UEG's educational platform for gastroenterology education bringing recordings, courses, guidelines, and more together in one place.

UEG Week Berlin 2025 Recordings Gut Guide online

Rate for better recommendations!

Your feedback helps us show you more of what you like and less of what you dislike!

More of this!

We will show you more similar content.

Not for me!

We won't suggest this again.

Bookmark!

Save this content for later!

New to myUEG? Create an account! Log In with myUEG account

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

COMPUTER-ASSISTED OPTICAL DIAGNOSIS OF COLORECTAL POLYPS 1-10MM IN SIZE WHEN USING AUTONOMOUS ARTIFICIAL INTELLIGENCE VERSUS AI-ASSISTED HUMAN DECISION-MAKING: A RANDOMIZED CONTROLLED TRIAL

Free for all myUEG account holders. Your access level is set automatically based on your occupation. Medical professionals get full access to all content. If you are a non-medical user, you can only access UEG Week content from congresses you attended.

Not sure what you can access? Learn more about account types.

Introduction

Artificial Intelligence (AI) -based optical polyp diagnosis (CADx) allows for pathology prediction during colonoscopies to support resecting and discarding polyps. However, it is unclear if clinical use of such CADx modules should be as an autonomous decision-making device or rather to assist endoscopists in their decision-making. We therefore evaluated outcomes for CADx optical diagnosis when used autonomously versus as an assistive device for polyps up to 10mm.

Aims & Methods

We conducted a secondary analysis of a randomized non-inferiority trial in which 1-10mm polyps found in patients undergoing diagnostic, screening, and surveillance colonoscopies were randomized to undergo optical diagnosis using: 1) an Autonomous AI-based CADx diagnosis or 2) an AI-assisted endoscopist diagnosis (AI-H). Primary outcome was the accuracy of optical diagnosis in both arms with reference standard being the histological evaluation of the polyps. Secondary outcomes included the surveillance interval agreement based on USMSTF guidelines when using CADx (with pathology as a reference standard) as well as the proportion of misclassified polyps with advanced histology.

Results

A total of 223 and 227 polyps 1-10mm in size were found amongst 268 patients randomized to the autonomous AI group versus 229 patients to the AI-H group, respectively. Accuracy for optical diagnosis for cases with high-confidence diagnoses was 77.6% (95% confidence interval [CI], 71.5-82.9) in the autonomous AI group versus 74.0% (95% CI, 67.8-79.6) in the AI-H group. When comparing surveillance interval agreement, autonomous AI-A did not exhibit superior agreement with USMSTF pathology-based recommendations compared to AI-H (88.5% [95% CI, 82.0-93.3] vs 83.4% [95% CI, 77.0-88.6]; P = 0.213), but did nearly reach the 90% PIVI recommendation benchmark to implement optical diagnosis. Prevalence of polyps with advanced histology (adenomas with villous component, high-grade dysplasia) and sessile serrated lesions was 11.2% (25/223 polyps) and 7.9% (18/227 polyps) in the autonomous AI and AI-H groups. The inability of CADx and endoscopists to specifically recognize these higher-risk lesions led to mismanagement of 3 out of 16 patients (18.8%) and 2 out of 16 patients (12.5%) with such lesions in the autonomous AI and AI-H groups, respectively.

Diagnostic characteristics for high confidence polyp optical diagnosis
	Autonomous AI			AI-H
Characteristics	1-5mm	6-10mm	1-10mm	1-5mm	6-10mm	1-10mm
Polyps, N	158	65	223	155	72	227
Index Advanced Histology*, n (%)	11 (7.0)	14 (21.5)	25 (11.2)	7 (4.5)	11 (15.3)	18 (7.9)
Accuracy, % (95% CI)	77.8 (70.6-84.1)	76.9 (64.8-86.5)	77.6 (71.5-82.9)	75.5 (67.9-82.0)	70.8 (58.9-81.0)	74.0 (67.8-79.6)
Adenoma, %
Sensitivity	85.0	100.0	89.1	91.7	91.3	91.5
Specificity	64.4	45.5	41.8	59.3	73.1	63.5
* Adenoma with villous component, high-grade dysplasia or sessile serrated lesion

Conclusion

In this study, autonomous use of CADx for optical diagnosis of polyps up to 10mm exhibited similar accuracy compared to its use as an assistive device. Autonomous AI did not achieve statistically significant different agreement with USMSTF guidelines-based surveillance interval assignment. Development of CADx advanced histology recognition and further evaluation of its use as an autonomous versus assistive device within multi-center studies is needed.

