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

RANDOMISED CONTROLLED TRIAL OF A CLOUD-BASED ARTIFICIAL INTELLIGENCE POLYP DETECTION SYSTEM (CADDIE)

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

Colorectal Cancer (CRC) is the third commonest cancer in men and women¹. Most CRCs develop from adenomatous polyps, with colonoscopy as the gold standard for screening. However, up to 27% of polyps are missed during colonoscopy². Artificial intelligence (AI) in endoscopy has been gaining increasing attention for its role in automated lesion detection and characterisation but clinical studies to date are limited to AI models that are deployed locally using computer hardware whilst polyp detection studies largely focus on expert colonoscopists in screening populations such as the UK bowel cancer screening programme (BCSP)³.

Aims & Methods

In this multi-centre, prospective randomized controlled parallel design trial, we aimed to assess whether the real-time cloud-based AI polyp detection system CADDIE improves adenoma detection rate (ADR) in symptomatic and surveillance patients when colonoscopy is undertaken by non-expert colonoscopists in routine clinical settings.
We enrolled 739 patients between April 2021 and Dec 2022, scoped by 32 endoscopists in 9 UK hospitals. Participants scheduled for surveillance or symptomatic colonoscopy aged 18 years or older were invited to participate. Exclusions included inpatient procedures, known inflammatory bowel disease (IBD), colorectal cancer, polyposis syndromes, previous resections, and planned therapy. Each endoscopist was limited to a maximum of 60 procedures and required to perform more than 20% of this target. The study was powered to show an increase in ADR between the two arms, using a two-group z-test with 80% power, a two-sided α level of 0.05 and accounting for an expected dropout rate of 10%. Patients were block randomised in a 1:1 ratio to standard of care (SOC) or intervention (CADDIE), stratified by endoscopist and indication. The primary end point was the difference in endoscopist ADR between intervention and SOC arms.

Results

There were 614 evaluable patients. ADR was significantly higher in the CADDIE group compared to SOC (Table 1). Adenomas were detected in 7.6% more patients in the CADDIE group than the SOC group (P=0.03). Proximal ADR was also 6.1% higher in the CADDIE group (P=0.01). Over 50% more adenomas were removed per colonoscopy (APC) in the CADDIE group compared to SOC (P=0.008). Although results were not significant for other outcomes, the general trend was towards higher detection in the CADDIE group.
We excluded 125 patients from data analysis as pre-defined in the study protocol (e.g. endoscopist moving hospital before meeting minimum recruitment target). Despite this, the study reached its recruitment goals.

Results Table

Mean (S.D)	Standard of Care (n=308)	Intervention (CADDIE) (n=306)	Adjusted Analysis (for sex, age and indication)
Age, mean ± S.D	57.8 ± 14.7	59.5 ± 14.7
Male sex, number (%)	153 (49.7%)	147 (48.0%)
Indication (symptomatic / surveillance)	91.9% / 8.1%	91.2%/8.8%
ADR	78 (25.3%)	103 (33.7%)	7.6%; P = 0.03
Proximal adenoma detection rate (pADR)	47 (15.3%)	72 (23.5%)	6.1% P = 0.01
Mean adenomas per colonoscopy (APC) ± S.D.	0.42 ± 0.98	0.66 ± 1.44	0.23; P = 0.008
Adenomas per extraction (APE)	129 (61.1%)	202 (67.6%)	4.5% P = 0.39
SSLs per colonoscopy (SLPC)	0.05 ± 0.26	0.07 ± 0.31	2.0% P = 0.40

Conclusion

We have shown a significant improvement in adenoma detection of almost 8% using the cloud-based CADDIE AI system in a non-screening population across a wide range of UK hospitals, where the endoscopists were independent but not BCSP trained. This increased detection was also seen in the proximal colon, where many hard to detect lesions are found. Furthermore, total numbers of adenomas removed per colonoscopy, which is increasingly recognised as an important metric of procedure quality, was significantly increased.

