Date of Graduation
Statler College of Engineering and Mineral Resources
Lane Department of Computer Science and Electrical Engineering
The purpose of this document is building a framework for working with clinical data. Vast amounts of clinical records, stored in health repositories, contain information that can be used to improve the quality of health care. However, the information generated from these records depends vastly on the manner, in which the data is arranged. A number of factors need to be considered, before information can be extracted from the patient records. This document deals with the preparation of a framework for the data, before it can be mined.;One of the issues to deal with is information about the patient contained in the clinical records that can be used for identification purposes. A means to create anonymous records is discussed in this document. Once the records have been de-identified, they can be used for data mining. In addition to storing patient records, the document also discusses the possibility of 'abstracting' information from these documents and storing them in the repository. Information generated from the combination of patient records and abstracted information, could be used to improve the quality of health care.;This document also discusses the possibility of creating a means to query information from the data repository. A prototype application, which provides all these facilities in a form that can be accessed from any remote location, is discussed. In addition, the prospect of using Clinical Document Architecture format to store the clinical records is explored.
Payyappillil, Hemambika, "Data mining framework" (2005). Graduate Theses, Dissertations, and Problem Reports. 4184.