COVID Predicting AI Model: Covid-19 is again back in India as the cases are rising gradually in the country. Taking note of the unpredictability of the COVID-19 pandemic, the US-based Massachusetts Institute of Technology (MIT) has introduced an AI model that can make effective predictions about which SARS-COV-2 variants have the possibility of mass infections.
The highlight of this AI model is that it can predict specific COVID-19 variants. The rest of the existing AI models can only predict viral transmissions, but they cannot predict variant-specific infections.
How this AI Model is Developed?
A team of scientists at MIT’s Sloan School of Management deeply researched the parameters that can become viral infections based on the analysis of 9 Million SARS-CoV-2 genetic sequences. The agency responsible for collecting these sequences was the Global Initiative on Sharing Avian Influenza Data which collected these from 30 different countries worldwide.
According to the PNAS Nexus journal findings, the scientists involved in the development of the AI model used the patterns that came out of this evaluation or analysis to build an ML-enabled risk assessment model resulting in the detection of around 72.8 per cent of the variants which have the possibility to cause infection to at least 100 people in the coming 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.
The researchers also suggested that the same process could be adopted to process could be adopted to predict other viral infections such as Avian flue viruses and others.
Keep watching our YouTube Channel ‘DNP INDIA’. Also, please subscribe and follow us on FACEBOOK, INSTAGRAM, and TWITTER