One of the implementations of AI technology is in the medical field and current models that can predict viral transmission do not predict variant-specific spread of infection.
How scientists developed this AI model
Led by Retsef Levi from MIT’s Sloan School of Management, a team studied the factors that could shape the viral spread based on an analysis of 9 million SARS-CoV-2 genetic sequences. These sequences were collected by the Global Initiative on Sharing Avian Influenza Data (GISAID) from 30 countries. The data also includes vaccination rates and infection rates.
According to the findings published in the journal PNAS Nexus, the team used the patterns that emerged from this analysis to build a machine learning-enabled risk assessment model. This is claimed to detect 72.8% of the variants in each country that will cause at least 1,000 cases per million people in the next three months.
“This work provides an analytical framework that leverages multiple data sources, including genetic sequence data and epidemiological data via machine-learning models to provide improved early signals on the spread risk of new SARS-CoV-2 variants,” the researchers said.
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 called for more research in this direction and said that a similar approach can potentially be extended to other respiratory viruses such as influenza, avian flu viruses, or other coronaviruses.