Medical Informatics Publications

These publications describe my work in Medical Informatics. These usually revolve around applying techniques we have developed for general English to the medical domain, which can include clinical notes or scholarly writing about medical topics.

2009

UMLS-Interface and UMLS-Similarity : Open Source Software for Measuring Paths and Semantic Similarity (McInnes, Pedersen, and Pakhomov) - To appear in the Proceedings of the Annual Symposium of the American Medical Informatics Association, Nov 14-18, 2009, San Francisco, CA
Supervised and Knowledge-based Methods for Disambiguating Terms in Biomedical Text using the UMLS and MetaMap (McInnes) - PhD Dissertation, Department of Computer Science and Engineering, University of Minnesota, Twin Cities, September, 2009.

2008

Learning High Precision Rules to Make Predictions of Morbidities in Discharge Summaries (Pedersen) - Appears in the Proceedings of the Second i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, Nov 7-8, 2008, Washington, DC.

2007

Using UMLS Concept Unique Identifiers (CUIs) for Word Sense Disambiguation in the Biomedical Domain (McInnes, Pedersen, and Carlis) - Appears in the Proceedings of the Annual Symposium of the American Medical Informatics Association, Nov 10-14, 2007, pp. 533-537, Chicago, IL. [acceptance rate 45%]
Measures of Semantic Similarity and Relatedness in the Biomedical Domain (Pedersen, Pakhomov, Patwardhan, and Chute), Journal of Biomedical Informatics, 40(3), 288-299, June 2007. [Journal Citation Reports Index Factor 2006: 2.346]
Determining the Syntactic Structure of Medical Terms in Clinical Notes (McInnes, Pedersen, and Pakhomov) - Appears in the Proceedings of BioNLP 2007, June 29, 2007, pp. 9-16, Prague, Czech Republic. [acceptance rate 29%] [ppt]

2006

Determining Smoker Status using Supervised and Unsupervised Learning with Lexical Features (Pedersen) - Appears in the Working Notes of the i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, Nov 10-11, 2006, Washington, DC.
A Comparative Study of Supervised Learning as Applied to Acronym Expansion in Clinical Reports (Joshi, Pakhomov, Pedersen, and Chute) - Appears in the Proceedings of the Annual Symposium of the American Medical Informatics Association, pp. 399-403, Nov 11-16, 2006, Washington, DC. [acceptance rate 41%] [ppt]
An End-to-End Supervised Target-Word Sense Disambiguation System (Joshi, Pakhomov, Pedersen, Maclin, and Chute) - Appears in the Proceedings of the Twenty-First National Conference on Artificial Intelligence, pp. 1941-1942, July 19, 2006, Boston, MA. (Intelligent System Demonstration)

2005

A Comparative Study of Support Vector Machines Applied to the Supervised Word Sense Disambiguation Problem in the Medical Domain (Joshi, Pedersen, and Maclin) - Appears in the Proceedings of the Second Indian International Conference on Artificial Intelligence, pp. 3449-3468, December 20-22, 2005, Pune, India. [acceptance rate 35%]
Abbreviation and Acronym Disambiguation in Clinical Discourse (Pakhomov, Pedersen and Chute) - Appears in the Proceedings of the Annual Symposium of the American Medical Informatics Association, pp. 589-593, October 22-26, 2005, Washington, DC. [acceptance rate 37%]
Resolving Ambiguities in Biomedical Text with Unsupervised Clustering Approaches (Savova, Pedersen, Purandare and Kulkarni) - University of Minnesota Supercomputing Institute Research Report UMSI 2005/80 and CB Number 2005/21, May.
Measures of Semantic Similarity and Relatedness in the Medical Domain (Pedersen, Pakhomov, and Patawardhan) - University of Minnesota Digital Technology Center Research Report DTC 2005/12, May. [This is a preliminary version of the JBI 2007 article].

2004

Incorporating Ngram Statistics in the Normalization of Clinical Notes (McInnes, Pakhomov, Pedersen and Chute) - Appears in MEDINFO 2004 : Proceedings of the 11th World Congress on Medical Informatics, p. 1882, September 2004, San Francisco, CA. (Poster)

By: Ted Pedersen - tpederse AT d umn edu