Modeling Time-to-Death and Its Determinants among HIV/AIDS Patients

Although remarkable decrease in the number of HIV related morbidity and mortality was recorded since the start of ART, exploring the effects of different socio-economic, demographic, and health factors determining survival of patients plays principal role. Despite the inconsistencies, previous studies revealed such determinants. However, plausible outcome can be obtained only if appropriate method of statistical analysis is used. For time-to-event, particularly time-to-death data, survival analysis is most appropriate method in which the Cox PH model is often used, although the AFT metric provides precise estimates provided that, distributional assumption is satisfied. Hence, the performances of Cox PH model and different parametric Models in both metric (PH and AFT) were compared to identify significant determinants of survival on 3042 eligible subjects followed for at least six years using secondary data obtained from University of Gondar Hospital, ART database. Model specific step-wise variable selection procedures were performed on 11 Covariates that appeared to be significant by Non-Parametric and independent analysis.

Autorentext

Yesuf Abdela (author) got his MSc in Biostatistics from University of Gondar. Dr. Salie Ayalew (co-author) is Assistant Professor of Statistics at University of Gondar and General Manager of Amhara Metal Industry and Machine Technology Development Enterprise, Ethiopia. He has written nine papers in reputable journals as well as reports.