Introduction

Immune checkpoint inhibitors (ICIs), a new class of immunotherapeutic agents, are the first-line treatment for many advanced epithelial cancers. Gastrointestinal irAEs, particularly diarrhea and colitis, affect approximately 40% of ICI-treated patients and often lead to therapy discontinuation.¹ High-dose corticosteroids represent the first-line treatment, but about one-third of patients show inadequate response and require second-line immunosuppressants such as Infliximab or Vedolizumab.² As the body of evidence about the role of gut microbiota in the pathogenesis of GI irAE grows, fecal microbiota transplantation (FMT) is emerging as a potential treatment for steroid- and biologic-refractory ICI-induced colitis.³ Although data are still preliminary, FMT represents a promising therapeutic strategy in this setting.

Aims & Methods

The aim of this study is to evaluate the safety and efficacy of FMT in patients referred to our Microbiome clinic for steroid- and biologic-refractory ICI-induced colitis. After clinical evaluation, patients were treated with FMT via colonoscopy from healthy donors. FMT was performed as already described, following international clinical guidelines.^4,5 Following the endoscopic procedure, patients were evaluated at 1, 4, 8, and 12 weeks. We collected data on: patient characteristics, cancer type, cancer treatment and its suspension, severity of diarrhea before FMT (graded via CTCAE)⁶, time in weeks from initiation of cancer therapy to onset of diarrhea, grade of diarrhea following treatment and resumption of ICI.

Results

Our cohort included 7 patients with steroid- and biologic-refractory ICI-induced colitis (grade 1: n=0 ; grade 2: n=1 ; grade 3: 5=x; grade 4: n=1). Four patients were affected by renal cell carcinoma, 2 by melanoma, 1 by pulmonary cancer. All patients were treated with PD-1/PDL-1 inhibitors or CTLA-4 ( Nivolumab: n= 3; Nivolumab and Ipilimumab: n=2; Durvalumab: n= 1; Pembrolizumab: n= 1) and 6 patients interrupted ICI due to gastrointestinal irAEs. All patients received single FMT from healthy donors via colonoscopy. Following FMT, diarrhea improved to grade ≤ 1 in 6 patients (85%) at week 1, 4, 8, and 12 after the procedure, suggesting a sustained effect of microbiome modulation in the medium term. One patient died during follow-up for reasons other than ICI-colitis.

Conclusion

Our preliminary findings suggest that FMT may be a promising therapeutic strategy for refractory ICI-colitis. Further, larger and randomized studies are warranted to confirm our data.

References

1. Dougan M, Wang Y, Rubio-Tapia A, Lim JK. AGA Clinical Practice Update on Diagnosis and Management of Immune Checkpoint Inhibitor Colitis and Hepatitis: Expert Review. Gastroenterology. 2021;160(4):1384-1393. doi:10.1053/j.gastro.2020.08.063
2. Haanen J, Obeid M, Spain L, et al. Management of toxicities from immunotherapy: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up. Ann Oncol. 2022;33(12):1217-1238. doi:10.1016/j.annonc.2022.10.001
3. Wang Y, Wiesnoski DH, Helmink BA, et al. Fecal microbiota transplantation for refractory immune checkpoint inhibitor-associated colitis. Nat Med. 2018;24(12):1804-1808. doi:10.1038/s41591-018-0238-9
4. Cammarota G, Ianiro G, Kelly CR, et al. International consensus conference on stool banking for faecal microbiota transplantation in clinical practice. Gut. 2019;68(12):2111-2121. doi:10.1136/gutjnl-2019-319548
5. Ianiro G, Rossi E, Thomas AM, et al. Faecal microbiota transplantation for the treatment of diarrhoea induced by tyrosine-kinase inhibitors in patients with metastatic renal cell carcinoma. Nat Commun. 2020;11(1):4333. doi:10.1038/s41467-020-18127-y
6. Freites-Martinez A, Santana N, Arias-Santiago S, Viera A. Using the Common Terminology Criteria for Adverse Events (CTCAE - Version 5.0) to Evaluate the Severity of Adverse Events of Anticancer Therapies. Actas Dermosifiliogr. 2021;112(1):90-92. doi:10.1016/j.ad.2019.05.009

