Machine learning platform guides pancreatic cyst management in patients

The two sets of charts compare the recommendations for managing patients with pancreatic cysts based on either CompCyst or standard-of-care pathology. This material relates to a paper that appeared in the Jul. 17, 2019, issue of Science Translational Medicine, published by AAAS. The paper, by S. Springer at Howard Hughes Medical Institute in Baltimore, MD; and colleagues was titled, 'A multimodality test to guide the management of patients with a pancreatic cyst.' Credit: S. Springer et al., Science Translational Medicine (2019) Usage Restrictions: Please cite the owner of the material when publishing. This material may be freely used by reporters as part of news coverage, with proper attribution. Non-reporters must contact Science for permission.

The new assay, called CompCyst, outperformed the current gold standard-of-care in an international, multicenter study of 875 patients. Crucially, the test would have avoided surgery in 60% of patients who underwent unnecessary surgical removal, suggesting its use could lead to fewer unneeded surgeries and lower health and economic costs.

Pancreatic cysts are fluid-filled lesions in the pancreas that are found in up to 8% of all people over the age of 70. Although most cysts are benign, some pancreatic cysts that produce mucin can transform into an aggressive form of pancreatic cancer.

What's more, it is difficult to distinguish precancerous cysts from benign ones, so noncancerous cysts are often misclassified and unnecessarily removed with pancreatic surgery.

To overcome this dilemma, Simeon Springer and colleagues enrolled 875 patients with pancreatic cysts and collected information of the mutations, proteins, and other markers linked to their either benign or mucin-producing cysts.

They used deep learning techniques to train CompCyst to read these markers and classify patients into those that should be monitored, not monitored, or receive surgery.

After training the test protocol with 436 of the original patients, the researchers found the test largely outperformed standard-of-care pathology when evaluated in 426 other patients: it correctly identified 60.4% of patients who should have been discharged (versus 18.9% using standard-of-care diagnosis), 48.6% of patients that should have been monitored (versus 34.3%), and 90.8% of patients in need of surgery (versus 88.8%).

Future work will be necessary to prospectively validate the markers used in the test, but Springer et al. say their platform has strong potential to be used in the clinic as a complement to existing approaches.

Media Contact

Science Press Package Team
scipak@aaas.org
202-326-6440

 @AAAS

http://www.aaas.org 

Media Contact

Science Press Package Team EurekAlert!

All news from this category: Health and Medicine

This subject area encompasses research and studies in the field of human medicine.

Among the wide-ranging list of topics covered here are anesthesiology, anatomy, surgery, human genetics, hygiene and environmental medicine, internal medicine, neurology, pharmacology, physiology, urology and dental medicine.

Back to the Homepage

Comments (0)

Write comment

Latest posts

Seawater as an electrical cable !?

Wireless power transfers in the ocean For drones that can be stationed underwater for the adoption of ICT in mariculture. Associate professor Masaya Tamura, Kousuke Murai (who has completed the…

Rare quadruple-helix DNA found in living human cells with glowing probes

New probes allow scientists to see four-stranded DNA interacting with molecules inside living human cells, unravelling its role in cellular processes. DNA usually forms the classic double helix shape of…

A rift in the retina may help repair the optic nerve

In experiments in mouse tissues and human cells, Johns Hopkins Medicine researchers say they have found that removing a membrane that lines the back of the eye may improve the…

Partners & Sponsors

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close