Due to the seemingly endless stream of publications and the tremendous amount of medical data collected. the development of advanced information extraction (IE) and information retrieval (IR) tools is becoming important to ensure continued access to meaningful information from an increasing amount of accumulated data. In this dissertation, IR. and IE are explored in three data domains: biomedical publications data, with a focus on figure search through the Yale Image Finder (YIF), an online biomedical figure discovery tool; clinical claims data, with a focus on finding similar patients using innovative similarity metrics: and linked data, with a focus on data representation and search. The first thesis contribution is a set of advanced YIF IR tools. including a new text region segmentation algorithm. the introduction of search by image type, and improved context-sensitive related figure retrieval. The second thesis contribution is the development of a novel Needleman-Wunsch-based alignment method that facilitates the retrieval of complex sequence-bused data by establishing trajectory similarity. Using the method, claims-based sequential patient data are compared, clustered, and used for the prediction of 30-day readmission after heart failure hospitalization. The third thesis contribution is the successful use of semantics to aid in biomedical information retrieval. Semantic search over VIF content is demonstrated using a new ontology that defines semantic relationships between figures and their data additionally, a schema for the generation of nanopublications is introduced as a means to convey basic scientific findings in an informal way.
|School Location:||United States -- Connecticut|
|Source:||DAI-B 78/11(E), Dissertation Abstracts International|
|Subjects:||Bioinformatics, Information science|
|Keywords:||Classification, Clustering, Information Extraction, Information Retrieval, Sequence Alignment, Yale Image Finder|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be