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, Lü; Cohen, Joshua D.; Thompson, Elizabeth D.; Allen, Peter J.; Klimstra, David S.; Schattner, Mark; Schmidt, C. Max; Yip-Schneider, Michele; Simpson, Rachel E.; Castillo, Carlos Fernández del; Mino‐Kenudson, Mari; Brugge, William R.; Brand, Randall E.; Singhi, Aatur D.; Scarpa, Aldo; Lawlor, Rita T.; 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 G.; Yachida, Shinichi; Hijioka, Susumu; Hooft, Jeanin E. van; He, Jin; Weiss, Matthew J.; Burkhart, Richard A.; Makary, Martin A.; Canto, Marcia Irene; Goggins, Michael; 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

doi:10.1126/scitranslmed.aav4772

Cited by 140 publications

(131 citation statements)

References 37 publications

Supporting

Mentioning

128

Contrasting

Unclassified

Order By: Relevance

“…MCLs can have mutations in KRAS, while GNAS mutations are highly specific. Overall, almost two thirds of IPMNs and MCNs harbor a mutation in KRAS or GNAS in the cyst fluid 41 . A novel recently-described approach is to combine the most specific clinical features with molecular markers.…”

Section: Cystic Lesionsmentioning

confidence: 99%

“…A novel recently-described approach is to combine the most specific clinical features with molecular markers. A recent study of 862 individuals undergoing surgery for pancreatic cysts, found that a combined molecular and clinical marker panel was more accurate than current clinical features alone, and use of these markers would have decreased the number of unnecessary operations by 60% 41 .…”

Section: Cystic Lesionsmentioning

confidence: 99%

“…While a comprehensive review of candidate biomarkers for early detection is beyond the scope of this review, we have highlighted several novel biomarkers resulting from studies designed with early detection in mind, summarised in Table 2. Note, genetic biomarkers were discussed in more detail in an earlier section of this review 41 . Future validation of these candidate biomarkers and others must demonstrate sufficient evidence to support their application in early detection through the use of pre-diagnostic human samples and appropriate controls (e.g.…”

Section: Current Promising Biomarkers For the Early Detection Of Pdacmentioning

confidence: 99%

See 2 more Smart Citations

Early detection of pancreatic cancer

Pereira

Oldfield

Ney

et al. 2020

The Lancet Gastroenterology & Hepatology

Self Cite

320

289

View full text Add to dashboard Cite

Pancreatic ductal adenocarcinoma (PDAC) is most frequently detected at an advanced stage. This limits treatment options and contributes to a dismal 5-year survival rate of 3 to 15%. PDAC is relatively uncommon and with current modalities, screening of the asymptomatic adult population is not feasible or recommended. However, screening of individuals in highrisk groups is undertaken. Here we review high-risk groups for PDAC, including individuals with inherited predisposition and patients with pancreatic cystic lesions. We discuss new studies aimed at finding ways of identifying PDAC in high-risk groups, such as individuals with new-onset diabetes mellitus and those attending primary and secondary care practices with suggestive symptoms. We review early detection biomarkers, explore the potential of exploiting social media for PDAC detection, appraise prediction models developed using electronic health records and research data, and examine the application of artificial intelligence to imaging for the purposes of early PDAC detection.

show abstract

Section: Cystic Lesionsmentioning

confidence: 99%

Section: Cystic Lesionsmentioning

confidence: 99%

Section: Current Promising Biomarkers For the Early Detection Of Pdacmentioning

confidence: 99%

See 1 more Smart Citation

Early detection of pancreatic cancer

Pereira

Oldfield

Ney

et al. 2020

The Lancet Gastroenterology & Hepatology

Self Cite

320

289

View full text Add to dashboard Cite

show abstract

“…Last years, there has been an increasing interest in artificial intelligence (AI)based diagnosis of IPMN and PCN in general. Two study groups have developed AIbased diagnostic algorithms using clinical, imaging, and cyst fluid features to assess the presence of advanced neoplasia with promising results for future implementation in clinical practice [130,131].…”