Disclosure

G.I. has received personal fees for acting as speaker for Biocodex, Danone, Sofar, Malesci, Metagenics and Tillotts Pharma, and for acting as consultant and/or advisor for Ferring Therapeutics, Giuliani, Malesci and Tillotts Pharma. A.G. reports personal fees for consultancy from Eisai Srl, 3PSolutions, Real Time Meeting, Fondazione Istituto Danone, SinergieSrl, Board MRGE and Sanofi SpA personal fees for acting as a speaker for Takeda SpA, AbbVie and Sandoz SpA and personal fees for acting on advisory boards for VSL3 and Eisai. G.C. has received personal fees for acting as advisor for Ferring Therapeutics. All other authors have no conflicts of interest to disclose.

Introduction

The cause of Crohn’s Disease (CD) remains unclear; however evidence suggests that dietary factors play a key role. With a rising incidence and no definitive cure, identifying modifiable risk factors is critical in preventing CD development. We aimed to study the association between fermentable dietary fibre intake and the future development of CD in an at-risk population.

Aims & Methods

Participants were recruited as part of the Crohn’s and Colitis Canada GEM study, a prospective cohort study of healthy first-degree relatives of patients with CD. At enrolment, a validated food frequency questionnaire was administered. Pectin, β-glucan, inulin, fructooligosaccharides (FOS), and arabinoxylan intake were quantified, and values energy-adjusted. Survival analysis was used to test the association between intake of fibre subtypes and risk of CD development. Generalized estimating equation tested the association between fibre intake and baseline impaired intestinal permeability (fractional urinary excretion of lactulose to mannitol ratio (LMR) >0.025); subclinical gut inflammation (faecal calprotectin (FCP) >250 μg/g); and faecal microbiome composition via 16s rRNA sequencing.

Results

76 of the 2,659 participants developed CD with a median follow-up of 8.9 years (IQR=5.7-12.3). Median age at recruitment was 17 years (IQR=12-25). 47% were male. Higher intake of inulin (HR = 0.78; 95% CI=0.61–0.99; p=0.04) and β-glucan (HR = 0.78; 95% CI=0.61–0.99; p=0.04) were associated with a reduced risk of CD development. No fibre subtype was associated with a higher risk of CD development. Lower intake of pectin, inulin, FOS and β-glucan was associated with impaired intestinal permeability (0.005<p<0.04). Lower inulin intake was associated with high FCP levels (p = 0.046). Higher pectin intake was associated with increased alpha diversity of faecal microbiome (p = 0.028). Higher inulin, FOS and pectin intake was associated with a shift in microbial taxa previously shown to be protective against CD onset in the GEM cohort; a reduction in Ruminococcus torques and an increase in NK4A214 group (phylum Firmicutes) presence (3.25×10⁻¹⁰<q<0.04).

Conclusion

This study demonstrates that dietary intake of fermentable fibre subtypes is associated with a reduced risk of CD development as well as with pleiotropic changes in CD risk biomarkers including microbiome, intestinal permeability, and subclinical inflammation. This suggests that the potential benefit of fermentable fibres on CD risk may involve changes in barrier function, and microbiome composition and function. Targeted interventions based on these findings could prove effective in preventing the onset of CD.

Introduction

Risankizumab (RZB) is a highly specific humanized monoclonal antibody that targets the p19 subunit of interleukin-23 and was designed to have low immunogenicity and high bioavailability, allowing for less-frequent dosing, although the clinical implications of these modifications have not been studied. The FORTIFY maintenance open label extension (OLE) is an ongoing phase 3 substudy evaluating the long-term efficacy and safety of RZB in pts with moderate to severe Crohn’s disease (CD). Here, we report interim efficacy and safety results from the FORTIFY OLE following up to 4 years (yrs) of RZB treatment.

