Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease
Open accessThe DOI matches its Crossref record; 124 of the 124 references it cites were found in a registry or an index; 19 of the 125 sources its claims cite were checked for support.
Abstract
Integrating artificial intelligence into inflammatory bowel disease (IBD) has the potential to revolutionise clinical practice and research. Artificial intelligence harnesses advanced algorithms to deliver accurate assessments of IBD endoscopy and histology, offering precise evaluations of disease activity, standardised scoring, and outcome prediction. Furthermore, artificial intelligence offers the potential for a holistic endo-histo-omics approach by interlacing and harmonising endoscopy, histology, and omics data towards precision medicine. The emerging applications of artificial intelligence could pave the way for personalised medicine in IBD, offering patient stratification for the most beneficial therapy with minimal risk. Although artificial intelligence holds promise, challenges remain, including data quality, standardisation, reproducibility, scarcity of randomised controlled trials, clinical implementation, ethical concerns, legal liability, and regulatory issues. The development of standardised guidelines and interdisciplinary collaboration, including policy makers and regulatory agencies, is crucial for addressing these challenges and advancing artificial intelligence in IBD clinical practice and trials.
Overview
CoChat Summary
TL;DR
This review argues that AI can standardize and improve IBD endoscopy and histology assessment and, when fused with OMICs, enable an “Endo-Histo-OMICs” precision-medicine approach. It also emphasizes unresolved challenges in data quality, reproducibility, explainability, bias, privacy, and regulation.
Key findings
- In IBD endoscopy, a meta-analysis of 12 studies found CNN-based deep learning for UC severity had pooled accuracy 91.5%, sensitivity 82.8%, and specificity 92.4%; UCEIS outperformed MES for sensitivity (94% vs 82%) and positive predictive value (94% vs 84%). AI-PICaSSO was associated with adverse outcomes (HR 4.05) similarly to human endoscopists (HR 4.59), and EndoBRAIN-UC predicted 12-month clinical relapse in 28.4% of the AI-active group vs 4.9% in the AI-healing group (p<0.001).
- For advanced and capsule endoscopy, a CNN using VCE/PICaSSO detected endoscopic remission better than WLE/UCEIS (sensitivity 79% vs 72%; specificity 95% vs 87%; AUROC 0.94 vs 0.85). AI-assisted pan-enteric capsule endoscopy reduced images for review from 2,965,900 to 86,129 (97.1% reduction), with pooled median review time 3.2 min per patient and observer sensitivity/specificity of 96%/93% and 92%/90%.
- In histology, a PHRI-based deep learning strategy analyzed 614 digitized biopsies from 302 UC patients and predicted histological remission with 80% accuracy in validation and 79% in testing. Other models predicted NHI score with k=0.91 and ⍴=0.89 and histological remission with accuracy 0.97; a CD model using 550 surgical slides predicted postoperative recurrence with AUROC 0.995; and AI-modelled GHAS/Geboes matched central reading with accuracies of 80–89% for GHAS in colon, 65–82% in ileum, and 65–85% for Geboes.
- In the “Endo-Omics” exploratory study of 29 IBD patients, in-vivo pCLE features predicted response to infliximab/vedolizumab with 85% accuracy in UC and 80% in CD; ex-vivo fluorescent biologic binding predicted response with AUROC 83%, accuracy 77%, PPV 89%, and NPV 50%, and a differentially expressed gene panel showed AUROC >0.7 for anti-TNF response.
Methods
- Narrative review; references were identified in December 2023 through PubMed searches using terms including “Inflammatory Bowel Disease,” “Ulcerative Colitis,” “Crohn’s Disease,” “Endoscopy,” “Advanced imaging,” “Endocytoscope,” “Confocal laser endomicroscopy,” “Histology,” “OMICs,” “RNA Transcriptomics,” “Microbiome,” “Precision Medicine,” “Machine Learning,” “Deep Learning,” and “Artificial Intelligence,” for all articles since database inception.
