A Review on Potentials of Artificial Intelligence Approaches to Forecasting COVID-19 Spreading
Abstract COVID-19 is by now one of the deadliest public health issues that as per the last announcement of the World Health Organization up to January 21, 2021, has infected more than 108,904,983 people and claimed more than 2,398,339 lives worldwide. Although different vaccines have proved and distributed one after another, several new mutated viruses have been detected, such as the new COVID-19 variant detected in the UK. Since new variants can spread so faster than the previous one and many other strains may come, it is necessary to focus on the effective methods that are able to predict the spreading trends quickly. Regarding the considerable progress in Artificial Intelligence (AI), utilizing AI-based techniques with a concentration on Deep Learning (DL) and Machine Learning (ML), which can forecast complex trends like epidemiological issues, are proposed to conquer the problems existing in statistical or conventional techniques. In this respect, the present paper reviews the recent peer-reviewed published articles and preprint reports about solutions that could efficiently address COVID-19 spread with a focus on the state-of-the-art and AI-based methods. The results revealed that methods under discussion in this paper have had significant potentials to predict epidemic diseases like COVID-19 as well as its mutations; however, there are still weaknesses and drawbacks that fall in the domain of future research and scientific endeavors.