A groundbreaking study has revealed that an artificial intelligence (AI) model can accurately predict which variants of the SARS-CoV-2 virus will lead to fresh waves of Covid-19 infections. The researchers, from the Massachusetts Institute of Technology (MIT) and The Hebrew University-Hadassah Medical School, analyzed 9 million genetic sequences of the virus across 30 countries, combining this data with information on vaccination and infection rates.
Using machine learning, an AI algorithm that learns from past data, the team developed a risk assessment model. This model can detect approximately 73% of variants in each country that will cause at least 1,000 cases per 10 lakh people within three months. After two weeks, the model’s accuracy improves to over 80%.
The researchers identified several key factors that influence a variant’s infectiousness. These include the early trajectory of infections it causes, its spike mutations, and how different its mutations are from those of the dominant variant during the observation period. Variants that acquire enough mutations can either lead to reinfections or target new population subgroups, the study found.
Current models for viral transmission dynamics and trends do not account for variant-specific spread, according to the researchers. However, their novel approach integrates variant-specific genetic data and epidemiological information to provide early signals and predict the future spread of newly detected variants. Furthermore, the study suggests that this technology could be extended to other respiratory viruses, such as influenza and avian flu, as well as other infectious diseases.
While this research marks a significant step forward in understanding and predicting the course of the Covid-19 pandemic, the team emphasizes the need for further exploration. They suggest investigating how genetic and biological understanding of a variant’s infectiousness and spread can be translated into predictive factors. This information would allow for evaluation based on available data and potentially aid in developing strategies to combat future outbreaks of infectious diseases.
[Source: Devdiscourse]
The source of the article is from the blog crasel.tk