Mapping Tuberculosis Incidence Using Mixture Distribution in Khuzestan Province, Iran



Gharibzadeh S¹ ; Gharibzadeh S¹ ; Alavi SM³ ; Chinipardaz R⁴ ; Ghafourian M⁵
Source: Research Journal of Pharmaceutical# Biological and Chemical Sciences Published:2016

Abstract

The allocation of resources in the health authority areas is based on a mapping of disease incidence and determination distribution of disease relative risk in small areas. Data on tuberculosis (TB) have been analyzed before, without giving sufficient attention to spatial variations. We aim to find high risk cities of Khuzestan province for TB with expanding a mixture of Poisson distributions for the number of cases and categorize the cities to one of the risk groups of TB. Mixture distributions of Poisson were used to find the number of risk groups, which might have produced by observed counts of TB patients in 23 cities of Khuzestan province. The Number of risk groups and Poisson parameters of each component were estimated with maximum likelihood approach using the computer package C.A.MAN (Computer Assisted Mixture Analysis). Bayesian methods were used to allocate each city to a particular risk group with a programme in R (3.0.0), the statistical software. The results were geographically presented in maps by using ArcGIS (9.3) software. Seven cities showed high risk with traditional method while in the mixture method, it was shown by 5. Our findings demonstrated the usefulness of the mixture models for modeling data with geographical variations.