Aims & Methods

The FORTIFY (NCT03105102) OLE enrolled pts who completed 52 weeks (wks) of RZB maintenance.^1,2 Pts received subcutaneous (SC) RZB 180mg every 8wks (Q8w) starting at wk56, except for pts who received rescue therapy prior to or during the OLE; these pts received SC RZB 360mg Q8w (see Table footnote for rescue therapy details). Pooled data (180mg+360mg) were analyzed through wk144 of the OLE (wk200 of cumulative RZB treatment) using as observed (AO) and modified nonresponder imputation (mNRI, pts were considered nonresponders for visits after premature discontinuation of RZB due to the primary reason of lack of efficacy or adverse event limited to Crohn’s disease only, as well as initiation of rescue, while other missing data were handled by multiple imputation [MI]) methods (‘All Patients [No Rescue or Prior to Rescue]’ group in Table). For pts who received rescue therapy, only their data obtained prior to receiving rescue were included in the aforementioned AO and mNRI analyses (‘All Patients [No Rescue]’ group in Table). Data from pts on the day of or after rescue were analyzed separately and reported AO starting at the initiation of rescue (defined as the last nonmissing value prior to or on initiation of rescue) and every 24 wks post-rescue (‘Rescue’ group in Table). Safety was evaluated in all pts receiving any RZB treatment in the OLE. Treatment-emergent adverse events (TEAEs) reported on/after the first dose in the OLE were summarized (cutoff date: 30DEC2024).

Results

A total of 1112 pts (excluding 36 pts who received RZB rescue at entry to OLE) received ≥1 dose of RZB 180mg or 360mg in the OLE. Efficacy rates (per mNRI analysis) were stable from OLE wk0 to wk144 for clinical remission per stool frequency/abdominal pain score (SF/APS, 64.5% to 75.8%) and per CD Activity Index (CDAI, 68.6% to 82.8%), endoscopic response (55.1% to 73.8%), and endoscopic remission (39.0% to 58.8%) (Table). Pts who received rescue therapy in the OLE demonstrated clinical and endoscopic improvements over time. The profiles of TEAEs and AEs of special interest were consistent with the known safety profile of RZB.^3,4
​

Conclusion

Durable clinical and endoscopic efficacy was observed in pts with moderate to severe CD who completed up to 4 yrs of RZB maintenance therapy in the FORTIFY OLE. Pts who received rescue therapy in the OLE also showed clinical and endoscopic improvements by wk144. No new safety risks for RZB were identified, supporting its long-term use in treating CD.

References

1. Ferrante M, et al. J Crohns Colitis. 2021;15(12):2001-2010.
2. Ferrante M, et al. Lancet. 2022; 399(10340):2031–46.
3. Papp KA, et al. J. Am. Acad. Dermatol. 2023; 89(6):1149–58.
4. Ferrante M, et al. J Crohns Colitis. 2024;18(Supplement_1):i168–70.

