Expanding eVision’s Scope of Influenza Forecasting

Abstract

According to the United States Center for Disease Control and Prevention (CDC) between 39 and 56 million people in the United States experienced flu like symptoms in the 2019-20 flue season. From which, 410 to 740 thousand were hospitalized and 24 to 62 thousand (most of them children or elderly) succumbed to the disease. Hence, the presence of an early warning mechanism that can alert pharmaceuticals, hospitals, and governments to the trends of the influenza season, would serve as a significant step in helping combat communicable diseases and reduce the mortality of child under the age of five. Both of which are among the targets for the 3rd United Nations (UN) Sustainable Development Goal (SDG): to ensure healthy lives and promote well-being for all at all ages.As reported in the [ACM Special Interest Group in Computers and Society (SIGCAS) 2020 Computers and Sustainable Societies (COMPASS)] and [IEEE Technology and Engineering Management Society (TEMS) 2020 International Conference on Artificial Intelligence for Good (AI4G)] Long Short-Term Memory (LSTM) neural networks are utilized by Santa Clara University’s EPIC (Ethical, Pragmatic, and Intelligent Computing) and BioInnovation & Design laboratories for continued research and development of an eVision (Epidemic Vision) tool to predict the trend of influenza cases throughout the flu season. There we reported eVision’s success in making 3 to 7 weeks in advance predictions for the 2018-2019 United States flu season with 90.15% accuracy on 7 week predictions and delineated future steps of 1) expanding eVision’s scope to study the effects of augmenting predictions with concurrent data from neighboring, near by, and developmentally similar countries/states with similar environmental conditions and 2) the introduction of confidence intervals for the predictions in order to account for the average error and thus increase the trustworthiness of eVision’s results. This paper is to report that as a result of those steps, both the Californian and Chilean 7 week forecasts improved by 1.98% and 7.89% respectively.