Modelling the Influence of Covariates of Typhoid Patients at the Tamale Teaching Hospital Using Generalised Linear Models

Abstract

Typhoid fever and typhoid perforation has become a major burden and causes a lot of deaths in the world especially in developing countries. This study considered a total of 418 patients diagnosed of Typhoid fever at the Tamale Teaching Hospital covering the period January 2010 to June 2015. The data was modelled using the Negative binomial regression model to ascertain the duration (days) of admission cases as well as the effect of some covariates. Preliminary analysis revealed children of school going age as the most vulnerable. Further, collinearity diagnostics did not exhibit interaction among the predictors. The results identified cost of treatment, location of patients and outcome of admission as significant contributing covariates. Based on the results, it was recommended that policy makers should take keen interest on the cost of treatment of typhoid since rising cost of treatment is likely to increase the number of days spent in the hospital thereby putting pressure on hospital facilities.