Survival Analysis and Stochastic Modelling on HIV/AIDS Data

This book has been aimed to apply the cox proportional hazard model to assess the determinant factors of survival time and discrete time homogeneous semi markov model to predict the clinical progression of AIDS disease using secondary data obtained from the antiretroviral therapy unit of Jimma University Specialized Hospital. The data were extracted from standard patient medical registration. A retrospective study was undertaken on a sample of 456 HIV/AIDS patients. Patients were followed for a median of 34 months. Of total sample, 312 (68.4%) were female and 144 (31.6%) were male. In the followed up period, 66 (14.5%) patients died and 390 (85.5%) patients were censored. The cox regression result indicated that the survival time of the HIV patient was significantly related with adherence level, age, alcohol use, CD4, condom use, functional status, marital status and WHO stage. The results of homogenous semi-markov model showed that the survival probability of a patient increased when CD4 count increased.