Disclosure

Marc Ferrante
Research grants from AbbVie, EG Pharma, Janssen, Pfizer, Takeda and Viatris. Consultancy fees from AbbVie, AgomAb Therapeutics, Boehringer Ingelheim, Celgene, Celltrion, Eli Lilly, Janssen-Cilag, MRM Health, Merck Sharp and Dohme, Pfizer, Takeda and ThermoFisher. Speakers’ fees from AbbVie, Biogen, Boehringer Ingelheim, Dr Falk Pharma, Ferring, Janssen-Cilag, Merck Sharp and Dohme, Pfizer, Takeda, Truvion Healthcare and Viatris
Remo Panaccione
Consulting fees from AbbVie, Abbott, Alimentiv, Amgen, Arena, AstraZeneca, Bristol Myers Squibb, Boehringer Ingelheim, Celgene, Celltrion, Cosmos Pharmaceuticals, Eisai, Elan, Ferring, Galapagos, Genentech, Gilead Sciences, GlaxoSmithKline, Janssen, Lilly, Merck, Mylan, Oppilan Pharma, Pandion Pharma, Pfizer, Progenity, Protagonist Therapeutics, Roche, Sandoz, Satisfai Health, Schering-Plough, Shire, Sublimity Therapeutics, Theravance, UCB, and Takeda; speaker fees from AbbVie, Arena, Celgene, Ferring, Gilead Sciences, Janssen, Lilly, Merck, Pfizer, Roche, Sandoz, Shire, and Takeda; and research/educational support from AbbVie, Ferring, Janssen, Pfizer, and Takeda. He has served on an advisory board for AbbVie, Amgen, Arena, Bristol Myers Squibb, Celgene, Celltrion, Ferring, Galapagos, Genentech, Gilead Sciences, GlaxoSmithKline, Janssen, Lilly, Merck, Mylan, Oppilan Pharma, Pandion Pharma, Pfizer, Sandoz, Shire, Sublimity Therapeutics, Takeda, and Theravance
Jean-Frederic Colombel
Research grants from AbbVie, Janssen Pharmaceuticals, and Takeda; payment for lectures from AbbVie, Allergan, Amgen, Ferring Pharmaceuticals, Shire, and Takeda; consulting fees from AbbVie, Amgen, Arena Pharmaceuticals, Boehringer Ingelheim, Bristol Myers Squibb, Celgene Corporation, Ferring Pharmaceuticals, Galmed Research, Genentech, GlaxoSmithKline, Imedex, Immunic, Iterative Scopes, Janssen Pharmaceuticals, Kaleido Biosciences, Lilly, Merck, Microbia, Novartis, PBM Capital, Pfizer, Protagonist Therapeutics, Sanofi, Takeda, TiGenix, and Vifor; and holds stock options in Intestinal Biotech Development.
Marla Dubinsky
Consulting fees from AbbVie, Arena, Bristol Myers Squibb, Celgene, Eli Lilly, Genentech, Gilead, Janssen, Pfizer, Prometheus Labs, and Takeda; and is founder and a shareholder of Trellus Health
Tadakazu Hisamatsu
Grant support from AbbVie, Daiichi-Sankyo, EA Pharma Co, Ltd. JIMRO, Mitsubishi Tanabe Pharma Corporation, Mochida Pharmaceutical Co., Ltd., Nippon Kayaku Co., Ltd., Pfizer Inc., Takeda Pharmaceutical Co., Ltd. Consulting fees from EA Pharma Co, Ltd., Janssen Research & Development, LLC., Gilead Sciences, Eli Lilly, Bristol Myers Squibb. Lecture fees from AbbVie, EA Pharma Co, Ltd, Mitsubishi Tanabe Pharma Corporation, Takeda Pharmaceutical Co., Ltd., Mochida Pharmaceutical Co., Ltd., Kissei Pharmaceutical Co, Ltd.
James O. Lindsay
Consultant and an advisory board participant for AbbVie, Atlantic Healthcare, Bristol Myers Squibb, Celgene, Celltrion, Eli Lilly, Ferring Pharmaceuticals, Galapagos, Gilead, GSK, Janssen, MSD, Napp, Pfizer, Shire, Takeda, and Vifor Pharma; has received speaker fees and sponsorship for academic meetings from AbbVie, Ferring Pharmaceuticals, Janssen, MSD, Napp, Norgine, Pfizer, Shire, Tillotts Pharma, and Takeda; and has received investigator-led research grants from AbbVie, Gilead, Pfizer, Shire and Takeda.
Geert D’Haens
Consultant for AbbVie, AgomAb, AstraZeneca, AM Pharma, AMT, Bristol Myers Squibb, Boehringer Ingelheim, Celltrion, Eli Lilly, Exeliom Biosciences, Exo Biologics, Galapagos, Index Pharmaceuticals,, GSK, Pfizer, Immunic, J&J, Origo, Polpharma, Procise Diagnostics, Prometheus Laboratories, Prometheus Biosciences, Progenity, Protagonist and Ventyx; and has received speakers bureau fees from AbbVie, Arena Pharmaceuticals, Galapagos, Gilead, Pfizer, Bristol Myers Squibb, and Takeda

Alexandra Song, Yi Yao, Yang Yang, Javier Zambrano, Fernando Aponte, and W. Rachel Duan are full-time employees of AbbVie and may own AbbVie stock or options.

