International Journal of Academic and Applied Research (IJAAR)   Year: 2021 | Volume: 5 | Issue: 12 | Page No.: 19-30 Relation between Accelerated Failure Time Models for Analyzing Hemodialysis Patients and Patient-Related Factors Reem Yousif Mekki,,Mohamed Hassan Mudawi, Manahil Saidahmed Mustafa , Altaiyb Omer Ahmed Mohmmed , A. A. Abdel Rahman. Abstract: The accelerated failure time (AFT) model is a parametric survival model that can replace Proportional Hazards (PH) models. The AFT model has a major advantage in that it does not require the PH assumption. Recently in Sudan the end-stage renal disease (ESRD) has become a major health problem, hence the aim of this study was to compare different parametric (AFT) models, such as (Weibull, Exponential, log logistic, and lognormal), in hemodialysis patients to determine the best model for evaluating the variables associated with patient survival.325 hemodialysis patients were treated at public hospitals in Khartoum State during the period from December 2005 to December 2010.The data in this study was used to forecast survival function in order to classify hemodialysis patients based on patient-related factors influencing end-stage renal disease (ESRD). The Weibull model, which is based on Cox-Snell Residuals and the Bayesian Information Criterion (BIC), is useful among others models. Furthermore, both Diabetes mellitus and hypertension, normal, dialysis frequency per week, and hospitals were found to have a significant impact on survival (P<0.05) in accelerated failure time models. The Weibull model was found to have the smallest BIC (711.09) values in multivariate analysis, so it was chosen as the best model for hemodialysis patients.