ARTICLE: A multimodality test to guide the management of patients with a pancreatic cyst

AUTHORS: Simeon Springer, David L. Masica, Marco Dal Molin, Christopher Douville, Christopher J. Thoburn, Bahman Afsari, Lu Li, Joshua D. Cohen, Elizabeth Thompson, Peter J. Allen, David S. Klimstra, Mark A. Schattner, C. Max Schmidt, Michele Yip-Schneider, Rachel E. Simpson, Carlos Fernandez-Del Castillo, Mari Mino-Kenudson, William Brugge, Randall E. Brand, Aatur D. Singhi, Aldo Scarpa, Rita Lawlor, Roberto Salvia, Giuseppe Zamboni, Seung-Mo Hong, Dae Wook Hwang, Jin-Young Jang, Wooil Kwon, Niall Swan, Justin Geoghegan, Massimo Falconi, Stefano Crippa, Claudio Doglioni, Jorge Paulino, Richard D. Schulick, Barish H. Edil, Walter Park, Shinichi Yachida, Susumu Hijioka, Jeanin van Hooft, Jin He, Matthew J. Weiss, Richard Burkhart, Martin Makary, Marcia I. Canto, Michael G. Goggins, Janine Ptak, Lisa Dobbyn, Joy Schaefer, Natalie Sillman, Maria Popoli, Alison P. Klein, Cristian Tomasetti, Rachel Karchin, Nickolas Papadopoulos, Kenneth W. Kinzler, Bert Vogelstein, Christopher L. Wolfgang, Ralph H. Hruban, and Anne Marie Lennon

JOURNAL: Sci Transl Med. 2019 Jul 17;11(501). pii: eaav4772. doi: 10.1126/scitranslmed.aav4772.

Abstract

Pancreatic cysts are common and often pose a management dilemma, because some cysts are precancerous, whereas others have little risk of developing into invasive cancers. We used supervised machine learning techniques to develop a comprehensive test, CompCyst, to guidethe management of patients with pancreatic cysts. The test is based on selected clinical features, imaging characteristics, and cyst fluid genetic and biochemical markers. Using data from 436 patients with pancreatic cysts, we trained CompCyst to classify patients as those who required surgery, those who should be routinely monitored, and those who did not require further surveillance. We then tested CompCyst in an independent cohort of 426 patients, with histopathology used as the gold standard. We found that clinical management informed by the CompCyst test was more accurate than the management dictated by conventional clinical and imaging criteria alone. Application of the CompCyst test would have spared surgery in more than half of the patients who underwent unnecessary resection of their cysts. CompCyst therefore has the potential to reduce the patient morbidity and economic costs associated with current standard-of-care pancreatic cyst management practices.

For a link to the full article, click here.

For a link to the abstract, click here.

Share This Post