Funding
AbbVie funded this study and participated in the study design, research, analysis, data collection, interpretation of data, reviewing, and approval of the abstract. All authors had access to relevant data and participated in the drafting, review, and approval of this abstract. No honoraria or payments were made for authorship. AbbVie and authors thank all the trial investigators and the patients who participated in this clinical trial.
Medical writing support was provided by Stephanie Parsons, PhD, an employee of AbbVie.

Introduction

Guselkumab (GUS) is a dual-acting IL-23p19 subunit inhibitor that potently neutralizes IL-23 and binds to CD64, a receptor on cells that produce IL-23. In the QUASAR studies, GUS intravenous (IV) induction and subcutaneous (SC) maintenance demonstrated symptomatic, endoscopic, and histologic efficacy through 2 years.^1,2 Here, we describe maintenance of endoscopic and histologic efficacy in the long-term extension (LTE).

Aims & Methods

At maintenance week (W) 0, GUS IV induction responders were randomized 1:1:1 to GUS 100 mg SC every 8 weeks (q8w), GUS 200 mg SC q4w or placebo (GUS withdrawal). Participants (pts) completing the W44 visit could enter the LTE and continue the treatment regimen they were receiving at W44. Placebo pts discontinued after study unblinding. Efficacy data for randomized pts who continued to receive their GUS regimen assigned at W0 in the LTE were analyzed using 2 methods: 1) nonresponder imputation (NRI) accounting for pts with treatment failure or missing data, and 2) “as observed.”

Results

Overall, 303 randomized pts (155 for 100 mg q8w and 148 for 200 mg q4w) continued their GUS treatment assigned at W0 in the LTE. Of pts who achieved endoscopic improvement at W44, 87.2% of GUS 100 mg q8w pts and 80.2% GUS 200 mg q4w pts maintained endoscopic improvement through W92 (NRI analysis; Table). Of pts who achieved histologic improvement at W44, 77.9% and 75.2%, respectively, maintained histologic improvement at W92. Of pts who achieved histo-endoscopic mucosal improvement (HEMI) at W44, 73.5% and 75.5%, respectively, maintained HEMI through W92. Of pts who were in histologic remission at W44, 71.2% maintained histologic remission at W92 in both GUS groups. Results of the as-observed analysis were consistent with the NRI analysis; the dropout rate was low among GUS-treated pts in the LTE. Proportions of pts who maintained endoscopic and histologic outcomes from W0 to W92 are presented in the Table.

Conclusion

High rates of long-term sustained endoscopic and histologic endpoints were observed at W92 of the LTE with both GUS dose regimens.

References

1. Rubin DT, et al. Guselkumab in patients with moderately to severely active ulcerative colitis (QUASAR): phase 3 double-blind, randomised, placebo-controlled induction and maintenance studies. Lancet. 2025;405(10472):33-49.
2. Lichtenstein GR, et al. Efficacy and safety of guselkumab for ulcerative colitis through week 92 of the QUASAR long-term extension study. Presented at: Digestive Disease Week (DDW); May 4–6, 2025; San Diego, CA.

