WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2872
Volume 14, 2017
DNER Clinical (Named Entity Recognition) from Free Clinical Text to Snomed-CT Concept
Authors: ,
Abstract: We have developed a new approach for the (NER) named entity recognition problem, in specific domains like the medical environment. The main idea is recognize clinical concepts in free text clinical reports. Actually most of the information contained in clinical reports from the Electronic Health System (EHR) of a hospital, is written in natural language free text, so we are researching the problem of automatic clinical named entities recognition from free text clinical reports, in this kind of texts we design a new NER approach, like a hybrid of theses approach, dictionary-based, machine learning, and a fuzzy function. To develop this, from clinical reports free text, we apply an unsupervised, shallow learning neural network, word2vec to represent words of the text as “words vectors”. Second, we use a specific domain dictionary-based gazetteer (using the ontology Snomed-CT to get the standard clinical code for the clinical concept), for match the correct concept, and recognize the named entity like a clinical concept, we use the distance and similarity between of the “words vector” of the terms from the document and the distance of the “word vector” with the Snomed-CT description term, applying a fuzzy function “DNER”, to get the best degree of identification for the named entity recognized. We have applied our approach on a Dataset with 318.585 clinical reports in Spanish from the emergency service of the Hospital “Rafael Méndez” from Lorca (Murcia) Spain, and preliminary results are encouraging.
Search Articles
Keywords: Snomed-CT, word2vec, doc2vec, clinical information extraction, skipgram, medical terminologies, search semantic, named entity recognition, ner, medical entity recognition
Pages: 83-91
WSEAS Transactions on Computers, ISSN / E-ISSN: 1109-2750 / 2224-2872, Volume 14, 2017, Art. #10