Introduction

Endoscopic evaluation of disease severity remains the cornerstone of disease assessment in ulcerative colitis (UC). Endoscopic evaluation using scoring systems such as the Mayo Endoscopic Subscore (MES) is, however, subjective with interrater agreements typically ranging from a kappa of 0.4 to 0.7. Post-hoc analysis from clinical trials indicates that up to 30% of patients were incorrectly included due to misclassification of disease severity. Recent studies including our own using artificial intelligence (AI) to assess the MES have shown enhanced classification accuracy using only white light procedures¹.

Aims & Methods

In this study, we aimed to refine our AI model to assess disease severity using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS).
We extracted 2000 images from recorded sigmoidoscopy/colonoscopy performed on UC patients at the Gastrounit, Copenhagen University Hospital Hvidovre, Denmark. Six IBD experts from The Digestive Disease Center, Copenhagen Univresity Hospital Bispebjerg, scored each image according to the UCEIS and MES. The majority score from the six experts for each subscore (Bleeding, Erosions and Ulcers, Vascular Pattern) was considered the gold standard. In cases of tied scores, the higher score was selected, preferring a model that overestimates rather than underestimates disease severity. The final UCEIS score was the sum of the gold standards for each subscore.
A convolutional neural network was trained on 80% of the images, and then validated on the remaining 20%. The network performance was evaluated against gold standard and individual experts’ scores.

Results

All six experts evaluated all 2000 images; the results are summarized in Table 1.

Table 1: Comparative kappa scores from the leave-one-out analysis of experts and the model versus gold standard (majority score from all six experts) for each subscore and the total of the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Mayo Endoscopic Subscore (MES)
(linear) Kappa	Expert Mean	Min	Max	AI Model
Bleeding	0.62	0.44	0.73	0.78
Erosion and Ulcers	0.65	0.46	0.71	0.82
Vascular pattern	0.73	0.41	0.88	0.88
Total UCEIS	0.69	0.44	0.80	0.84
Total MES	0.68	0.50	0.77	0.87

The model surpassed the interrater reliability of expert IBD endoscopists in all subscores, showing particularly strong performance in the erosion and ulcers and vascular patterns subscores. The model’s moderate performance in the "bleeding" subscore reflects the lower kappa scores among experts, underscoring the challenges of visual assessments in this area. Notably, the model's performance on the MES was high, indicating significant overlap in the visual cues used for both UCEIS and MES scoring.

Conclusion

This study demonstrates the potential of using an AI model to enhance the accuracy of UC severity assessments with the UCEIS with results surpassing experts. The overlapping visual cues for MES and UCEIS suggest that the AI model can streamline training and application across different scoring systems, enhancing clinical practice efficiency.
We plan to validate the model on a new test set from another hospital to further evaluate its generalizability and effectiveness across various settings. This is essential for confirming its potential to significantly improve the consistency and precision of UC severity assessments.

References

1. Lo, B. et al. High accuracy in classifying endoscopic severity in ulcerative colitis using convolutional neural network. American Journal of Gastroenterology Publish Ah, (2022).
​

Introduction

Biliary strictures are usually caused by malignancies such as Cholangiocarcinoma (CCA) or Pancreatic Ductal Adenocarcinoma (PDAC). 70% of these neoplasms are diagnosed at advanced stages due to late-onset symptoms, lack of biomarkers, and challenges in obtaining histological samples. Curative surgical resection with adjuvant therapy is the first-line treatment, but 20% of cases are resectable at diagnosis and 80% relapse within 3 years^1,2. The impact of systemic therapies on overall survival remains limited, however new targeted therapies have shown remarkable efficacy in patients with actionable mutations based on tumor genetic profiling. Clinical guidelines advocate multigene panel analysis of tumor tissue prior to or during first-line treatment^3,4, considering that 40% of CCA patients and around 25% of PDAC patients harbor actionable genetic mutations^5,6. When tumor tissue is insufficient, liquid biopsies using cfDNA can be considered³. Liquid biopsy of bile, collected during an Endoscopic Retrograde Cholangiopancreatography (ERCP) in malignant biliary stricture cases, could potentially detect therapeutic targets.

Aims & Methods

This prospective proof-of-concept pilot study aims to assess NGS-based cfDNA analysis in bile as a novel liquid biopsy for detecting genetic mutations, and specifically actionable mutations, compared to tissue NGS.
19 CCA and 9 PDAC patients with malignant biliary stenosis undergoing ERCP in a tertiary hospital (2017-2020) were included. Bile samples were collected during the first ERCP and the Pathological Anatomy department selected tissue samples with ≥40% tumor content. Massive sequencing of DNA libraries was performed using the Pan-Cancer Panel^TM (52-genes) for bile samples, and the Oncomine^TM Comprehensive Assay Panel v3 (161 genes) for tissue.

