A new AI tool has the potential to screen populations detecting those at high risk of pancreatic cancer three years before a typical diagnosis, according to a study published this month.
The research, led by teams from Harvard Medical School and the University of Copenhagen, used patients’ medical records to pinpoint those at the highest risk. The AI algorithm then looked for ‘telltale signs’ across two data sets of nine million patient records from Denmark and the United States successfully identifying patterns in those who did go on to develop pancreatic cancer.
“AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest,” said study co-senior investigator Søren Brunak, professor of disease systems biology and director of research at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen.
If applied at scale, study co-senior investigator Chris Sander, a faculty member in the Department of Systems Biology in the Blavatnik Institute at HMS, said it would make early treatment possible and increase the chances of extending patients’ life spans.
“An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making,” added Sander.
The research was published in Nature Medicine.