Simplifying COVISimplifying COVID-19 Data Analytics for Efficient Pandemic Management: A Novel ApproachD-19 Data Analytics for Efficient Pandemic Management: A Novel Approach

Abstract

This study presents a streamlined approach to pandemic management by simplifying COVID-19 data analytics. It focuses on the significant role of mobility patterns in forecasting case trajectories. Utilizing open mobility data from Google and Apple, a novel predictive model is proposed that aids health authorities in scenario projection and case monitoring. This model facilitates informed decision-making with minimal economic impact during future outbreaks. Key findings highlight the profound link between mobility changes and COVID-19 case trends, emphasizing the necessity of integrating mobility data into predictive models. The model, employing linear and polynomial regression analyses and incorporating the basic reproduction number, R0, forecasts can be extended up to 90 days. The study acknowledges limitations, particularly the reliance on mobility data that does not fully encompass all variables affecting virus transmission. Moreover, it explores the mental health implications of mobility restrictions, suggesting a broader impact of pandemic management strategies. The proposed model is a practical tool for managing pandemics through mobility data analysis, underscoring the need for comprehensive studies on the wider effects of mobility changes to guide public health policies