Results

Concerning CCA patients, bile NGS identified all patients with mutations (19/19) opposite to 84.3% (16/19) of patients in tissue. Bile NGS identified 7 patients (37%) with actionable mutations, none was detected in tissue. We detected 47/49 mutations in bile NGS vs. 22/49 in tissue. High concordance was observed: 91% (20/22) of tissue mutations were also in bile. Regarding actionable mutations considered in ESMO guidelines³; 7 were detected in bile NGS, none detected in tissue. The actionable mutations identified were ERBB2 (5), IDH2 (1), and KRAS^G12C(1).
In the PDAC group, bile NGS identified 89% (8/9) of patients with mutations, compared to 66.6% (6/9) of patients in tissue. Bile NGS identified 5 patients (55%) with actionable mutations vs. 4 (44%) in tissue. Bile NGS detected 16/18 mutations in bile in contrast to 12/18 in tissue. High concordance was observed: 83.3% (10/12) of tissue mutations were also in bile. NGS in bile detected 6 actionable mutations considered in ESMO guidelines^4,; KRAS^G12D (5) and ERBB3, compared to 4 in tissue; KRAS^G12D.

Conclusion

These results highlight the potential of bile liquid biopsy in detecting actionable mutations; bile NGS increased the diagnosis sensibility and the number of mutations detected, compared with tissue NGS, which could allow more patients to be considered for targeted therapies. This approach does not require histological material consumption and collecting bile during an ERCP is simple and secure. In addition, NGS technology is available in all molecular laboratories. We consider that the application of liquid biopsy in bile can be accessible and an effective tool, with direct and immediate clinical implementation, improving precision medicine strategies and the therapeutic management of CCA and PDAC patients with biliary stenosis.

References

1. Banales JM, Marin JJG, Lamarca A, Rodrigues PM, Khan SA, Roberts LR, et al. Cholangiocarcinoma 2020: the next horizon in mechanisms and management. Nat Rev Gastroenterol Hepatol. 2020 Sep;17(9):557-588. Epub 2020 Jun 30.
2.Park W, Chawla A, O’Reilly EM. Pancreatic Cancer: A Review. JAMA. 2021 Sep 7;326(9):851–62.3.
3.Vogel A, Ducreux M; ESMO Guidelines Committee. ESMO Clinical Practice Guideline interim update on the management of biliary tract cancer. ESMO Open. 2025 Jan;10(1):104003. Epub 2024 Dec 17.
4.Conroy T, Pfeiffer P, Vilgrain V, Lamarca A, Seufferlein T, O’Reilly EM, et al. Pancreatic cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up. Ann Oncol. 2023 Nov;34(11):987–1002.
5. Gilbert TM, Randle L, Quinn M, McGreevy O, O'leary L, Young R, et al. Molecular biology of cholangiocarcinoma and its implications for targeted therapy in patient management. Eur J Surg Oncol. 2025 Feb;51(2):108352. Epub 2024 Apr 17
6. Boileve A, Smolenschi C, Lambert A, Boige V, Tarabay A, Valery M, et al. Role of molecular biology in the management of pancreatic cancer. World J Gastrointest Oncol. 2024 Jul 15;16(7):2902-2914.

Introduction

Crohn’s disease (CD) is associated both (i) with polymorphisms in the card15 gene, coding for the cytosolic NOD2 innate immunity receptor, recognizing bacterial peptidoglycan (PG), and (ii) with a decrease in Faecalibacterium, an anti-inflammatory intestinal bacterium¹. Oral administration of Faecalibacterium could represent a novel therapeutic strategy for CD patients, which is currently under investigation with F. prausnitzii EXL01 strain (human clinical trial #NCT05542355). Indeed, Faecalibacterium exhibits anti-inflammatory effects both in vitro and in vivo in colitis models^1-6 and we recently discovered that it directly induced the production of Interleukin-10 (IL-10) in CD14+ human monocytes⁷. However, the bacterial molecules, the host receptors and signaling pathways involved are still poorly understood. Therefore, the aim of the current study was to decipher the role of the interaction between Faecalibacterium, its PG and NOD2 in health and CD.

