Application Of Data Mining For Effective Prognosis Of Hiv/Aids Testing
No Thumbnail Available
Date
2016-10-09
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
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. Knowing about HIV/AIDS help the individuals, communities, government and stakeholders to prevent and design the appropriate policy which leads to eradicate the disease.
Now days Healthcare and non-Healthcare industries are stored huge amounts of data about patients, hospital resources, disease diagnosis, electronic patient records, and medical devices. Huge amount of data are a key resource to be processed and analyzed for knowledge extraction that enables support for cost savings and decision making. The problem of effectively utilizing this huge amount of data is becoming a major problem for all health and to make effective decision. So in order to make effective and efficient decision on the data using data mining techniques is the best solution.
The main objective of this study was to design/develop an effective HIV/AIDS prognosis model by using data mining techniques.
The six steps hybrid methodology has been followed to develop the HIV testing prognosis model. Three classifications techniques such as Decision tree J48, Naivebayes and Neural network (MLP) algorithms were experimented for building and evaluating the models.
A total of 14,786 EDHS 2011 records have been used to develop the models. , the J48 pruned tree classifier algorithm with 10-fold cross validation test option performed best classification accuracy of 98.5121% with 98.51% sensitivity, where as Naive Bayes and Neural Network (MLP) classifier algorithms with 10-fold cross validation test option performed best classification specificity of 98.1% and 98.1% result respectively.
In general the results obtained from this research indicate that data mining is useful and appropriate tool in bringing relevant information for decision and policy makers. Hence, the organization should have to design a knowledge base system, which can provide advice for the domain experts is future research direction of the study.
Description
Keywords
Effective Prognosis Of Hiv/Aids Testing