Judith Leo

All contact details

Adaptive Reference Predictive Model: A Case of Tracking Environmental Determinants and Waterborne Epidemics Linkages

The role of environmental factors and population dynamics as determinants of epidemics has become an area of increasing interest. The interest has been stimulated by the growing number of problems in antibiotic resistance among pathogens and re-emergence of epidemic diseases in the world, having their origin from environmental causes. In additional to that according to the global health observatory data, it was reported by World Health Organization (WHO) in 2015 that the global burden of waterborne epidemic diseases from environmental factors are expected to increase substantially overtime with the increase of epidemic size.

In line with this research study, there are several mathematical models that have postulated and quantified the role of environmental and human activities factors in tracking, controlling and preventing waterborne epidemics.  Mathematical models are believed to be the most powerful tools in developing the mechanistic understanding of infectious diseases and furthermore, they can provide detailed prediction of epidemiological phenomena, such as the size of the outbreak which is a considerable public health significance. However, there is still limited knowledge on integration of all essential environmental factors at once in the mathematical model. In additional to that, if large numbers of datasets are integrated at once then the computation complexity of the mathematical model becomes significantly high. Therefore, taking advantages of the computational strength and adaptability features of machine learning techniques, this research will be carried out to facilitate the development of adaptive predictive models’ necessary for tracking environmental datasets which are linked to the cause of waterborne epidemics with a focus of reducing computational complexity.

Contact details:

The Nelson Mandela African Institution of Science and Technology (NM-AIST)
P.O. Box 447 Arusha, Tanzania