Disclosure

Daniel von Renteln has received research funding from ERBE Elektromedizin GmbH, Ventage, Pendopharm, Fujifilm, and Pentax and has received consultant or speaker fees from Boston Scientific Inc, ERBE Elektromedizin GmbH, and Pendopharm. The remaining authors disclose no conflicts.

COMPUTER-ASSISTED OPTICAL DIAGNOSIS OF COLORECTAL POLYPS 1-10MM IN SIZE WHEN USING AUTONOMOUS ARTIFICIAL INTELLIGENCE VERSUS AI-ASSISTED HUMAN DECISION-MAKING: A RANDOMIZED CONTROLLED TRIAL

Megan Oleksiw 1, Mahsa Taghiakbari 2, Roupen Djinbachian 3, Heiko Pohl 4, Alan N. Barkun 5, Sacha Sidani 6, Jeremy Liu Chen Kiow 6, Benoit Panzini 6, Simon Bouchard 6, Erik Deslandres 6, Daniel von Renteln 3

1 Montreal University Hospital Research Center, Montreal, Canada

2 Montreal University Hospital Research Center, Montreal, Canada|||Montreal University Hospital Center (CHUM), Montreal, Canada

3 Montreal University Hospital Center (CHUM), Montreal, Canada|||Montreal University Hospital Research Center, Montreal, Canada

4 Dartmouth-Hitchcock Medical Center, Lebanon, United States|||White River Junction VA Medical Center, Vermont, United States

5 McGill University and McGill University Health Center, Montreal, Canada

6 Montreal University Hospital Center (CHUM), Montreal, Canada

Event

UEG Week Vienna 2024

Topics

Colorectal Endoscopy Histopathology

Submission format

Abstract

Session

AI for polyp detection: Advances, pitfalls and challenges

Citation

United European Gastroenterology Journal 2024; 12 (Supplement 8)

Published

2024

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

I do underwater resection

Michael John Bourke 1

1 Westmead Hospital Sydney, Westmead, Australia

Event

UEG Week Berlin 2025

Topics

Endoscopy Nurses

Session

Large controversies for large polyps

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

TEXTBOOK OUTCOME – MEASURE OF EFFICACY AND SAFETY USED TO COMPARE METHODS OF COMMON BILE DUCT STONE (CBDS) REMOVAL DURING CHOLECYSTECTOMY IN POPULATION BASED PROSPECTIVE COHORT STUDY

Not sure what you can access? Learn more about account types.

Introduction

Methods to clear CBDS carry varying risk of adverse effects while leaving them in situ can lead to complications secondary to retained stones.^1–3 Thus, the modality of choice reasonably affects the assessment of whether an attempted removal of asymptomatic CBDS is feasible and adequate. In Sweden, available methods to clear common bile duct stones identified on intraoperative cholangiography during cholecystectomy are flushing/manipulating with cholangio catheter, trans cystic stone extraction, intra-operative endoscopic retrograde cholangiopancreatography (IOERCP), postoperative ERCP, laparoscopic choledochotomy, open choledochotomy and leaving the stone in situ.

