UTHealth at SemEval-2016 Task 12: an End-to-End System for Temporal Information Extraction from Clinical Notes

Proceedings of SemEval-2016, pages 1292–1297, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics UTHealth at SemEval-2016 Task 12: an End-to-End System for Temporal Information Extraction from Clinical Notes Hee-Jin Lee, Yaoyun Zhang, Jun Xu, Sungrim Moon, Jingqi Wang, Yonghui Wu, and Hua Xu University of Texas Health Science Center at Houston Houston, TX, USA hee.jin.lee@uth.tmc.edu, {firstname.lastname}@uth.tmc.edu Abstract The 2016 Clinical TempEval challenge ad- dresses temporal information extraction from clinical notes. The challenge is composed of six sub-tasks, each of which is to identify: (1) event mention spans, (2) time expression spans, (3) event attributes, (4) time attributes, (5) events’ temporal relations to the docu- ment creation times (DocTimeRel), and (6) narrative container relations among events and times. In this article, we present an end-to-end system that addresses all six sub-tasks. Our system achieved the best performance for all six sub-tasks when plain texts were given as input. It also performed best for narrative con- tainer relation identification when gold stan- dard event/time annotations were given. 1 Introduction Temporality is crucial in understanding the course of clinical events from a patient’s electronic health records. Since a large part of the information on temporality resides in narrative clinical notes, auto- matic extraction of temporal information from clin- ical notes using natural language processing (NLP) techniques has received much attention. Over the years, research community challenges on clinical temporal information extraction have been orga- nized; i.e., the 2012 Informatics for Integrating Biology and the Bedside (i2b2) challenge (Sun et al., 2013), the 2013/2014 CLEF/ShARe chal- lenge (Mowery et al., 2014), and the 2015 Clinical TempEval challenge (Savova et al., 2015). These challenges provide annotated corpora on temporal entities and relations, which facilitate comparisons of multiple systems and expediate the development of clinical temporal information extraction method- ologies. The 2016 Clinical TempEval challenge is the most recent community challenge that addresses temporal information extraction from clinical notes. Follow- ing the 2015 Clinical TempEval challenge, the 2016 challenge consists of six sub-tasks, each of which is to identify: (1) spans of event mentions, (2) spans of time expressions, (3) attributes of events, (4) at- tribute of times, (5) events’ temporal relations to the document creation times (DocTimeRel), and (6) nar- rative container relations among events and times (TLINK:Contains). 440 annotated clinical notes from Mayo Clinic, or the THYME corpus (Styler IV et al., 2014), were provided as the training data set, and 153 plain text clinical notes were provided as the test set. The participating systems were evalu- ated through two phases. In phase 1, the systems were evaluated on their results for all six sub-tasks given plain texts as inputs. In phase 2, system pre- dictions on DocTimeRel and TLINK:Contains were evaluated given the gold-standard event annotations (EVENT) and time annotations (TIMEX3). In this article, we describe a comprehensive sys- tem that addresses all six sub-tasks. We designed the system by adapting state-of-the-art techniques from previous work on named entity recognition (Tang et al., 2013a; Jiang et al., 2011) and temporal …

Content truncated to 500 words