- Additional articles were identified from reference lists of pivotal review articles, and the final reference list was generated based on originality and relevance to the broad scope of the review.
- No primary patient data or new experimental analysis were generated; the paper synthesizes published studies and presents overview tables and conceptual figures.
Limitations
- Stated by the paper: challenges include data quality, standardization, reproducibility, clinical implementation, ethical concerns, legal liability, and regulatory issues; meta-analyses showed moderate-to-high heterogeneity; AI data in CD histology remain limited; external validation in large, diverse cohorts is needed; human-centric and methodology-centric biases persist; and AI-specific regulatory frameworks are lacking.
- Evident from the text: this is a narrative review rather than a systematic review, with a search limited to December 2023 PubMed plus selected reference lists and no formal risk-of-bias or quality appraisal; several cited studies are small or exploratory (e.g., 5 CD patients, 29 IBD patients), and some AI histology work reports incomplete diagnostic metrics (e.g., Peyrin-Biroulet and colleagues did not report specific diagnostic metrics).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
9 Valid · 5 Not valid · 82 Not checked · 23 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In addition, AI has demonstrated promising potential to predict therapy responses for IBD by combining computer-aided in-vivo and ex-vivo pCLE image analysis with genomic data, which has shown in an exploratory study the ability to predict the response to biological therapy.9”
§ 1. AI in IBD Endoscopy > 1.2 AI-guided IBD Endoscopy Prediction of Response to Therapy and Outcomes
What the sources say
- Partly supportedcites [9] Iacucci, 2023, Computer-aided imaging analysis of probe-based confocal laser endomicroscopy with molecular labeling and gene expression identifies markers of response to biological therapy in IBD Patients: the endo-omics study, Inflamm Bowel Dis sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Pioneering studies have shown that an integrative approach can identify patient subgroups (phenomapping) for tailored disease management.”
§ 6. Precision "Endo-Histo-OMICs" Enabled by AI in IBD > 6.1 A New Era of "Endo-Histo-OMICs"
What the sources say
- Supportedcites [83] Sudhakar, 2021, Understanding the molecular drivers of disease heterogeneity in Crohn's disease using multi-omic data integration and network analysis, Inflamm Bowel Dis source
The Unsupervised Clustering section (p. 6) reports that the integrated analysis identified patient clusters aligned with distinct Crohn’s disease traits. The opening summary (p. 1) says the resulting molecular targets could support more individualized treatment of specific subtypes; it presents tailored management as a potential application, not an outcome already demonstrated. (LLM, conf=0.90)
- Not checked yetcites [84] Hensel, 2024, Classifying breast cancer subtypes on multi-omics data via sparse canonical correlation analysis and deep learning, BMC Bioinformatics
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“In vivo , endomicroscopy findings defined as vessel tortuosity, crypt morphology, and fluorescein leakage predicted response to therapy in UC and CD patients, with an accuracy of 85% and 80%, respectively.”