Aims & Methods

This observational cohort study was based on the national Swedish Register for Gallstone Surgery and ERCP (GallRiks) with validated prospectively assembled data for 90% of all cholecystectomies and ERCP procedures in Sweden from 2009 to 2023.⁴ The aim was to assess efficacy and safety of the respective methods of clearing CBDS by estimating their odds ratio (OR) of failing to reach textbook outcome. Leaving CBDS in situ was considered reference method.
Textbook outcome was defined as cholecystectomy and CBDS clearance laparoscopically completed in one session without immediate or 30-day surgical complications (bleeding from wound or GI tract, wound dehiscence, wound infection, sepsis, bile duct injury with or without leakage or bleeding), readmissions, reinterventions, stent placement or prolonged postoperative hospitalization beyond three days.
The size of CBDS was categorized as small (<4mm) intermediate (4-8 mm) and large (>8mm). Patients were considered asymptomatic if no previous or current sign of bilirubinemia, cholangitis or pancreatits was recorded.

Results

Among the 192 203 patients in the register between 2009 and 2023, 25 295 patients presented with a CBDS during cholecystectomy. Failure to achieve textbook outcome was seen for 12 147 (48%) across all stone sizes and management options. Odds ratio of failing textbook outcome when adjusting only for CBDS size was 0.7 (95%CI 0.63-0.77) for intraoperative ERCP and 0.63 (95% CI 0.55-0.71) for transcystic extraction while flushing and manipulating the stone had OR 0.5 (95% CI 0.44-0.57). Laparoscopic choledochotomy had OR 14.36 (95% CI 8.83- 25.09) to fail textbook outcome. All compared to leaving the stone in situ.
For a subgroup of asymptomatic stones smaller than 4mm the flushing manipulating option was the only one beneficial compared to leaving them in situ with unadjusted OR 0.73(95% CI 0.59-0.90) of failing textbook outcome.

Conclusion

This study introduces a novel composite outcome measure—textbook outcome—to define successful, complication-free clearance of common bile duct stones (CBDS) encountered during cholecystectomy. Using this measure, the greatest benefit was seen in the flush/manipulate group, which was also the only approach that provided a clear advantage for small asymptomatic stones compared to leaving them in situ.
Balancing safety and efficacy of CBDS clearance methods remains essential, given the potential for complications associated with interventions in the common bile duct.
Importantly, small asymptomatic stones did not seem to benefit from more invasive removal techniques beyond flushing and manipulation with the cholangiocatheter,
when evaluated using this composite outcome measure. However, these results need to be interpreted with caution due to the risk of selection bias.

References

1 Lammert F, Gurusamy K, Ko CW, Miquel J-F, Méndez-Sánchez N, Portincasa P, et al. Gallstones. Nat Rev Dis Primers [Internet]. Nature Publishing Group; 2016 Apr 28 [cited 2023 Nov 6]; 2: 1–17. Available from: https://www.nature.com/articles/nrdp201624
2 Saito H, Kadono Y, Shono T, Kamikawa K, Urata A, Nasu J, et al. Remaining issues of recommended management in current guidelines for asymptomatic common bile duct stones. World J Gastroenterol [Internet]. 2021 May 14 [cited 2023 Oct 24]; 27: 2131–2140. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8117734/
3 Berg LS, Friis-Andersen H, Zinther NB, Öztoprak M, Gotschalck KA. Feasibility and outcome of transcystic laparoscopic common bile duct exploration as first-line treatment for common bile duct stones: a retrospective cross-sectional study. Surg Endosc [Internet]. 2025 Feb 11 [cited 2025 Feb 17]; 1–11. Available from: https://link.springer.com/article/10.1007/s00464-025-11587-7
4 Enochsson, L. S G. GallRiks Annual Reports 2018 [Internet]. 2019 [cited 2019 Oct 3]. Available from: https://www.ucr.uu.se/gallriks/fou/arsrapporter/arsrapport-2018-2/viewdocument/837

TEXTBOOK OUTCOME – MEASURE OF EFFICACY AND SAFETY USED TO COMPARE METHODS OF COMMON BILE DUCT STONE (CBDS) REMOVAL DURING CHOLECYSTECTOMY IN POPULATION BASED PROSPECTIVE COHORT STUDY

Eyvind Liljegren 1, Emma Sverdén 1, Johanna Osterberg 1, Lars Enochsson 2, Gabriel Sandblom 1

1 Karolinska Institutet, Stockholm, Sweden

2 Umeå University, Stockholm, Sweden

Event

UEG Week Berlin 2025

Topics

Endoscopy Hepatobiliary

Submission format

Abstract

Session

Textbook knowledge and limits of HPB endoscopy

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Quality in polypectomy: How to achieve? How to assess?

