The number of COVID-19 cases is gradually rising again in India. Amid this, scientists at the Massachusetts Institute of Technology (MIT) in the US have developed an AI model capable of predicting which SARS-CoV-2 variants can cause new waves of infection. One of the significant implementations of Artificial Intelligence is in the medical field, and current models that can foresee viral transmission do not predict the variant-specific spread of infection.  

A team led by Retsef Levi from MIT’s Sloan School of Management studied the elements that can cause the viral spread based on an analysis of 9 million SARS-CoV-2 genetic sequences. The Global Initiative collected such sequences on Sharing Avian Influenza Data (GISAID) from 30 countries. The data also involves vaccination rates and infection rates. 

As per the findings published in the journal PNAS Nexus, the team utilised the patterns formed from this analysis to develop a machine-learning-enabled risk assessment model. This is asserted to spot 72.8% of the variants in each country that will cause a minimum of 1000 cases per million people in the next three months.  

The researchers said, “This work provides an analytics framework that leverages multiple data sources, including genetic sequences data and epidemiological data via machine-learning models to provide improved early signals on the spread risk of new SARS-CoV-2 variants”.  

While the 72.8% predictive accuracy is obtained after an observation period of one week after detection, the performance increases to 80.1% after two weeks of observation.  

Scientists have planned for more research in this direction and said that the same kind of approach could potentially be extended to other respiratory viruses like influenza, avian flu viruses or other coronaviruses.