A method for extracting text abstracts from electronic medical records

Abstract

A method for extracting text summaries from electronic medical records. By defining a semantic coverage loss function, the abstract summaries summed up by doctors in the past can be used for training an automatic extraction summarization model, which avoids data labeling. Select the more important sentences from the original electronic medical record as a candidate set, narrow the search scope of the automatic extraction abstract, and then by listing the different combinations of sentences in the candidate set, find the sentence combination with the highest semantic coverage in the original electronic medical record. As an extractive summary, when judging the semantic coverage, the judgment is made based on the semantic information of all sentences in the candidate set, which reduces the possibility of information redundancy and information loss in the automatic extractive summary, and improves the quality of the automatic extractive summary.

Description

technical field [0001] The invention relates to the technical field of medical informatization, in particular to a method for extracting text abstracts from electronic medical records. Background technique [0002] The electronic medical record is the original record of the whole process of the patient's diagnosis and treatment in the hospital, and it is also an important system that provides clinical decision support for physicians. Although electronic medical records replace paper medical records and facilitate the storage and search of related data, many important information of electronic medical records are still deeply buried in a large amount of text content. If physicians need to read a patient's electronic medical record comprehensively in clinical work, it often takes a long time. Therefore, extracting abstracts from electronic medical records is of great significance to increase the efficiency of physicians’ clinical work. Especially in the entry of discharge med...

AI Technical Summary

Problems solved by technology

[0004] However, the current general extractive summarization technology faces the following problems: 1) The commonly used extractive summarization technology generally takes the sentence in the text as the extraction unit and relies on the judgment of text similarity to obtain the more important sentences in the text, that is, from A subset is extracted from all the sentences in the original text, but the semantic connection between sentences in the extracted summary is weak, so the coverage of the extracted sentence combination on the original text is not necessarily the highest, and information redundancy will still occur. Situations where residual or critical information is missing

2) The performance of general unsupervised summary extraction models is often unsatisfactory. If you want to obtain a high-performance extraction model, you need data labeling. The purpose of data labeling is to mark important sentences from the original electronic medical records. Data labeling of medical texts is a A highly specialized, costly, time-consuming, and difficult-to-manage job

Images