In a new study, researchers have developed a test using artificial intelligence (AI) tools that may more accurately find which people with pancreatic cysts will develop pancreatic cancers.
The research was done by an international scientific team led by Johns Hopkins Kimmel Cancer Center researchers.
Pancreatic cysts are common. They are found in 4% of people in their 60s and 8% of people over age 70, according to previously published research.
That means some 800,000 people with a pancreatic cyst are identified each year in the U.S. alone. By contrast, only a small fraction of cysts progress to cancer.
The newly developed test is called dubbed CompCyst (for comprehensive cyst analysis).
It incorporates measures of molecular and clinical markers in cyst fluids and may strongly improve conventional clinical and imaging tests.
In the new study, the team used information from more than 800 patients with pancreatic cysts who had cyst fluid analysis and cyst removal surgery.
The found the new test more often than standard current methods correctly identified which patients needed and may have a chance to benefit from surgery, and which were unlikely to benefit from surgery or needed further monitoring only.
Moreover, the team found the test would have spared from surgery more than half of the patients who underwent cyst removal later deemed unnecessary because the cysts were unlikely to have caused cancer.
The findings show that CompCyst can be a complement to existing clinical and imaging criteria when evaluating pancreatic cysts.
It could provide a greater degree of confidence for doctors when they advise patients that they do not require follow-up and can be discharged from surveillance.
This can be a more objective way to manage many patients with this disease.
Future work will validate the test. The team hopes over the next five years, doctors could use CompCyst in many more patients with cysts in an effort to guide surgical treatment.
One author of the study is Anne Marie Lennon, M.B.B.Ch., Ph.D., professor of medicine.
The study is published in Science Translational Medicine.
Copyright © 2019 Knowridge Science Report. All rights reserved.
