| Literature DB >> 31316009 |
Simeon Springer1,2, David L Masica2,3,4, Marco Dal Molin2,5, Christopher Douville1,2,3,4, Christopher J Thoburn1,2, Bahman Afsari2,6, Lu Li1,2, Joshua D Cohen1,2,3, Elizabeth Thompson2,5, Peter J Allen7, David S Klimstra8, Mark A Schattner9, C Max Schmidt10, Michele Yip-Schneider10, Rachel E Simpson10, Carlos Fernandez-Del Castillo11, Mari Mino-Kenudson12, William Brugge13, Randall E Brand14, Aatur D Singhi15, Aldo Scarpa16,17, Rita Lawlor16,17, Roberto Salvia18, Giuseppe Zamboni19, Seung-Mo Hong20, Dae Wook Hwang21, Jin-Young Jang22, Wooil Kwon22, Niall Swan23, Justin Geoghegan24, Massimo Falconi25, Stefano Crippa25, Claudio Doglioni26, Jorge Paulino27, Richard D Schulick28, Barish H Edil28, Walter Park29, Shinichi Yachida30, Susumu Hijioka31, Jeanin van Hooft32, Jin He33, Matthew J Weiss33, Richard Burkhart33, Martin Makary33, Marcia I Canto34, Michael G Goggins2,5,6,34, Janine Ptak1,2, Lisa Dobbyn1,2, Joy Schaefer1,2, Natalie Sillman1,2, Maria Popoli1,2, Alison P Klein1,2,6, Cristian Tomasetti35,36, Rachel Karchin3,4,6,35, Nickolas Papadopoulos1,2, Kenneth W Kinzler1,2, Bert Vogelstein37,2, Christopher L Wolfgang35,6,33, Ralph H Hruban2,5,6,37, Anne Marie Lennon37,2,6,33,34,38.
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 guide the 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.Entities:
Mesh：
Year: 2019 PMID： 31316009 PMCID： PMC7859881 DOI： 10.1126/scitranslmed.aav4772
Source DB: PubMed Journal: Sci Transl Med ISSN： 1946-6234 Impact factor: 17.956