘乔
Owner DONGHUA UNIV
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