An AI-powered machine learning tool may allow physicians to better identify origins in enigmatic cancers, according to researchers at the Massachusetts Institute of Technology in Cambridge, Mass., and Dana-Farber Cancer Institute in Boston.
The model can analyze a sequence of around 400 genes and then use that information to make a focused prediction about where a tumor originated in the body, according to an Aug. 7 news release.
Not being able to identify the origin of a tumor can limit the treatment options a patient is given, but in its testing, the AI tool, dubbed 'OncoNPC' showed positive results and "enabled a 2.2-fold increase in patients with [a cancer of unknown primary] who could have received genomically guided therapies," researchers wrote of their findings, which were published Aug. 7 in Nature Medicine.
"A sizeable number of individuals develop these cancers of unknown primary every year, and because most therapies are approved in a site-specific way, where you have to know the primary site to deploy them, they have very limited treatment options," Alexander Gusev, PhD, senior author of the study and associate professor of medicine at Harvard Medical School and Dana-Farber Cancer Institute stated.
OncoNPC could offer clinicians support with managing patients who experience these types of cancers, the researchers claim.