A Covid-19 Epidemiological Analysis and Forecasting Dashboard for Hospitals using Time-Series Analysis and Deep Learning

COVID-19 is a disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that, to date, has over 774 million confirmed cases and claimed over 7 million lives. Forecasts are therefore essential as they aide in the necessary preparation of healthcare logistics. In this study, forecasting models such as ARIMA, RNN and LSTM were developed to predict Covid-19 time-series data relevant to hospitals, which were then evaluated and compared using MAE and RMSE. Across the different variables, LSTM had the least error. A web-based dashboard was also developed for forecasting these time-series variables for healthcare institutions, particularly those which are accommodating Covid-19 patients.