References

1. Xi Y, Xu P. Global colorectal cancer burden in 2020 and projections to 2040. Transl Oncol. 2021 Oct;14(10):101174. doi: 10.1016/j.tranon.2021.101174. Epub 2021 Jul 6. PMID: 34243011; PMCID: PMC8273208.
2. Zhao S, Wang S, Pan P, Xia T, Chang X, Yang X, Guo L, Meng Q, Yang F, Qian W, Xu Z, Wang Y, Wang Z, Gu L, Wang R, Jia F, Yao J, Li Z, Bai Y. Magnitude, Risk Factors, and Factors Associated With Adenoma Miss Rate of Tandem Colonoscopy: A Systematic Review and Meta-analysis. Gastroenterology. 2019 May;156(6):1661-1674.e11. doi: 10.1053/j.gastro.2019.01.260. Epub 2019 Feb 6. PMID: 30738046.
3. Hassan C, Spadaccini M, Iannone A, Maselli R, Jovani M, Chandrasekar VT, Antonelli G, Yu H, Areia M, Dinis-Ribeiro M, Bhandari P, Sharma P, Rex DK, Rösch T, Wallace M, Repici A. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis. Gastrointest Endosc. 2021 Jan;93(1):77-85.e6. doi: 10.1016/j.gie.2020.06.059. Epub 2020 Jun 26. PMID: 32598963.

Disclosure

Laurence B Lovat is a consultant for, and minority shareholder in Odin Vision

RANDOMISED CONTROLLED TRIAL OF A CLOUD-BASED ARTIFICIAL INTELLIGENCE POLYP DETECTION SYSTEM (CADDIE)

Rawen Kader 1, Paul Bassett 2, Yusuf Kabir 3, Sharon Cheung 3, Lester Macabodbod 3, Archana Jayanthi 3, Manish Chand 4, Laurence B. Lovat 1

1 Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London (UCL), London, United Kingdom|||University College London Hospital, London, United Kingdom

2 Statsconsultancy Ltd, London, United Kingdom

3 Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London (UCL), London, United Kingdom

4 University College London Hospital, London, United Kingdom

Event

UEG Week Copenhagen 2023

Topics

Colorectal Digestive Oncology Endoscopy Mechanisms & Personalised Medicine

Submission format

Abstract

Session

AI in lower GI endoscopy

Citation

United European Gastroenterology Journal 2023; 11 (Supplement 8)

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.

Optimising surgical therapies in fistulising Crohn's disease

Philip J. Tozer 1

1 St Marks Hospital, London, United Kingdom

Event

UEG Week Berlin 2025

Topics

IBD Mechanisms & Personalised Medicine Surgery

Session

Focus on fistulising Crohn’s disease

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.

Which measures are important to prevent complication of IBD

Elena Sonnenberg 1

1 Charité – Universitätsmedizin Berlin, Berlin, Germany

Event

UEG Week Berlin 2025

Topics

IBD Nurses

Session

IBD nurses: All around the gut

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.

Which advanced therapy should you choose in patients with fistulising Crohn's disease?

Krisztina Barbara Gecse 1

1 Amsterdam University Medical Center, Amsterdam, Netherlands

Event

UEG Week Berlin 2025

Topics

IBD Mechanisms & Personalised Medicine Surgery

Session

Focus on fistulising Crohn’s disease

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.

Summary: Metabolic and vascular disorders of the liver

Event

UEG Postgraduate Teaching Programme Berlin 2025

Topics

Hepatobiliary

Session

Metabolic and vascular disorders of the liver

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.

Undertstanding genetic causes of liver and bile duct diseases: Treatment implications

Verena Keitel-Anselmino 1

1 University Hospital Magdeburg, Magdeburg, Germany

Event

UEG Week Berlin 2025

Topics

Hepatobiliary Mechanisms & Personalised Medicine

Session

Infectious and rare hepatitis

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

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

Intestinal ultrasound (IUS) is a non-invasive modality for monitoring disease activity in inflammatory bowel disease (IBD). While widely used for long-term assessment, its utility in early response evaluation following biologic therapy initiation or modification remains underexplored.

