Researchers have created an artificial intelligence model they say can accurately predict a person's lifespan, the Boston Globe reported.
A computer scientist at Boston-based Northeastern University joined researchers from Denmark in developing the Life2vec system that uses a large language model to scan massive amounts of people's data to identify patterns, including when they are likely to die, according to the Dec. 31 story. The study was published Dec. 18 in Nature Computational Science.
The tool predicted which of 100,000 Danish citizens between the ages of 35 and 65 had lived and died with 78% accuracy, according to the story. "We now live in an era where we can look at all the data all at once," co-author Tina Eliassi-Rad, PhD, a computer science professor at Northeastern, told the newspaper. "It means you can pay attention and learn correlations between every piece of data we have."
While the tool is "strictly in the lab for now," the researchers say it could one day be used in the U.S. to figure out the best health behaviors for Americans based on their demographics, personalities and social activities, the Globe reported.