Disclosure

Study support: Johnson & Johnson.
TH: AbbVie, Bristol Myers Squibb, Daiichi-Sankyo, EA Pharma Co, Ltd., JIMRO, Eli Lilly, Gilead Sciences, Johnson & Johnson, Kissei Pharmaceutical Co, Ltd., Mitsubishi Tanabe Pharma Corporation, Mochida Pharmaceutical Co., Ltd., Nippon Kayaku Co., Ltd., Pfizer Inc, Takeda Pharmaceutical Co., Ltd.
JP: AbbVie, Alimentiv, Athos, Atomwise, Boehringer Ingelheim, Celsius, Ferring, Galapagos, Genentech/Roche, GlaxoSmithKline, Johnson & Johnson, Mirum, Nimbus, Pfizer, Progenity, Prometheus, Protagonist, Revolo, Sanofi, Sorriso, Surrozen, Takeda, Wasserman.
FM: AbbVie, Arena, Celltrion, Eli Lilly and Company, Ferring, Fresenius, Galapagos, GlaxoSmithKline, Johnson & Johnson, Merck, Pfizer, Prometheus Biosciences, Roche, Sandoz, Tillots, Takeda, Teva.
GRL: AbbVie, American College of Gastroenterology, CellCeutrix, Celgene, Clinical Advances in Gastroenterology, Ferring, Gastroenterology and Hepatology [Gastro-Hep Communications], Gilead, Johnson & Johnson, Orthobiotech, Eli Lilly, Luitpold / American Regent, Merck, McMahon Publishing, Pfizer, Prometheus, Romark, Salix/ Valeant, Shire, SLACK, Springer, Takeda, UCB, Up-To-Date, Vindico, Virgo.
JRA: Abbvie, Bristol Myer Squibb, Ferring, Finch, Iterative Scopes, Johnson & Johnson, Merck, Pfizer, Roivant, Seres Therapeutics, Roivant Adiso.
BB: AbbVie, Alimentiv, Allergan, Amgen, AMT, Bausch Health, Bristol Myers Squibb, Business Intelligence, Celgene, Celltrion, Eupraxia Fresenius Kabi, Ferring, Genentech/Roche, Gilead, Iterative Scopes, GlaxoSmithKline, Jamp, Johnson & Johnson, Merck, Microbiome Insights, Mylan, Novartis, Organon, Pendopharm, Pfizer, Protagonist, Qu Biologic, Sandoz, Takeda, Viatris.
WA: AbbVie, Amgen, BMS, Dynacare, Eli-Lilly, Johnson & Johnson, Merck, Novartis, Pfizer, Prometheus, Sandoz, Sanofi, Takeda, Theradiag.
MAS: AbbVie, Bristol-Myers Squibb, Falk, Galapagos, Janssen, Lilly, MSD, Pfizer, Samsung Bioepis, Sandoz, Sanofi, STADA, Takeda, Tillotts.
BDY: AbbVie Korea, BMS Pharmaceutical Korea Ltd., Celltrion, Chong Kun Dang Pharm, CJ Red BIO, Cornerstones Health, Curacle, Daewoong Pharm, Dong-A ST, Eisai Korea, Eli Lilly and Company Korea, Ferring Korea, Imscout, IQVIA, Johnson & Johnson, Johnson & Johnson Korea, JEIL PHARMACEUTICAL CO., Kangstem Biotech, Korea Otsuka Pharm, Korea United Pharm, Medtronic Korea, NanoEntek, ORGANOIDSCIENCES LTD, Pfizer Korea, Samsung Bioepis, Takeda, Takeda Korea, Yuhan.
SY, MG, NS, DP, YM, HZ: Johnson & Johnson.
AD: Abivax, AbbVie, Amgen, Arena Pharmaceuticals, Biogen, Boehringer Ingelheim, Bristol Myers Squibb, CED Service GmbH, Celltrion, Dr Falk Foundation, Ferring Pharmaceuticals, Fresenius Kabi, Galapagos, Gilead, High5MD, Johnson & Johnson, Lilly, Materia Prima, MedToday, MSD, Pfizer, Pharmacosmos, Roche, Sandoz, Stada, Takeda, Thieme, Tillotts, UniMed Verlag, Vifor Pharma.
DTR: Abbvie, Altrubio, Apex, Avalo Therapeutics, Bristol-Myers Squibb, Buhlmann Diagnostics Corp, Celgene, Connect BioPharma, Intouch Group, Iterative Health, Johnson & Johnson, Lilly, Pfizer, Samsung Neurologica, Takeda.
BES: AbbVie, Abivax, Adiso Therapeutics, Agomab, Alimentiv, Amgen, AnaptysBio, Arena Pharmaceuticals, AstraZeneca, Biolojic Design, Biora Therapeutics, Boehringer Ingelheim, Boston Pharmaceuticals, Bristol Myers Squibb, Celltrion, Equillium, Enthera, Enveda Biosciences, Evommune, Ferring, Galapagos, Genentech (Roche), Gilead Sciences, GlaxoSmithKline, Gossamer Bio, Imhotex, Index Pharmaceuticals, Innovation Pharmaceuticals, Inotrem, Johnson & Johnson, Kaleido, Kallyope, Lilly, Merck, Microba, Mirador Therapeutics, Mobius Care, Morphic Therapeutics, MRM Health, Nexus Therapeutics, Nimbus Discovery, Odyssey Therapeutics, Pfizer, Progenity, Prometheus Biosciences, Prometheus Laboratories, Protagonist Therapeutics, Q32 Bio, Rasayana Therapeutics, Recludix Therapeutics, Reistone Biopharma, Sanofi, Sorriso Pharmaceuticals, Spyre Therapeutics, Sun Pharma, Surrozen, Takeda, Target RWE, Teva, TLL Pharmaceutical, Tr1X, Union Therapeutics, Ventyx Biosciences, and Vividion Therapeutics.