Aims & Methods

The PG structure of F. prausnitzii EXL01 was determined by ultra high-performance liquid chromatography and mass spectrometry. NOD2 activation was evaluated using HEK-human NOD2 reporter cell line. Following stimulation with either bacteria or PG, secretion of IL-10 and TNF-a by i) WT and NOD2 KO THP1 human monocytic cell line and ii) by dendritic cells (DC) from WT and NOD2^-/- mice and from human patients with CD harboring 0 or 2 NOD2 loss-of-function frameshift mutations were evaluated by ELISA.

Results

Faecalibacterium PG presents an amino acid substitution in the minimal motif recognized by NOD2 (data patented). PG of F. prausnitzii activates NOD2, but not NOD1, in a dose-dependent manner and has a higher ability to activate NOD2 than the one from other Gram positive bacteria. We showed that the production of IL-10 by THP1 monocytes and murine DC upon stimulation either with F. prausnitzii or its PG was decreased in absence of NOD2, indicating that secretion of IL-10 by human and murine immune cells upon Faecalibacterium stimulation is dependent on NOD2. Interestingly, no significant effect was observed for TNF-a secretion, leading to a significant decrease of the IL-10/TNF- a ratio in NOD2 KO cells. In addition, secretion of IL-10 upon stimulation with F. prausnitzii or its PG was lower in DC from CD patients with 2 NOD2 loss-of-function frameshift mutations compared to DC from CD patients without NOD2 mutation. Levels of secreted TNF-a were higher in DC from CD patients with 2 NOD2 loss-of-function frameshift mutations compared to DC from CD patients without NOD2 mutation, leading to decreased IL-10/TNF- a ratio in absence of functional NOD2. The pathways downstream of NOD2 as well as the effects of Faecalibacterium and its PG on NOD2 in vivo are currently under investigation.

Conclusion

Our study showed that Faecalibacterium and its PG activate NOD2, and therefore the production of IL-10, in a different way than other Gram-positive bacteria. These results provide new insight into the molecular pathways underlying the immunomodulatory effects of F. prausnitzii, and highlight NOD engagement as a key immunological feature. Identification of PG as a molecule responsible for the therapeutic effects paves the way for the next generation of Faecalibacterium-based drugs, whether whole-cell or component-driven, in inflammatory diseases such as CD.

References

1. Sokol H, Pigneur B, Watterlot L, et al. Faecalibacterium prausnitzii is an anti-inflammatory commensal bacterium identified by gut microbiota analysis of Crohn disease patients. Proc Natl Acad Sci U S A. 2008; 105: 16731-6.
2. Lenoir M, Martin R, Torres-Maravilla E, et al. Butyrate mediates anti-inflammatory effects of Faecalibacterium prausnitzii in intestinal epithelial cells through Dact3. Gut Microbes. 2020; 12: 1-16.
3. Quevrain E, Maubert MA, Michon C, et al. Identification of an anti-inflammatory protein from Faecalibacterium prausnitzii, a commensal bacterium deficient in Crohn's disease. Gut. 2016; 65: 415-25.
4. Rossi O, van Berkel LA, Chain F, et al. Faecalibacterium prausnitzii A2-165 has a high capacity to induce IL-10 in human and murine dendritic cells and modulates T cell responses. Sci Rep. 2016; 6: 18507.
5. Sarrabayrouse G, Bossard C, Chauvin JM, et al. CD4CD8 lymphocytes, a novel human regulatory T cell subset induced by colonic bacteria and deficient in patients with inflammatory bowel disease. PLoS Biol. 2014; 12: e1001833.
6. Touch S, Godefroy E, Rolhion N, et al. Human CD4+CD8alpha+ Tregs induced by Faecalibacterium prausnitzii protect against intestinal inflammation. JCI Insight. 2022; 7.
7. https://www.biorxiv.org/content/10.1101/2024.10.06.616495v1

Disclosure

HS reports lecture fees, board membership, or consultancy from Carenity, AbbVie, Astellas, Danone, Ferring, Mayoly Spindler, MSD, Novartis, Roche, Tillots, Enterome, BiomX, Takeda, Biocodex, has stocks from Enterome and is co-founder of Exeliom Biosciences. PL report lecture fee, board membership, or consultancy from Biose, Biostime, Boiron, Bonduelle, BMS, Bromatech, IPSEN, iTaK, Lallemand, Lesaffre, L’Oréal, Mayoli, Merck, Procter and Gamble, Second Genome, Therascience and URGO and is co-founder of Exeliom Biosciences. Other authors declare no competing interests. DS, LH, PR and BH are employees of Exeliom Biosciences.