New Delhi, Jan, 06: Amid a fresh surge in coronavirus cases, the latest study has discovered that an artificial intelligence (AI) model can forecast which versions of the Covid-causing SARS-CoV-2 virus are likely to result in new waves of infection.
According to researchers from the Massachusetts Institute of Technology (MIT) in the US and The Hebrew University-Hadassah Medical School in Israel, the model is capable of detecting approximately 73% of the variants in each country that will cause at least 1,000 cases per 10 lakh people in the three months following a one-week observation period, and over 80% after two weeks.
The research team analyzed 9 million genetic sequences of SARS-CoV-2 across 30 countries, obtained from the Global Initiative on Sharing Avian Influenza Data (GISAID). This genetic data was combined with information on vaccination rates, infection rates, and other factors. GISAID is an initiative that promotes the rapid sharing of data related to priority pathogens, including influenza and the coronavirus.
Utilizing the patterns identified in their analysis, the researchers developed a risk assessment model based on machine learning, an AI algorithm capable of learning from past data and making predictions. The findings of their study have been published in the journal PNAS Nexus.
The study revealed that the most influential factors affecting a variant’s infectiousness include the early trajectory of the infections it causes, its spike mutations, and how different its mutations are from those of the most dominant variant during the observation period.
The researchers highlighted that current models predicting the dynamics and trends of viral transmission do not specifically predict the spread of variants. Their novel approach leverages variant-specific genetic data and epidemiological information to offer improved early signals and predict the future spread of newly detected variants.
Moreover, the researchers suggested that this modeling approach could potentially be extended to other respiratory viruses, such as influenza and avian flu viruses, or other coronaviruses, providing insights into the future course of various infectious diseases. They also emphasized the need for future research to explore how genetic and biological understanding of a variant’s infectiousness can be translated into predictive factors based on available data.(Agencies)
