Realization method and system for electronic medical record post-structuring and auxiliary diagnosis

Abstract

The invention relates to a realization method and system for electronic medical record post-structuring and auxiliary diagnosis. A combination mode of multiple types of distance measurement is used: a character string editing distance refers to a minimum number of replacement, insertion and deletion operations required for converting a character into another character string; a Jaro-Winkler distance measures similarity between two character strings and is used for repeated recording detection; a geometric mean value of a Chinese character distance and a Chinese character input method is adopted as comprehensive similarity measurement for measuring similarity between characteristic texts; characteristic ranking is realized by using a TF-IDF method and is used for assessing the importance of characteristic terms relative to documents in a file set or a corpus library, and the importance of the characteristic terms is in direct proportion to an occurrence frequency in the documents and is in inverse proportion to an occurrence document in the corpus library; and files are converted to be in a file format of PU learning of a positive example data set and an unlabelled data set according to the generated characteristic terms, and through the PU learning, the system automatically recommends related diagnoses for clinical medical personnel to refer.

Description

technical field [0001] The invention relates to an electronic medical record structure system and its realization method, in particular to a realization method and system of the post-structuralization and auxiliary diagnosis of the electronic medical record. Background technique [0002] Traditional electronic medical records are recorded in the form of text descriptions. Although the structure of medical records has certain standards as a basis, due to the complexity of related medical clinical fields, there are different contents in each field. Even if the same content, the corresponding The description methods are also different, so it is difficult to generate a structured electronic medical record: one way is to extract structured content from ordinary text descriptions through natural language processing (Natural Language Processing, NLP). Another solution is to realize the structuring of medical record information through structured entry. The fully structured electron...

AI Technical Summary

Problems solved by technology

The many shortcomings of structured electronic medical records lead to the unsmooth development of domestic electronic medical records, so many hospitals still use the electronic medical record system with free text input. Such electronic medical records are just a transcription process from paper data to electronic data, which is not conducive to In-depth data analysis

Many electronic medical record systems do not have perfect standards to follow in the input process, and there is no unified specification, so it is a potential obstacle for future data exchange, data integration, and data analysis

Images