Mixture Cure Rate Modelling for Cancer Survival Data A Comparative Study (original) (raw)

2018

Abstract

Introduction: Heterogeneity is a common phenomenon in cancer survival. Cancer survival probability varies hugely with respect to the prognostic factors. When the patients have long- term survival and the studied population is a mixture of susceptible individuals, who may experience the event of interest, and non-susceptible individuals, who will never experience it and are heterogeneous, mixture cure rate model is the alternate method.Methods: For illustration, breast cancer patients registered during 2006 followed-up till 2014was considered, and further followed-up till 2016 was considered for validation. Kaplan-Meier (K-M) method, mixture distribution (MD) models and mixture cure rate (MCR) models were used for estimating the probabilities. Anderson-Darling Statistics, Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and Kullback-Leibler survival (KLS) divergence were used for model identification.Results: The mixing proportion was estimated as 0.52 for the...

Preethi George hasn't uploaded this paper.

Let Preethi know you want this paper to be uploaded.

Ask for this paper to be uploaded.