Electronic medical record text structuring method

Abstract

The invention discloses an electronic medical record text structuring method. The method comprises the following steps that 1, a medical knowledge database is loaded; 2, an electronic medical record text is read; 3, word segmentation is carried out on short sentences through a forwards maximum match algorithm, and words in sentences, word properties and relative position relations are obtained; 4, whether the semantics in the sentences for disease information description is positive or negative is judged; 5, disease information elements are extracted; 6, the steps 2-5 are repeated till all interesting contents in the electronic medical record are obtained; 7, different expressions of the disease information elements are combined, the same disease information is combined according to a medical synonym bank, and redundant information is removed; 8, disease description information elements are stored in a structure / class mode, the structuring process is finished, disease relevant information can be effectively extracted from medical record description text, structural expression for disease information is formed, and therefore disease occurrence regularity, definite diagnosis ways, treatment effects and the like are deeply explored.

Description

technical field [0001] The invention relates to a text structuring method for natural language, in particular to a text structuring method for electronic medical records. Background technique [0002] Electronic medical records are electronic documents that record the whole process of diagnosis and treatment after patients enter the hospital. When the doctor is entering the electronic medical record, the relevant fields will be stored in the corresponding fields in the relational database; when the patient is printing the electronic medical record, the required fields will be retrieved from the database and displayed in a certain document format. [0003] The current development of epidemiology and outpatient medicine requires medical workers not only to provide effective treatment for patients, but also to summarize experience and explore the rules of clinical treatment and clinical experiments. This requires in-depth data mining of electronic medical records to discover n...

AI Technical Summary

Problems solved by technology

[0012] At present, the structured entry of medical records is relatively mature, and major medical software companies have launched related products; due to the complexity of natural language expressions and the professionalism of medical terms, the post-structured work of medical records has a large amount of tasks and high difficulty The characteristics of related research in China are relatively sluggish, and this invention has a significant role in promoting the in-depth mining of medical record data

Images