The Mayo/MITRE System for Discovery of Obesity and Its Comorbidities
Guergana Savova, Cheryl Clark, Jiaping Zheng, Kevin Bretonnel Cohen, Ben Wellner, David P. Harris, Marcia Lazo, John S. Aberdeen, Qian Hu, Christopher G. Chute, Lynette Hirschman · 2008
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.