Real-Time AI During Pancreatoscopy for Detection of Pancreatic Neoplasia

This prospective pilot study will evaluate the diagnostic performance of a previously validated artificial intelligence (AI) model when applied in real time during digital per-oral pancreatoscopy (POPS). The study will include adults undergoing clinically indicated pancreatoscopy for suspected or known intraductal papillary mucinous neoplasm (IPMN), indeterminate pancreatic-duct abnormalities, or preoperative assessment of IPMN extent. During the procedure, the endoscopist will first record a visual assessment while the AI system is hidden. The AI overlay will then be activated during the same pancreatoscopy examination, and its findings will be recorded independently. AI and endoscopist assessments will be compared with a prespecified reference standard based on surgical histopathology when available or tissue sampling and clinical/imaging follow-up when surgery is not performed. The primary objective is to estimate the sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of real-time AI for identifying high-grade dysplasia or invasive carcinoma. The study is designed as a pilot to assess feasibility and generate preliminary diagnostic-accuracy estimates for future confirmatory research.

Sex

All

Minimum age

18 Years

Inclusion Criteria:

1. Adults aged 18 years or older.
2. Patients with a clinical indication for digital per-oral pancreatoscopy (POPS) as part of their diagnostic evaluation or preoperative assessment.
3. Patients with one or more of the following clinical indications:

   3.1. Suspected or known main-duct or mixed-type IPMN. 3.2. Branch-duct IPMN with suspected communication with the main pancreatic duct and worrisome features or high-risk stigmata.

   3.3. Indeterminate main pancreatic duct stricture, filling defect, or intraductal abnormality after cross-sectional imaging and/or EUS.

   3.4. Need for preoperative assessment or mapping of IPMN extent.
4. Ability to undergo digital POPS according to the treating team's clinical assessment.
5. Ability to provide written informed consent.
6. Availability of an adequate reference-standard assessment, including histopathology when surgery is performed or tissue/cytologic assessment with clinical and imaging follow-up when surgery is not performed.
7. Willingness and ability to complete the required 6-month clinical/imaging follow-up when a surgical reference standard is not available.

Exclusion Criteria:

1. Acute pancreatitis within 2 weeks before the planned pancreatoscopy.
2. Hemodynamic instability or clinical condition precluding safe pancreatoscopy.
3. ASA physical status IV or V when the treating team determines that the procedure cannot be safely performed.
4. Uncorrectable coagulopathy or other contraindication to pancreatoscopy and/or tissue sampling.
5. Pancreatic or gastrointestinal altered anatomy that prevents technically feasible digital POPS.
6. Evidence of unsafe pancreatic duct disruption or another anatomical or procedural condition that makes pancreatoscopy inappropriate.
7. Pregnancy.
8. Inability or unwillingness to provide informed consent.
9. Inability or unwillingness to complete the required follow-up when a non-surgical reference standard is necessary.

• BACKGROUNDBossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, Lijmer JG, Moher D, Rennie D, de Vet HC, Kressel HY, Rifai N, Golub RM, Altman DG, Hooft L, Korevaar DA, Cohen JF; STARD Group. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ. 2015 Oct 28;351:h5527. doi: 10.1136/bmj.h5527. PMID 26511519
• BACKGROUNDde Jong DM, Stassen PMC, Groot Koerkamp B, Ellrichmann M, Karagyozov PI, Anderloni A, Kylanpaa L, Webster GJM, van Driel LMJW, Bruno MJ, de Jonge PJF; European Cholangioscopy study group. The role of pancreatoscopy in the diagnostic work-up of intraductal papillary mucinous neoplasms: a systematic review and meta-analysis. Endoscopy. 2023 Jan;55(1):25-35. doi: 10.1055/a-1869-0180. Epub 2022 Jun 3. PMID 35668651
• BACKGROUNDKahaleh M, Gaidhane M, Shahid HM, Tyberg A, Sarkar A, Ardengh JC, Kedia P, Andalib I, Gress F, Sethi A, Gan SI, Suresh S, Makar M, Bareket R, Slivka A, Widmer JL, Jamidar PA, Alkhiari R, Oleas R, Kim D, Robles-Medranda CA, Raijman I. Digital single-operator cholangioscopy interobserver study using a new classification: the Mendoza Classification (with video). Gastrointest Endosc. 2022 Feb;95(2):319-326. doi: 10.1016/j.gie.2021.08.015. Epub 2021 Aug 31. PMID 34478737
• BACKGROUNDRobles-Medranda C, Valero M, Soria-Alcivar M, Puga-Tejada M, Oleas R, Ospina-Arboleda J, Alvarado-Escobar H, Baquerizo-Burgos J, Robles-Jara C, Pitanga-Lukashok H. Reliability and accuracy of a novel classification system using peroral cholangioscopy for the diagnosis of bile duct lesions. Endoscopy. 2018 Nov;50(11):1059-1070. doi: 10.1055/a-0607-2534. Epub 2018 Jun 28. PMID 29954008
• BACKGROUNDRobles-Medranda C, Baquerizo-Burgos J, Alcivar-Vasquez J, Kahaleh M, Raijman I, Kunda R, Puga-Tejada M, Egas-Izquierdo M, Arevalo-Mora M, Mendez JC, Tyberg A, Sarkar A, Shahid H, Del Valle-Zavala R, Rodriguez J, Merfea RC, Barreto-Perez J, Saldana-Pazmino G, Calle-Loffredo D, Alvarado H, Lukashok HP. Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model. Endoscopy. 2023 Aug;55(8):719-727. doi: 10.1055/a-2034-3803. Epub 2023 Feb 13.