Application of Data Mining to Identify Patterns in VCT Dataset

Voluntary Counseling and Testing (VCT) is an important intervention and entry point in the prevention, control and management of the human immunodeficiency virus (HIV. But, the documentation process of VCT logbooks and dataset has given little attention on the identification of the VCT user's patterns and the outcome of the test results in Ethiopia. So, assessment of patterns in VCT outcomes using classification and association techniques of data mining is important for proper intervention. Based on the result of this study, physical status, reason to test, marital status, history of STIs,age and sex of the VCT clients are the optimal classifiers of HIV test result. From the association rules, females are more exposed for HIV infection and there is high HIV prevalence in 25-29 years age groups. Sothat data mining can apply to identify interesting patterns that help HIV and AIDS prevention and affected people care and support program. Thus, HIV care and support as well as prevention activities shall focus on attributes that are optimal and have high support and confidence with positive result and prevention activities shall focus on attributes associated with negative test results.

Autorentext

Kinfe Wubetu is Public Health (PH) Professional and has enormous practical experience on the field in various INGOs. Currently he is working in Save the Children in Ethiopia as Regional Coordinator for HIV/AIDS and Child Protection. His formal education includes B.Sc in PH from Debub University and MPH-Health Informatics from University of Gondar.