The Cox regression and Kaplan-Meier for time-to-event of survival data patients with renal failure

Background: renal failure disease usually occurs when the blood supply to the kidneys is suddenly interrupted or when the kidneys become overloaded with toxins.
Objectives: in this article two main survival models were used, Cox regression and Kaplan-Meier to estimate the median patient survival time for conditions causing renal failure and to comparison of the survival rates of people with illnesses causing renal failure.
Methods: The research community is made up of individuals who have been diagnosed with renal failure, and the data were gathered from the patient records at the Police Hospital (Khartoum - Burri). All individuals with renal failure who were tracked down and given the diagnosis were included in the process of thorough inventory. The computations were done using some statistical Software (SPSS, STATA), with level of significance 0.05.
Results: some variables like other disease were causes RF ( diabetes, heart disease, osteoporosis, hepatitis, and growth retardation) associated with renal failure, Cox regression was used and the basic variables shown that 65.7% of the independent variables (duration of disease, housing, diabetes and hepatitis infection) determine the survival time of the estimated model.
Conclusions: Kaplan–Meier and Cox regression methods both are used in clinical and epidemiological research. The Cox regression analysis is based on estimating the HR associated with a specific risk factor or predictor for a given endpoint. The standard Cox regression method allows for an investigation of the effect of one or more variables (covariates) on the “time-to-first-event” analysis. An assessment of proportional hazards is a prerequisite to fitting a Cox regression model.