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

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. SinghiAldo 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, Anne Marie Lennon

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
Article numbereaav4772
JournalScience translational medicine
Volume11
Issue number501
DOIs
StatePublished - Jul 17 2019

Fingerprint

Pancreatic Cyst
Cysts
Cyst Fluid
Practice Management
Standard of Care
Genetic Markers
Biomarkers
Economics
Morbidity
Costs and Cost Analysis

ASJC Scopus subject areas

  • Medicine(all)

Cite this

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

In: Science translational medicine, Vol. 11, No. 501, eaav4772, 17.07.2019.

Research output: Contribution to journalArticle

Springer, S, Masica, DL, Molin, MD, Douville, C, Thoburn, CJ, Afsari, B, Li, L, Cohen, JD, Thompson, E, Allen, PJ, Klimstra, DS, Schattner, MA, Max Schmidt, C, Yip-Schneider, M, Simpson, RE, Castillo, CFD, Mino-Kenudson, M, Brugge, W, Brand, RE, Singhi, AD, Scarpa, A, Lawlor, R, Salvia, R, Zamboni, G, Hong, SM, Hwang, DW, Jang, JY, Kwon, W, Swan, N, Geoghegan, J, Falconi, M, Crippa, S, Doglioni, C, Paulino, J, Schulick, RD, Edil, BH, Park, W, Yachida, S, Hijioka, S, Van Hooft, J, He, J, Weiss, MJ, Burkhart, R, Makary, M, Canto, MI, Goggins, MG, Ptak, J, Dobbyn, L, Schaefer, J, Sillman, N, Popoli, M, Klein, AP, Tomasetti, C, Karchin, R, Papadopoulos, N, Kinzler, KW, Vogelstein, B, Wolfgang, CL, Hruban, RH & Lennon, AM 2019, 'A multimodality test to guide the management of patients with a pancreatic cyst', Science translational medicine, vol. 11, no. 501, eaav4772. https://doi.org/10.1126/scitranslmed.aav4772
Springer, Simeon ; Masica, David L. ; Molin, Marco Dal ; Douville, Christopher ; Thoburn, Christopher J. ; Afsari, Bahman ; Li, Lu ; Cohen, Joshua D. ; Thompson, Elizabeth ; Allen, Peter J. ; Klimstra, David S. ; Schattner, Mark A. ; Max Schmidt, C. ; Yip-Schneider, Michele ; Simpson, Rachel E. ; Castillo, Carlos Fernandez Del ; Mino-Kenudson, Mari ; Brugge, William ; Brand, Randall E. ; Singhi, Aatur D. ; Scarpa, Aldo ; Lawlor, Rita ; Salvia, Roberto ; Zamboni, Giuseppe ; Hong, Seung Mo ; Hwang, Dae Wook ; Jang, Jin Young ; Kwon, Wooil ; Swan, Niall ; Geoghegan, Justin ; Falconi, Massimo ; Crippa, Stefano ; Doglioni, Claudio ; Paulino, Jorge ; Schulick, Richard D. ; Edil, Barish H. ; Park, Walter ; Yachida, Shinichi ; Hijioka, Susumu ; Van Hooft, Jeanin ; He, Jin ; Weiss, Matthew J. ; Burkhart, Richard ; Makary, Martin ; Canto, Marcia I. ; Goggins, Michael G. ; Ptak, Janine ; Dobbyn, Lisa ; Schaefer, Joy ; Sillman, Natalie ; Popoli, Maria ; Klein, Alison P. ; Tomasetti, Cristian ; Karchin, Rachel ; Papadopoulos, Nickolas ; Kinzler, Kenneth W. ; Vogelstein, Bert ; Wolfgang, Christopher L. ; Hruban, Ralph H. ; Lennon, Anne Marie. / A multimodality test to guide the management of patients with a pancreatic cyst. In: Science translational medicine. 2019 ; Vol. 11, No. 501.
@article{ee77ec196ecb4d029fd84f9625f9d17e,
title = "A multimodality test to guide the management of patients with a pancreatic cyst",
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.",
author = "Simeon Springer and Masica, {David L.} and Molin, {Marco Dal} and Christopher Douville and Thoburn, {Christopher J.} and Bahman Afsari and Lu Li and Cohen, {Joshua D.} and Elizabeth Thompson and Allen, {Peter J.} and Klimstra, {David S.} and Schattner, {Mark A.} and {Max Schmidt}, C. and Michele Yip-Schneider and Simpson, {Rachel E.} and Castillo, {Carlos Fernandez Del} and Mari Mino-Kenudson and William Brugge and Brand, {Randall E.} and Singhi, {Aatur D.} and Aldo Scarpa and Rita Lawlor and Roberto Salvia and Giuseppe Zamboni and Hong, {Seung Mo} and Hwang, {Dae Wook} and Jang, {Jin Young} and Wooil Kwon and Niall Swan and Justin Geoghegan and Massimo Falconi and Stefano Crippa and Claudio Doglioni and Jorge Paulino and Schulick, {Richard D.} and Edil, {Barish H.} and Walter Park and Shinichi Yachida and Susumu Hijioka and {Van Hooft}, Jeanin and Jin He and Weiss, {Matthew J.} and Richard Burkhart and Martin Makary and Canto, {Marcia I.} and Goggins, {Michael G.} and Janine Ptak and Lisa Dobbyn and Joy Schaefer and Natalie Sillman and Maria Popoli and Klein, {Alison P.} and Cristian Tomasetti and Rachel Karchin and Nickolas Papadopoulos and Kinzler, {Kenneth W.} and Bert Vogelstein and Wolfgang, {Christopher L.} and Hruban, {Ralph H.} and Lennon, {Anne Marie}",
year = "2019",
month = "7",
day = "17",
doi = "10.1126/scitranslmed.aav4772",
language = "English (US)",
volume = "11",
journal = "Science Translational Medicine",
issn = "1946-6234",
publisher = "American Association for the Advancement of Science",
number = "501",

}

TY - JOUR

T1 - A multimodality test to guide the management of patients with a pancreatic cyst

AU - Springer, Simeon

AU - Masica, David L.

AU - Molin, Marco Dal

AU - Douville, Christopher

AU - Thoburn, Christopher J.

AU - Afsari, Bahman

AU - Li, Lu

AU - Cohen, Joshua D.

AU - Thompson, Elizabeth

AU - Allen, Peter J.

AU - Klimstra, David S.

AU - Schattner, Mark A.

AU - Max Schmidt, C.

AU - Yip-Schneider, Michele

AU - Simpson, Rachel E.

AU - Castillo, Carlos Fernandez Del

AU - Mino-Kenudson, Mari

AU - Brugge, William

AU - Brand, Randall E.

AU - Singhi, Aatur D.

AU - Scarpa, Aldo

AU - Lawlor, Rita

AU - Salvia, Roberto

AU - Zamboni, Giuseppe

AU - Hong, Seung Mo

AU - Hwang, Dae Wook

AU - Jang, Jin Young

AU - Kwon, Wooil

AU - Swan, Niall

AU - Geoghegan, Justin

AU - Falconi, Massimo

AU - Crippa, Stefano

AU - Doglioni, Claudio

AU - Paulino, Jorge

AU - Schulick, Richard D.

AU - Edil, Barish H.

AU - Park, Walter

AU - Yachida, Shinichi

AU - Hijioka, Susumu

AU - Van Hooft, Jeanin

AU - He, Jin

AU - Weiss, Matthew J.

AU - Burkhart, Richard

AU - Makary, Martin

AU - Canto, Marcia I.

AU - Goggins, Michael G.

AU - Ptak, Janine

AU - Dobbyn, Lisa

AU - Schaefer, Joy

AU - Sillman, Natalie

AU - Popoli, Maria

AU - Klein, Alison P.

AU - Tomasetti, Cristian

AU - Karchin, Rachel

AU - Papadopoulos, Nickolas

AU - Kinzler, Kenneth W.

AU - Vogelstein, Bert

AU - Wolfgang, Christopher L.

AU - Hruban, Ralph H.

AU - Lennon, Anne Marie

PY - 2019/7/17

Y1 - 2019/7/17

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85069828509&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069828509&partnerID=8YFLogxK

U2 - 10.1126/scitranslmed.aav4772

DO - 10.1126/scitranslmed.aav4772

M3 - Article

C2 - 31316009

AN - SCOPUS:85069828509

VL - 11

JO - Science Translational Medicine

JF - Science Translational Medicine

SN - 1946-6234

IS - 501

M1 - eaav4772

ER -