Yetisgen, MelihaRHINE, ADAM M.2017-05-162017-05-162017-03RHINE_washington_0250O_16818.pdfhttp://hdl.handle.net/1773/38649Thesis (Master's)--University of Washington, 2017-03Within the field of clinical support, access to relevant, peer-reviewed information from medical journals and other research publications is critical to making informed decisions regarding the diagnosis and care of patients. This study aims to build a complete biomedical information retrieval system, based on the data released by the National Institute of Standards and Technology for Text REtrieval Conference Clinical Decision Support track. Through the use of query expansion, machine-learning classification, a vector space model with tf-idf ranking implementation, along with additional specialized preprocessing data transformation and post-processing scoring techniques, we constructed an IR system competitive with the state of the art for this specific retrieval task, and demonstrated our success through the use of standardized evaluation metrics.application/pdfen-USCC BYCDSClinical Decision SupportClinical InformaticsInformation RetrievalNISTTRECLinguisticsBioinformaticsInformation scienceLinguisticsThesis