Section: Surveillancementioning

confidence: 99%

Endoscopic Management and Follow-Up of Intraductal Papillary Mucinous Neoplasia (IPMN)

Hoogenboom¹,

Fockens²,

Wallace³

et al. 2020

Gastrointestinal and Pancreatico-Biliary Diseases: Advanced Diagnostic and Therapeutic Endoscopy

View full text Add to dashboard Cite

Intraductal papillary mucinous neoplasms (IPMN) are common and increasingly detected in patients undergoing cross-sectional imaging for reasons unrelated to the pancreas. Individuals diagnosed with an IPMN should be followed over time because of the malignant potential of these cystic lesions. The primary goal of surveillance is to identify the small minority of IPMN that progresses into advanced neoplasia and benefits from resection, while simultaneously avoiding unnecessary pancreatic surgery in the majority of IPMN that remains benign. Cross-sectional imaging and endoscopic ultrasound with or without fluid and tissue acquisition are currently used to evaluate the risk of malignancy in IPMN. This chapter summarizes the diagnostic workup, surveillance, and treatment of IPMN, focusing on endoscopic modalities and adjacent tests.

show abstract

“…[5][6][7][8][9] Beyond endoscopy, computer vision is also being applied quite extensively in abdominal radiology, for instance, to classify and risk stratify pancreatic cysts identified on CT and magnetic resonance imaging, in some cases with algorithms that can integrate other clinical and laboratory data as well. 10,11 To focus only on computer vision, however, creates a too-narrow view of the potential for AI in gastroenterology. There is also enthusiasm and some early progress for AI technologies seeking to reduce the tremendous burden of documentation in electronic health records (EHRs), to automate repetitive tasks, to reduce administrative burdens, and to facilitate quality reporting and analytics.…”

mentioning

confidence: 99%

Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force

Berzin

Parasa

Wallace

et al. 2020

Gastrointestinal Endoscopy

View full text Add to dashboard Cite

Artificial intelligence (AI) in GI endoscopy holds tremendous promise to augment clinical performance, establish better treatment plans, and improve patient outcomes. Although there are promising initial applications and preliminary clinical data for AI in gastroenterology, the field is still in a very early phase, with limited clinical use. The American Society for Gastrointestinal Endoscopy has convened an AI Task Force to develop guidance around clinical implementation, testing/validating algorithms, and building pathways for successful implementation of AI in GI endoscopy. This White Paper focuses on 3 areas: (1) priority use cases for development of AI algorithms in GI, both for specific clinical scenarios and for streamlining clinical workflows, quality reporting, and practice management; (2) data science priorities, including development of image libraries, and standardization of methods for storing, sharing, and annotating endoscopic images/video; and (3) research priorities, focusing on the importance of high-quality, prospective trials measuring clinically meaningful patient outcomes. (Gastrointest Endosc 2020;92:951-9.) Artificial intelligence (AI) is poised to play a crucial role throughout the practice of gastroenterology. Machine learning (ML) is a branch of AI focusing on computer algorithms that can learn from data and perform specific tasks and analyses, often without explicit human programming. Deep learning is an advanced subset of ML that relies on specific algorithms termed artificial neural networks. The enthusiasm for medical AI applications has centered around expectations that these technologies may assist physicians by assimilating, triaging, and interpreting clinical data (laboratory results, electrocardiographic tracings, CTs, etc) to support physician performance in a consistent manner in all phases of clinical care and automate certain burdensome tasks, such as clinical documentation and billing, to allow physicians to refocus on direct patient care and other meaningful professional activities.

show abstract

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

Cited by 140 publications

References 37 publications

Early detection of pancreatic cancer

Early detection of pancreatic cancer

Endoscopic Management and Follow-Up of Intraductal Papillary Mucinous Neoplasia (IPMN)

Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force

Contact Info

Product

Resources

About