Koeling, Rob, Carroll, John, Tate, Rosemary and Nicholson, Amanda (2011) Annotating a corpus of clinical text records for learning to recognize symptoms automatically. In: Nytrø, Øystein, Slaughter, Laura and Moen, Hans (eds.) Proceedings of LOUHI 2011 Third International Workshop on Health Document Text Mining and Information Analysis. CEUR Workshop Proceedings, 744 . Norwegian University of Science and Technology, Trondheim, Norway, pp. 43-50. ISBN 1613-0073

PDF (Copyright with authors) - Published Version Download (480kB)

Abstract

We report on a research effort to create a corpus of clinical free text records enriched with annotation for symptoms of a particular disease (ovarian cancer). We describe the original data, the annotation procedure and the resulting corpus. The data (approximately 192K words) was annotated by three clinicians and a procedure was devised to resolve disagreements. We are using the corpus to investigate the amount of symptom-related information in clinical records that is not coded, and to develop techniques for recognizing these symptoms automatically in unseen text.

Item Type:	Book Section
Additional Information:	E-publication
Schools and Departments:	Brighton and Sussex Medical School > Primary Care and Public Health
Related URLs:	Organisation
Depositing User:	Rob Koeling
Date Deposited:	06 Feb 2012 19:49
Last Modified:	15 Aug 2012 15:51
URI:	http://sro.sussex.ac.uk/id/eprint/22351

View download statistics for this item

📧 Request an update