§ 6. Precision "Endo-Histo-OMICs" Enabled by AI in IBD > 6.1 A New Era of "Endo-Histo-OMICs"
What the sources say
- Supportedcites [9] Iacucci, 2023, Computer-aided imaging analysis of probe-based confocal laser endomicroscopy with molecular labeling and gene expression identifies markers of response to biological therapy in IBD Patients: the endo-omics study, Inflamm Bowel Dis source
The Abstract Results state that in vivo vessel tortuosity, crypt morphology, and fluorescein leakage predicted response in UC and CD, with accuracies of 85% and 80%, respectively. The In vivo pCLE analysis section reports the corresponding discriminants and accuracies. (LLM, conf=0.94)
plainstates an associationn = 29- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Additionally, AI-enabled accurate disease assessment and scoring can potentially lead to a reduction in the necessary sample size for clinical trials.26”
What the sources say
- Could not verifycites [26] Brodersen, 2024, Artificial intelligence-assisted analysis of pan-enteric capsule endoscopy in patients with suspected Crohn's disease. A study on diagnostic performance, J Crohns Colitis sourceExperimental — accuracy not yet measured
Our copy of Brodersen et al. (2024) is complete and covers AI-assisted pan-enteric CE review: diagnostic accuracy (Results), review-time/image-output reduction (Discussion and Accepted Manuscript), the need for manual review to calculate activity scores such as Lewis, Eliakim or SES-CD (Discussion), and future prospects of fully automated reading and outcome prediction (Accepted Manuscript). However, no passage states or implies that accurate AI disease assessment/scoring could reduce the sample size required for clinical trials; searches for 'sample size', 'power', 'clinical trial endpoints' and 'disease activity scoring in trials' returned only the study's own statistical analysis section and its enrollment in the diagnostic-accuracy trial NCT03134586. Nothing in our copy contradicts the claim either, and no alternative source is named for it, so the point cannot be checked against this paper. (LLM, conf=0.72)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“One of the primary advantages of the AI-aided fusion multimodal approach is the ability to identify and understand specific and interconnected biological alterations, enabling early and improved disease diagnosis and outcome.85”
§ 6. Precision "Endo-Histo-OMICs" Enabled by AI in IBD > 6.1 A New Era of "Endo-Histo-OMICs"
What the sources say
- Partly supportedcites [85] Sakurai, 2023, Positioning and usefulness of biomarkers in inflammatory bowel disease, Digestion sourceExperimental — accuracy not yet measured
The 'Positioning of Biomarkers in the Management of IBD' section describes biomarkers as useful for diagnosis and for predicting treatment response, prognosis, and recurrence; page numbers are unavailable in our copy. It does not establish that an AI-aided multimodal fusion approach identifies interconnected biological alterations or improves diagnosis and outcomes. Searches for AI-aided fusion and multimodal biomarkers found no passage supporting that central part of the claim. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
48 more claims · 1 with their cited sources checked
Create a free account to see all 119 claims and to verify the 106 references still open.
- It may state two separate claims as one. 51
- Probably not a substantial claim. 30
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 1. AI in IBD Endoscopy > 1.3 AI-guided IBD Endoscopy Dysplasia Detection
“95% sensitivity, 99% specificity”
§ 1. AI in IBD Endoscopy > 1.3 AI-guided IBD Endoscopy Dysplasia Detection
“0.85 AUC”
Citations
Cites
Artificial intelligence in healthcare: past, present and future
Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2017) · Stroke and Vascular Neurology · doi:10.1136/svn-2017-000101 · Cited by 4,837
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015
Artificial intelligence in radiology
Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. W. L. (2018) · Nature Reviews Cancer · doi:10.1038/s41568-018-0016-5 · Cited by 3,803
The Future of Digital Health with Federated Learning
Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B., Maier-Hein, K., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.08119 · Cited by 3,495
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Turner, D., Ricciuto, A., Lewis, A., D’Amico, F., Dhaliwal, J., Griffiths, A. M., Bettenworth, D., Sandborn, W. J., Sands, B. E., Reinisch, W., et al. (2021) · Gastroenterology · doi:10.1053/j.gastro.2020.12.031 · Cited by 2,911
Self-citationArtificial intelligence in medicine
Hamet, P., & Tremblay, J. (2017) · Metabolism · doi:10.1016/j.metabol.2017.01.011 · Cited by 2,334
Maaser, C., Sturm, A., Vavricka, S. R., Kucharzik, T., Fiorino, G., Annese, V., Calabrese, E., Baumgart, D. C., Bettenworth, D., Borralho Nunes, P., et al. (2019) · Journal of Crohn's and Colitis · doi:10.1093/ecco-jcc/jjy113 · Cited by 1,823
Artificial intelligence and deep learning in ophthalmology
Ting, D. S. W., Pasquale, L. R., Peng, L., Campbell, J. P., Lee, A. Y., Raman, R., