A novel approach for selecting combination clinical markers of pathology applied to a large retrospective cohort of surgically resected pancreatic cysts

David L. Masica, Marco Dal Molin, Christopher Wolfgang, Tyler Tomita, Mohammad R. Ostovaneh, Amanda Blackford, Robert A. Moran, Joanna Law, Thomas Barkley, Michael Goggins, Marcia Irene Canto, Meredith Pittman, James R. Eshleman, Syed Z. Ali, Elliot K. Fishman, Ihab R. Kamel, Siva P Raman, Atif Zaheer, Nita Ahuja, Martin A. MakaryMatthew J Weiss, Kenzo Hirose, John L. Cameron, Neda Rezaee, Jin He, Young Joon Ahn, Wenchuan Wu, Yuxuan Wang, Simeon Springer, Luis L. Diaz, Nickolas Papadopoulos, Ralph H. Hruban, Kenneth W. Kinzler, Bert Vogelstein, Rachel Karchin, Anne Marie Lennon

Research output: Contribution to journalArticlepeer-review

21 Scopus citations

Abstract

Objective: Our objective was to develop an approach for selecting combinatorial markers of pathology from diverse clinical data types. We demonstrate this approach on the problem of pancreatic cyst classification. Materials and Methods: We analyzed 1026 patients with surgically resected pancreatic cysts, comprising 584 intraductal papillary mucinous neoplasms, 332 serous cystadenomas, 78 mucinous cystic neoplasms, and 42 solid-pseudopapillary neoplasms. To derive optimal markers for cyst classification from the preoperative clinical and radiological data, we developed a statistical approach for combining any number of categorical, dichotomous, or continuous-valued clinical parameters into individual predictors of pathology. The approach is unbiased and statistically rigorous. Millions of feature combinations were tested using 10-fold cross-validation, and the most informative features were validated in an independent cohort of 130 patients with surgically resected pancreatic cysts. Results: We identified combinatorial clinical markers that classified serous cystadenomas with 95% sensitivity and 83% specificity; solid-pseudopapillary neoplasms with 89% sensitivity and 86% specificity; mucinous cystic neoplasms with 91% sensitivity and 83% specificity; and intraductal papillary mucinous neoplasms with 94% sensitivity and 90% specificity. No individual features were as accurate as the combination markers. We further validated these combinatorial markers on an independent cohort of 130 pancreatic cysts, and achieved high and well-balanced accuracies. Overall sensitivity and specificity for identifying patients requiring surgical resection was 84% and 81%, respectively. Conclusions: Our approach identified combinatorial markers for pancreatic cyst classification that had improved performance relative to the individual features they comprise. In principle, this approach can be applied to any clinical dataset comprising dichotomous, categorical, and continuous-valued parameters.

Original languageEnglish (US)
Pages (from-to)145-152
Number of pages8
JournalJournal of the American Medical Informatics Association
Volume24
Issue number1
DOIs
StatePublished - Jan 2017

Keywords

  • Clinical model
  • Combination marker
  • Composite marker
  • IPMN
  • MOCA
  • Mucinous cyst
  • Pancreatic cyst

ASJC Scopus subject areas

  • Health Informatics

Fingerprint

Dive into the research topics of 'A novel approach for selecting combination clinical markers of pathology applied to a large retrospective cohort of surgically resected pancreatic cysts'. Together they form a unique fingerprint.

Cite this