LIST-LUX: Disorder Identification from Clinical Texts

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 427–432, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics LIST-LUX: Disorder Identification from Clinical Texts Asma Ben Abacha, Aikaterini Karanasiou, Yassine Mrabet, and Julio Cesar Dos Reis* Luxembourg Institute of Science and Technology (LIST) 29, avenue John F. Kennedy, L-1855 Kirchberg, Luxembourg [asma.benabacha, aikaterini.karanasiou, yassine.mrabet]@list.lu * Institute of Computing, University of Campinas Av. Albert Einstein, 1251, Cidade Universit´aria Zeferino Vaz, 13083-852, Campinas, SP Brazil julio.dosreis@ic.unicamp.br Abstract This paper describes our participation in task 14 of SemEval 2015. This task focuses on the analysis of clinical texts and includes: (i) the recognition of the span of a disorder men- tion and (ii) its normalization to a unique concept identifier in the UMLS/SNOMED- CT terminology. We propose a two-step ap- proach which relies first on Conditional Ran- dom Fields to detect textual mentions of dis- orders using different lexical, syntactic, or- thographic and semantic features such as on- tologies and, second, on a similarity measure and SNOMED to determine the relevant CUI. We present and discuss the obtained results on the development corpus and the official test corpus. 1 Introduction With the exponential growth of clinical texts, rec- ognizing named entities becomes more and more important for several applications such as infor- mation retrieval, question answering or scientific analysis. The task of identifying mentions to medical concepts in free text and mapping these mentions to a knowledge base was recently pro- posed in ShARe/CLEF eHealth Evaluation Lab 2013 (Suominen et al., 2013). The task 7 in SemEval 2014 (Pradhan et al., 2014) elaborates in that previous effort focusing on the recognition and normalization of named entity mentions belonging to the UMLS semantic group “Disorders”. Similarly, task 14-1 of SemEval 20151 1http://alt.qcri.org/semeval2015/task14/ targets the identification of disorder mentions and their association to the relevant concept identifiers (CUI) in the UMLS/SNOMED CT terminology. A disorder is normalized to “CUI-less” if the disor- der mention is present, but there is no good equiv- alent CUI in UMLS/SNOMED-CT. Task 14-2b of SemEval 2015 specifically addresses Disorder Slot Filling. The aim is to identify the values of nine slots (negation indicator, subject, uncertainty indi- cator, course, severity, conditional, generic indica- tor and body location), given the span of disorder mentions from task 14-1. In this paper we focus on task 1, i.e. disorder identification. In the following section we describe our approach to the detection of disorder mentions in clinical texts and their categorization with the rel- evant UMLS/SNOMED-CT CUI. In section 3 we present and discuss the obtained results on the de- velopment corpus and the official results before giv- ing our concluding remarks in section 4. 2 Two-Step Approach for Disorder Identification Our method includes two main steps: (1) the detec- tion of disorder mentions using Conditional Ran- dom Fields (CRFs) and (2) the extraction of the as- sociated CUI from SNOMED based on similarity measures. These two steps are described in more details in the following sections. 2.1 Step I …

Content truncated to 500 words