Predicting Malaria Outbreak Using Indigenous Knowledge and Fuzzy Cognitive Maps: A Case Study of Vhembe District in South Africa

Malaria, a vector-borne disease, remains a major public health problem in many countries, particularly in Sub-Saharan Africa, where health resources are limited. Early warning of malaria outbreaks is crucial for effective control and mitigation of the devastating impacts of malaria. Tapping into the vital role indigenous knowledge (IK) plays in combating infectious diseases and the success of an artificial intelligence technique called fuzzy cognitive map (FCM) in modelling infectious diseases, this paper aims to predict malaria outbreaks using IK and FCM. The concepts used to develop the FCM were the IK indicators participants in Vhembe in South Africa used to ṇpredict malaria outbreaks. These IK indicators were collected through unstructured interviews. The developed malaria outbreak prediction FCM model was used to conduct simulations and make predictions of malaria outbreaks. As an initial stride for constructing such a tool, this paper demonstrates how the artificial intelligence technique, FCM, can represent IK indicators and predict malaria outbreaks. This promotes the recognition of IK in the effort to control and mitigate malaria outbreaks. Modelling IK using artificial intelligence opens the opportunity to incorporate IK with modern prediction models to develop robust early warning systems based on multiple knowledge systems.