A multi-modality test to guide the management of patients with a pancreatic cyst
- 1. The Ludwig Center and Howard Hughes Medical Institute at the Sidney Kimmel Cancer Center1, The Sol Goldman Pancreatic Cancer Research Center, Biomedical Engineering, The Johns Hopkins Medical Institutions; the Institute for Computational Medicine, the Department of Pathology, Oncology, The Johns Hopkins University, Baltimore, MD, 21287 USA; The Departments of Surgery, Pathology, and Gastroenterology, Memorial Sloan-Kettering Cancer Center, New York, NY 10065 USA; The Department of Surgery, University of Indiana University School of Medicine, Indianapolis IN 46202 USA; The Departments of Surgery and Histopathology and Gastroenterology, Massachusetts General Hospital, Harvard Medical School, Boston MA 02114 USA; The Department of Medicine, and Pathology, University of Pittsburgh. Pittsburgh PA 15213 USA; ARC-Net Research Centre and Department of Pathology and Diagnostics, University and Hospital Trust of Verona, Italy, General and Pancreatic Surgery, The Pancreas Institute, University and Hospital Trust of Verona, Verona 37134 Italy; Department of Pathology, Ospedale Sacro Cuore-Don Calabria, Negrar, 37024 Italy, 20 The Departments of Pathology20 and 21Hepatobiliary and Pancreas Surgery21, Asan Medical Center, University of Ulsan College of Medicine, Seoul, 05505 South Korea., The Department of Surgery and Cancer Research Institute, Seoul National University College of Medicine, Seoul, 03080 South Korea; The Department of Histopathology, and Surgery, St. Vincent's University Hospital, Dublin, D04 T6F4 Ireland; Division of Pancreatic Surgery, Department of Surgery, Department of Pathology, IRCCS San Raffaele Scientific Institute, Milan, 20132 Italy; The Department of PathologySurgery, Centro Hepatobiliopancreático e Transplantação, Hospital Curry Cabral, Lisbon, 1050-099 Portugal; The Department of Surgery, University of Colorado. Aurora CO 80045 USA; The Department of Medicine, Stanford University Medical Center. Palo Alto, CA 94304 USA; The Department of Hepatobiliary and Pancreatic Surgery, Pathology and Cancer Genomics, National Cancer Center Hospital and National Cancer Center Research Institute, Tokyo, 104-0045 Japan; The Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, 464-8681 Japan; The Department of Gastroenterology and Hepatology, Amsterdam Medical Center, Amsterdam 1017 ZX Netherlands; The Department of Surgery, Medicine, Biostatistics and Bioinformatics, and Radiology The Johns Hopkins University, Baltimore, MD, 21287 USA
Description
Pancreatic cysts are common and often pose a management dilemma, as some cysts are pre-cancerous 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 was used as the gold standard. Pathology of the resected specimens was used as the diagnostic 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.
Files
MOCA-master.zip
Files
(743.3 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:0344730844a09b6804a6f037e5600cdf
|
743.3 kB | Preview Download |