Application of Predictive Analytics for Early Warning System for Healthcare Management

Abstract

Coronavirus disease (COVID-19) has become a pandemic after its outbreak in January 2020. The majority of the countries have witnessed peak effects of the disease, and they need to learn from their past experience of dealing with and pro-actively controlling the future waves. Thus, this article aims to analyse the effect of the COVID-19 pandemic on some of the key states in India and provide analytical actionable insight for better epidemic management. In this article, we have focused on Maharashtra and tried to show how other states can also incorporate pro-active pandemic management to reduce the number of causalities in the following waves. The key objectives of this article are to provide a scenario base forecasted number of patients for Maharashtra with sufficient lead time, review the current capacity of the health infrastructure, analyse the risk of the current health infrastructure, identify the breaking point of system failure in advance, measure the gap between capacity (supply) vs demand and raise alarms and device an early warning system (EWS) pro-actively. Quantitative analysis of the statistics related to COVID-19 has been done based on their official (government) data and some of the previous research work. Prophet Model has been used to forecast and then the forecasted values are combined with the daily load in hospitals to measure the extra load on the healthcare system.