MIT's AI model identifies Covid-19 variant trends, know here

The Covid-19 situation in India is concerning, with the rise of the JN.1 variant which is pushing the cases day by day.

Amidst this, scientists from the Massachusetts Institute of Technology (MIT) in the US have created an AI model to predict which SARS-CoV-2 variants might lead to new waves of infection, as reported by Gadgets Now.

In the medical field, AI technology plays a crucial role. Current models predicting viral transmission so not account for the specific spread of different variants.

Here's How The MIT Team Developed This AI Model:

Led by Retsef Levi from MIT’s Sloan School of Management, they studied factors shaping viral spread by analysing 9M SARS-CoV-2 genetic sequences.

These sequences were gathered by the Global Initiative on Sharing Avian Influenza Data (GISAID) from 30 countries, including vaccination and infection rates.

According to their findings published in the journal PNAS Nexus, the team used patterns from this analysis to create a machine learning-enabled risk assessment model.

This model claims to detect 72.8% of variants in each country that will cause at least 1,000 cases per million people in the next three months, as per the report.

This work establishes an analytical framework that utilises various data sources, like genetic sequences and epidemiological data, through machine learning models to provide better early signals for the spread risk of new SARS-CoV-2 variants, as stated by the researchers.

Scientists are urging further research in this direction, suggesting that a similar approach could be applied to other respiratory viruses like influenza, avian flu, or other coronavirus, as per the report.