论文信息 - The Mayo/MITRE System for Discovery of Obesity and Its Comorbidities

The Mayo/MITRE System for Discovery of Obesity and Its Comorbidities

This paper describes the joint Mayo/MITRE system entries for the 2008 i2b2 community evaluation "Challenges in Natural Language Processing for Clinical Data" for the task of identifying obesity and its comorbidities from patient records. Our best systems result in macro-averaged F of 0.7377 and 0.6202 for the textual and intuitive labels respectively. The methods employed are a combination of machine learning and rule-based techniques.

[1] Wendy W. Chapman,et al. Evaluation of negation phrases in narrative clinical reports , 2001, AMIA.

[2] Corinna Cortes,et al. Support-Vector Networks , 1995, Machine Learning.

[3] Iryna Gurevych,et al. Towards Enhanced Interoperability for Large HLT Systems : UIMA for NLP , 2008 .

[4] John F. Hurdle,et al. Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research , 2008, Yearbook of Medical Informatics.