A Review of Epidemic Forecasting Using Artificial Neural Networks

Background and aims: Since accurate forecasts help inform decisions for preventive health-careintervention and epidemic control, this goal can only be achieved by making use of appropriatetechniques and methodologies. As much as forecast precision is important, methods and modelselection procedures are critical to forecast precision. This study aimed at providing an overview ofthe selection of the right artificial neural network (ANN) methodology for the epidemic forecasts. It isnecessary for forecasters to apply the right tools for the epidemic forecasts with high precision.Methods: It involved sampling and survey of epidemic forecasts based on ANN. A comparison ofperformance using ANN forecast and other methods was reviewed. Hybrids of a neural network withother classical methods or meta-heuristics that improved performance of epidemic forecasts wereanalysed.Results: Implementing hybrid ANN using data transformation techniques based on improvedalgorithms, combining forecast models, and using technological platforms enhance the learning andgeneralization of ANN in forecasting epidemics.Conclusion: The selection of forecasting tool is critical to the precision of epidemic forecast; hence, aworking guide for the choice of appropriate tools will help reduce inconsistency and imprecision inforecasting epidemic size in populations. ANN hybrids that combined other algorithms and models,data transformation and technology should be used for an epidemic forecast.