Forecasting the spread of COVID-19 based on policy, vaccination, and Omicron data.

Abstract

The COVID-19 pandemic caused by the novel SARS-COV-2 virus poses a great risk to the world. During the COVID-19 pandemic, observing and forecasting several important indicators of the epidemic (likenew confirmed cases, new cases in intensive care unit, andnew deaths for each day) helped prepare the appropriate response (e.g., creating additional intensive care unit beds, andimplementing strict interventions). Various predictive models and predictorvariables have been used to forecast these indicators. However, the impact of prediction models and predictorvariables on forecasting performance has not been systematically well analyzed. Here,we compared the forecasting performance using a linear mixed model in terms of prediction models (mathematical, statistical, andAI/machine learning models) and predictor variables (vaccination rate, stringency index, andOmicron variantrate) for seven selected countries with the highest vaccination rates. We decided on our best models based on the Bayesian Information Criterion (BIC) and analyzed the significance of each predictor. Simple models were preferred. The selection of the bestprediction models and the use of Omicron variantrate were considered essential in improving prediction accuracies. For the test dataperiod before Omicron variantemergence, the selection of the bestmodels was the most significant factor in improving prediction accuracy. For the test period after Omicron emergence, Omicron variantrate use was considered essential in deciding forecasting accuracy. For prediction models, ARIMA, lightGBM, and TSGLM generally performed well in both test periods. Linear mixed models with country as a random effect has proven that the choice of prediction models and the use of Omicron data was significant in determining forecasting accuracies for the highly vaccinated countries. Relatively simple models, fit with either prediction model or Omicron data, produced best results in enhancing forecasting accuracies with test data.