Temporal Annotation in the Clinical Domain

Temporal Annotation in the Clinical Domain William F. Styler IV1, Steven Bethard2, Sean Finan3, Martha Palmer1, Sameer Pradhan3, Piet C de Groen4, Brad Erickson4, Timothy Miller3, Chen Lin3, Guergana Savova3 and James Pustejovsky5 1 Department of Linguistics, University of Colorado at Boulder 2 Department of Computer and Information Sciences, University of Alabama at Birmingham 3 Children’s Hospital Boston Informatics Program and Harvard Medical School 4 Mayo Clinic College of Medicine, Mayo Clinic, Rochester, MN 5 Department of Computer Science, Brandeis University Abstract This article discusses the requirements of a formal specification for the annotation of temporal information in clinical narratives. We discuss the implementation and extension of ISO-TimeML for annotating a corpus of clinical notes, known as the THYME cor- pus. To reflect the information task and the heavily inference-based reasoning demands in the domain, a new annotation guideline has been developed, “the THYME Guidelines to ISO-TimeML (THYME-TimeML)”. To clarify what relations merit annotation, we distinguish between linguistically-derived and inferentially-derived temporal orderings in the text. We also apply a top performing Temp- Eval 2013 system against this new resource to measure the difficulty of adapting systems to the clinical domain. The corpus is available to the community and has been proposed for use in a SemEval 2015 task. 1 Introduction There is a long-standing interest in temporal reason- ing within the biomedical community (Savova et al., 2009; Hripcsak et al., 2009; Meystre et al., 2008; Bramsen et al., 2006; Combi et al., 1997; Keravnou, 1997; Dolin, 1995; Irvine et al., 2008; Sullivan et al., 2008). This interest extends to the automatic ex- traction and interpretation of temporal information from medical texts, such as electronic discharge sum- maries and patient case summaries. Making effective use of temporal information from such narratives is a crucial step in the intelligent analysis of informat- ics for medical researchers, while an awareness of temporal information (both implicit and explicit) in a text is also necessary for many data mining tasks. It has also been demonstrated that the temporal in- formation in clinical narratives can be usefully mined to provide information for some higher-level tempo- ral reasoning (Zhao et al., 2005). Robust temporal understanding of such narratives, however, has been difficult to achieve, due to the complexity of deter- mining temporal relations among events, the diver- sity of temporal expressions, and the interaction with broader computational linguistic issues. Recent work on Electronic Health Records (EHRs) points to new ways to exploit and mine the informa- tion contained therein (Savova et al., 2009; Roberts et al., 2009; Zheng et al., 2011; Turchin et al., 2009). We target two main use cases for extracted data. First, we hope to enable interactive displays and summaries of the patient’s records to the physician at the time of visit, making a comprehensive review of the patient’s history both faster and less prone to oversights. Sec- ond, we hope to enable temporally-aware secondary research across large databases of medical records (e.g., “What percentage of patients who undergo pro- cedure X develop side-effect …

Content truncated to 500 words