The Prediction of AIDS Survival: A Data Mining Approach

Dom R. M., Kareem S. A., Abidin B., Kamaruzaman A., Kajindran A.

2nd WSEAS International Conference on Multivariate Analysis and Its Application in Science and Engineering, İstanbul, Turkey, 30 May - 01 June 2009, pp.48-53 identifier

  • Publication Type: Conference Paper / Full Text
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.48-53
  • Istanbul Technical University Affiliated: No


Data mining methods which combine techniques from database research, statistics and artificial intelligence have been applied to many research disciplines including engineering, finance and medicine. The objective of this paper is to describe the feasibility of applying a predictive data mining technique to predict the survival of AIDS. An adaptive fuzzy repression technique, FuReA, was used to predict the length of survival of AIDS patients based on their CD4, CD8 and viral load counts. Predictive ability of FuReA was measured and compared with fuzzy neural network prediction models. We found that both FuReA and fuzzy neural network models were able to predict the survival of AIDS with an accuracy of 60% to 100% based on selected dependent variables. These provisionary results demonstrate the viability Of FuReA in predicting survival among AIDS patients.