I am using the patients' survival times in an open cohort study of cancer patients as a measure of the life expectancy .I would like to predict the patients' life expectancy considering other patients' covariates i.e. age and sex. I could not use COX-regression because it predicts the death rate rather than life expectancy .Moreover, I could not use linear regression because the survival time data is positively skewed. Does anyone know what the best fit model in this case considering survival time as the dependent variable