Evelien Dekker 1

1 AMC, Amsterdam, Netherlands

Event

UEG Postgraduate Teaching Programme 2023

Topics

Education & Training Endoscopy IBD

Session

How does quality in endoscopy affect the prognosis of our patients?

Published

2023

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Is the prone position during ERCP really safe? Let’s talk about it!

Margherita Ghiraldo 1

1 Azienda Ospedale Università di Padova – Ospedale S. Antonio, Paduva, Italy

Event

UEG Week Copenhagen 2023

Topics

Colorectal Endoscopy Nurses Oesophagus Pancreas

Session

Free papers II: Patient care and assistance

Published

2023

UEG Poster

Standard Poster

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Introduction

Solitary rectal ulcer syndrome (SRUS) is a chronic benign disorder characterized by the presence of an abnormality of the rectum in persons who have a long history of straining during defecation. It is a misnomer as only 3^rd of the patients have solitary ulcer, many have no ulcer.

Aims & Methods

This was a retrospective observational longitudinal study, conducted in the department of Gastroenterology at Jinnah Post graduate Medical Center and National Medical Center, Karachi, from 1^st March 2017 to till to date . All adult patients of either gender diagnosed with SRUS on basis of clinical history and endoscopic features were included in the study. The data obtained was analyzed on the statistical software SPSS version 26.Descriptive statistics were obtained by frequencies and percentages.

Results

There were total 85 patients in our study out of which 49(58%) were female and 36(42%) were male. Mean age was 35 ±17 years. Most common presentation was per rectal bleed 68(80%) ,Constipation 58 (68.57%) and followed by abdominal pain 32(37.9%).The most common predisposing risk factor was 85 (100%) self-digitation, 51(60%) prolong stay in toilet and rectal prolapse 5 (7.1%). Endoscopically most common finding was of single ulcer 80(95.7%), followed by proctitis 59(70%) and multiple ulcers 12(14.3%) and Histology revealed mucosal ulceration 75(88%) extension of muscular fibers 65 (77%), fibromuscular obliteration of lamina propria 59(70%) and crypt distortion 54 (64.3%). Associated psychological condition among patients were obsessive compulsive disorder 51 (60%) and anxiety disorder 46(52%). Most of the patients were treated through lifestyle modification and biofeedback. Only 4 patients were referred to surgical intervention.

Conclusion

SRUS is a rare disorder with variable clinical presentation. In this study patients commonly presented with bleeding p/r followed by abdominal pain. However, common predisposing factor was self -digitation, in this regard awareness is needed in our region.

References

Felt-Bersma RJF. Solitary rectal ulcer syndrome. Curr Opin Gastroenterol. 2021;37(1):59-65.
Sadeghi A, Biglari M, Forootan M, Adibi P. Solitary rectal ulcer syndrome: a narrative review. Middle East J Dig Dis. 2019;11(3):129-34.
Thirumal P, Sumathi B, Nirmala D. A Clinical entity often missed-solitary rectal ulcer syndrome in children. Front Pediatr. 2020;8:396.
Forootan M, Darvishi M. Solitary rectal ulcer syndrome: a systematic review. Medicine (Baltimore). 2018;97(18):e0565.
Abusharifah O, Bokhary RY, Mosli MH, Saadah OI. Solitary rectal ulcer syndrome in children and adolescents: a descriptive clinicopathologic study. Int J Clin Exp Pathol. 2021;14(4):399-407.
Abreu M, Azevedo Alves R, Pinto J, Campos M, Aroso S. Solitary rectal ulcer syndrome: a paediatric case report. GE Port J Gastroenterol. 2017;24(3):142-6
Lambin T, Lafeuille P, Rivory J, Rostain F, Fabritius M, Cotte E, et al. Adenocarcinoma arising from a long-standing solitary rectal ulcer syndrome.

Endoscopy. 2022;54(5):E205-6.