Researchers at Berg, a Boston-based pharmaceutical startup, are using artificial intelligence and machine learning to develop predictive ways to fight the flu, Time reports.
To understand the biology behind effective immune responses to the flu, Berg and Sanofi are using an AI algorithm to analyze data from patient samples exposed to the vaccine.
By using AI and machine learning tools, researchers hope to gain a better understanding of immune responses to then develop more precise flu shots and even personalized flu prevention, Niven Narain, PhD, co-founder and CEO of Berg, told Time.
Flu vaccines are currently based on experts' predictions about which strains will be most pervasive in the upcoming flu season, but they're not always right.
"We really don't have a handle on exactly what type of response a new vaccine should be inducing to give us the best protection," Richard Webby, PhD, director of the World Health Organization Collaborating Centre for Studies on the Ecology of Influenza in Animals at St. Jude Children's Research Hospital in Memphis,Tenn., told Time.
Berg's partnership with Sanofi allows them to study a large number of patients and measure multiple immune response variables, Dr. Webby added.
New information about immune response has already been learned from other AI efforts, Jacco Boon, PhD, assistant professor of medicine specializing in influenza virology at Washington University in St. Louis, told Time. Researchers are using machine learning to predict the spread of influenza through the culmination of physician data, social media posts, Google searches and retail information. The CDC posts an aggregation of these predictions online to show flu prevalence and where it is likely to spread.