Exploration of artificial neural network and support vector regression for malaria incidence prediction in amhara region, ethiopia

Malaria is one of the major public health problems in Ethiopia. Early prediction of a Malaria incidence is the key for control of malaria morbidity, mortality as well as reducing the risk of transmission of malaria in the community and can help policymakers, health providers, medical officers, ministry of health and other health organizations to better target medical resources to areas of greatest need. In this study, the use of Artificial Neural Networks (ANNs) and Support Vector Regression (SVR) are explored to build malaria incidence prediction models for Amahara Region using a dataset collected from 2013 to 2017. The input parameters used are elevation, monthly rainfall, monthly average temperature, monthly average humidity and number of one month lag positive malaria cases. The developed models performance evaluated and compared based on Root Mean Square Error (RMSE), mean square error (MSE), mean absolute error (MAE) and regression coefficient(R). The results indicate that the proposed SVR model provides more accurate prediction compared to the ANN model.