An Intelligent Data Analytics Approach for Crisis Management in Healthcare Systems

Abstract

Crisis management is preparing for and managing possible crises that may impact organizations and individuals at different levels. It involves effective communication, quick decision-making, and strategic planning to minimize the negative impact of a crisis and ensure swift recovery. It plays a vital role in healthcare systems, especially in virus outbreaks. Its role is to monitor and manage the spread of viruses. Moreover, it can use Machine Learning (ML) techniques to achieve this goal. This paper discusses how to apply ML approaches to daily reports of infection cases. The adopted ML approaches are Auto Regressive Integrated Moving Average (ARIMA) model and the Long Short-Term Memory (LSTM) model. Furthermore, it uses Root Mean Square Error (RMSE) as a performance measure to evaluate the applied models. Simulation results show that ARIMA model performs better as compared to other models, which can provide a prediction accuracy of more than 99%.