Addis Ababa University Libraries Electronic Thesis and Dissertations: AAU-ETD! >
School of Information Science and Computer Science >
Thesis - Health Informatics >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/3539

Advisors: Dr. Million Meshesha
Keywords: health informatics
Copyright: Jun-2011
Date Added: 31-Jul-2012
Publisher: AAU
Abstract: AIDS is the disease caused by HIV, which weakens the body’s immune system until it can no longer fight off the simple infections that most healthy people’s immune system can resist. HIV/AIDS continues to be a major global health priority. Knowledge about HIV status helps both individual and community. In spite of the widely and freely available VCT centers in Addis Ababa, the benefits of knowledge of HIV status for both individuals and communities; most people often do not know their HIV status. One of the solutions for this problem is to predict the HIV status of the population using data mining techniques so as to find out the burden of the disease on the subsets of the population and prepare intervention programs. The purpose of this thesis is HIV status predictive modeling to support the scaling up of HIV testing in Addis Ababa. The CRISP-DM methodology is followed for HIV status predictive modeling and discovering association rules between HIV status and selected attributes. J48 and ID3 algorithms are experimented to build and evaluate the models. Apriori algorithm is used to discover association rules. SPSS version 16 and Microsoft excel are used for further preparation of the dataset and WEKA 3.6 is used as the data mining tool to implement the algorithms. Pruned J48 classifier that predicts HIV status with 81.8% accuracy is developed. Association rule mining has also revealed its potential in discovering the relationships of the selected attributes and HIV status
Description: A Thesis Submitted to the School of Graduate Studies of Addis Ababa University in Partial Fulfillment of the Requirements for the Degree of Master of Science in Health Informatics
URI: http://hdl.handle.net/123456789/3539
Appears in:Thesis - Health Informatics

Files in This Item:

File Description SizeFormat
ELIAS LEMUYE.pdf1.26 MBAdobe PDFView/Open

Items in the AAUL Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.


  Last updated: May 2010. Copyright © Addis Ababa University Libraries - Feedback