Aims & Methods

This prospective study aimed to assess early ultrasonographic response at week 6 in ulcerative colitis (UC) and Crohn’s disease (CD) patients undergoing induction, dose escalation, or switching of biologic therapy. A total of 24 patients (mean age: 40.1 ± 12.8 years; 54.2% female) were included. Fourteen patients (58.3%) were initiating biologic treatment, 4 (16.7%) underwent dose escalation, and 6 (25%) were switched to another biologic agent. Biologic therapies included infliximab (70.8%), adalimumab (16.7%), and others (12.5%). IUS examination was performed at baseline and at week 6. The following parameters were assessed: bowel wall thickness (BWT), wall stratification, color doppler signal activity and mesenteric fat inflammation. IUS remission was defined as bowel wall thickness less than 3 mm and no color doppler signal. IUS improvement was defined as more than 25% decrease in bowel wall thickness without increase in color doppler signal. IUS activity assesment was performed at the same segment of the bowel at the 6th weeks.

Results

A total of 24 patients were included in the study, with a mean age of 40.1 ± 12.8 years; 13 (54.2%) were female. Seven patients (29.2%) had ulcerative colitis (UC), and 17 (70.8%) had Crohn’s disease (CD). Fourteen patients (58.3%) had newly initiated biologic therapy, 4 (16.7%) underwent dose escalation, and 6 (25%) were switched to a different biologic agent. Anti-TNF agents were used in 21 patients (87.5%), including infliximab in 17 (70.8%) and adalimumab in 4 (16.7%). The remaining 3 patients (12.5%) were treated with other biologic agents. At baseline, the most active intestinal segment on IUS was the terminal ileum in CD patients (9 patients, 52.9%) and the sigmoid colon in UC patients (4 patients, 57.1%) (p = 0.021). At week 6, 11 patients (45.8%) showed ultrasonographic improvement, 9 patients (37.5%) had no change, and 4 patients (16.7%) showed worsening. The baseline mean bowel wall thickness (BWT) of the most active segment was 5.5 ± 1.3 mm, which decreased to 4.4 ± 1.7 mm at week 6. A reduction in BWT was observed in 18 patients (75%), while an increase was seen in 6 patients (25%) (p = 0.002). In multivariate regression analysis, higher baseline bowel wall thickness was identified as an independent predictor of ultrasonographic improvement at week 6 (OR: 3.137; 95% CI: 1.005–9.790; p = 0.04). In patients who showed improvement, bowel wall thickness significantly decreased from baseline 6.2 ± 1.5 mm to 3.7 ± 1.6 mm at week 6 (to; p = 0.003), whereas in patients who worsened, an increase in wall thickness was observed (5.3 ± 1.0 mm to 6.7 ± 1.7 mm; p = 0.068). By disease group, 5 of the UC patients (71.4%) showed ultrasonographic improvement, 1 (14.3%) remained unchanged, and 1 (14.3%) worsened. Among CD patients, 6 (35.3%) showed improvement, 8 (47.1%) had no change, and 3 (17.6%) worsened. However, there was no statistically significant difference in response patterns between the UC and CD groups (p = 0.244).

Conclusion

Intestinal ultrasound at week 6 effectively detected early treatment response, with baseline bowel wall thickness emerging as a predictor of improvement. These results support its use in routine early monitoring of IBD patients on biologic therapy.

References

1. Calabrese E, Rispo A, Zorzi F, De Cristofaro E, Testa A, Costantino G, Viola A, Bezzio C, Ricci C, Prencipe S, Racchini C, Stefanelli G, Allocca M, Scotto di Santolo S, D'Auria MV, Balestrieri P, Ricchiuti A, Cappello M, Cavallaro F, Guarino AD, Maconi G, Spagnoli A, Monteleone G, Castiglione F. Ultrasonography Tight Control and Monitoring in Crohn's Disease During Different Biological Therapies: A Multicenter Study. Clin Gastroenterol Hepatol. 2022 Apr;20(4):e711-e722.
2. Paredes JM, Moreno N, Latorre P, Ripollés T, Martinez MJ, Vizuete J, Moreno-Osset E. Clinical Impact of Sonographic Transmural Healing After Anti-TNF Antibody Treatment in Patients with Crohn's Disease. Dig Dis Sci. 2019 Sep;64(9):2600-2606.