Enterprise AI Analysis

A study on the methods of terminology expansion based on inclusion and exclusion criteria

With the rapid growth of medical knowledge and text resources, traditional manual expansion of medical terminology is not only costly but also time-consuming, making it difficult to keep up with the speed of medical knowledge generation. This article aims to propose a mixed term recognition method based on conditional random fields (CRF) and rules using clinical inclusion and exclusion criteria (NAE) text, to achieve accurate extraction of candidate terms in NAE criteria. The term is indexed and matched using Lucene and Solr driven Usagi technology to obtain a new term set. Experimental results have shown that the method has significant effects in improving the accuracy of term recognition and expanding coverage. Although the data scale of the inclusion and exclusion standards is limited, the proposed method demonstrates good practical potential. This article systematically introduces inclusion and exclusion standards for the first time, providing an innovative path for the construction of medical terminology resources and information standardization.