The dangers of population-level mycotoxin exposure have been well documented. Climate-sensitive aflatoxins (AFs) are important food hazards. The continual effects of climate change are projected to impact primary agricultural systems, and consequently food security. This will be due to a reduction in yield with a negative influence on food safety. The African climate and subsistence farming techniques favour the growth of AF-producing fungal genera particularly in maize, which is a food staple commonly associated with mycotoxin contamination. Predictive models are useful tools in the management of mycotoxin risk. Mycotoxin climate risk predictive models have been successfully developed in Australia, the USA, and Europe, but are still in their infancy in Africa. This review aims to investigate whether AFs' occurrence in African maize can be effectively mitigated in the face of increasing climate change and food insecurity using climate risk predictive studies. A systematic search is conducted using Google Scholar. The complexities associated with the development of these prediction models vary from statistical tools such as simple regression equations to complex systems such as artificial intelligence models. Africa's inability to simulate a climate mycotoxin risk model in the past has been attributed to insufficient climate or AF contamination data. Recently, however, advancement in technologies including artificial intelligence modelling has bridged this gap, as climate risk scenarios can now be correctly predicted from missing and unbalanced data.
Keywords: aflatoxin; climate change; food insecurity; maize; predictive model; regulation.