Introduction

The achievement of histological remission (HR) is a key treatment goal in ulcerative colitis (UC), as it is suggestive of better disease management and predicts response to therapy.
The absence of neutrophils in epithelium and lamina is crucial to define HR. However, the role of neutrophil number and localisation remains unclear. We aimed to develop a novel artificial intelligence (AI)-driven system to automate neutrophil detection, localisation, and quantification, supporting assessment of HR and enable the prediction of response to therapy.

Aims & Methods

We developed an AI-driven system by integrating two deep learning models to (1) segment whole slide images (WSIs) into epithelium, crypts and lamina propria and to (2) detect and quantify neutrophils. Outputs from these models were combined to compute neutrophil densities in the lamina propria, epithelium, and overall tissue. The optimal neutrophil density cut-offs to assess disease activity (Geboes score >2B.0) in UC patients were identified in the AMAC phase 2 Mirikizumab trial, and subsequently validated in the multicentre prospective PICaSSO cohort study. Cut-offs to determine treatment response at weeks 12 and 52 (histological improvement [HI; Geboes score ≤3.1] and histological remission [HR; Geboes score ≤2B.0]), were also evaluated.

Results

Table 1 shows the system diagnostic performance in assessing disease activity and predicting response to therapy at W12 and W52 in the Mirikizumab cohort.
303 WSIs from active UC patients from the multicentre, randomised, double-blind, parallel-arm, placebo-controlled phase 2 clinical trial of Mirikizumab were analysed. The model yielded a DICE SØrensen of 0.57 for segmentation, precision of 82.3% and recall of 77.0% for neutrophil detection. The system identified an overall optimal neutrophil density cut-off (cells/mm²) predictive of disease activity of >21.7.0 (>10.1 and >30.4 for epithelium and lamina propria, respectively), with an accuracy of 86% (85% and 85%, respectively). Further validation in the multicenter PICaSSO cohort yielded to similar results.
Moreover, the overall optimal cut-off to predict histological remission at W52 was <20.8 (<10.4 and <27.9 for epithelium and lamina propria, respectively), with an accuracy of 82.0% (81% and 80%, respectively).

Conclusion

Our novel AI-based system demonstrates strong potential as an automated tool to detect, localise, and quantify neutrophils to assess histological activity and predict response to therapy in a clinical trial UC cohort and real-world settings. This framework could be applied in clinical trials and routine clinical practice, offering objective guidance for personalised management in UC patients.

References

[1] Santacroce G, Meseguer P, Zammarchi I, et al. P406 A novel active learning-based digital pathology protocol annotation for histologic assessment in Ulcerative Colitis using PICaSSO Histologic Remission Index (PHRI). Journal of Crohn's and Colitis, Volume 18, Issue Supplement_1, January 2024, Pages i843–i844
[2] Graham S, Vu QD, Jahanifar M, et al. CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting. Med Image Anal. 2024;92:103047.

Disclosure

MI received research grants and consultant fees from Olympus, Pentax, Eli Lilly, and Janssen. All other authors declare no competing interests.