KEYNOTE SPEECH I AI and Machine Learning for Disease Incidence Modeling

Vector borne diseases have been a serious concern all over the world. Due to various factors, South Asian and South East Asian region have seen a surge in incidences of dengue, malaria, chicken guinea, encephalitis etc. Many of such diseases are having geographic significance and many times have been found to be seasonal. Earlier researches have indicated the influence of climatic factors over appearance of disease cases and outbreaks. This study investigated the influence of climate factors on the incidence of malaria in the in India. WEKA machine learning tool with two classifier techniques, Multi-Layer Perceptron (MLP) and J48 were used with three test options, 10-fold cross-validation, percentile split, and supplied test. A comparative analysis was carried out to ascertain the superior model amongst the techniques concerning the prediction accuracy of malaria in the context of varying climate. The results suggested J48 had exhibited better skill to MLP with the 10-fold cross-validation method had better performance over the percentile Spilt and supplied test options. J48 demonstrated less error (RMSE = 0.6), better kappa = 0.63, and higher accuracy = 0.71), suggesting it as most suitable model. Seasonal variation of temperature and humidity had better association with malaria incidents compared to rainfall and the performance was better during the monsoon and post-monsoon when the incidents are at the peak.