Survival Analysis of Cholera Patients a Parametric and Non-parametric Approach

Abstract

Aims: The aim of this study is to investigate survival probability of cholera patients who were under follow-up and identify significant risk factors for mortality. Methodology: In this research, we present the basic concepts, nonparametric methods (the Kaplan-Meier method and the log-rank test) and parametric method. Parametric AFT models (Exponential, Weibull, Lognormal and Log logistic) were compared using Akaike’s Information Criterion (AIC). Results: Recorded data of 513 patients were obtained from UNICEF Cholera Hospital for Internally Displaced Persons Camps within Maiduguri, Borno State. Non-Parametric and Parametric approach were used to estimate the survival probability of the patients and examine the association between the survival times with different risk factors. The analysis shows that some factors significantly contribute to longer survival time of cholera patients. These factors include being a female, age less than twenty, being vaccinated before the infection and mild degree of dehydration. Conclusion: The vaccination, age, sex and degree of dehydration of a cholera patient affects its survival hence, much attention should be given to older patients, degree of dehydration and vaccine (killed oral 01 with whole-cell with Bsubunit) should be administered whenever there is outbreak. When carrying out survival analysis of this kind, a Weibull model is Recommended for used while if dealing with Accelerated Failure Time models.