April 12, 2023 -- Doctors are using artificial intelligence to step up the war against lung cancer.
A new AI tool named Sybil can spot early signs of the disease years before doctors would find it traditionally on a CT scan, say researchers at Boston’s Mass General Cancer Canter and the Massachusetts Institute of Technology in Cambridge.
Sybil accurately predicted lung cancer within a year 86% to 94% of the time in one of their studies.
Lung cancer is the third most common cancer in the country, the CDC says. It’s the leading cause of cancer deaths, with more than 127,000 a year, says the American Cancer Society.
Now, researchers say Sybil can analyze a CT image for abnormal growths or dangerous patterns, the researcher said. Results were published in the Journal of Clinical Oncology.
“The naked eye cannot see everything,” said Lecia Sequist, MD, the program director of the Cancer Early Detection and Diagnostics Clinic at Massachusetts General Hospital on NBC.com. “The AI that we developed is looking at the scan in a completely different way than a human radiologist looks at it.”
Low-dose chest computed tomography (LDCT) has lowered death from lung cancer up to 24%. But often, lung cancer isn’t spotted until it has progressed too far.
“Lung cancer rates continue to rise among people who have never smoked or who haven’t smoked in years, suggesting that there are many risk factors contributing to lung cancer risk, some of which are currently unknown,” Sequist said in a Massachusetts General Hospital press release.
“Instead of assessing individual environmental or genetic risk factors, we’ve developed a tool that can use images to look at collective biology and make predictions about cancer risk.”
The U.S. Preventive Service Task Force recommends annual LDCTs for some long-term smokers over 50 or those who have quit within 15 years, the hospital says. But less than 10 percent of eligible patients are screened annually.