A proof-of-concept study led by Johns Hopkins Kimmel Cancer Center in the US has found CompCyst, an artificial intelligence (AI)-based laboratory test, could accurately identify pancreatic cysts that will develop into cancers.
CompCyst builds on patient data including clinical impressions and symptoms, CT images, and molecular markers such as DNA alterations in cyst fluid.
Go deeper with GlobalData
During the study, the research team used data from more than 800 patients with pancreatic cysts.
It was observed that the AI-based test correctly differentiated more patients who may or may not benefit from surgery or require further monitoring than existing standard clinical and imaging approaches.
The researchers added that the new test would have avoided cyst removal in more than 50% of patients, where the surgery was later considered unnecessary as the cysts were unlikely to have developed into cancer.
Johns Hopkins multidisciplinary pancreatic cyst clinic director Anne Marie Lennon said: “Our study demonstrates the potential role of CompCyst as a complement to existing clinical and imaging criteria when evaluating pancreatic cysts.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalData“It could provide a greater degree of confidence for physicians when they advise patients that they do not require follow-up and can be discharged from surveillance.”
The team performed histopathological analysis of resected surgical specimens to determine the exact nature of the cysts.
They assessed molecular profiles of 862 pancreatic cysts and fed this information as well as clinical and radiologic data into a computer programme that used AI to classify patients based on the nature of their cysts.
The researchers noted that the study has several limitations, including extraction of cyst fluid at the time of surgery and assessment of cysts that are more atypical than those found in clinical practice.
They intend to further assess the AI-based test in a prospective validation study next year.
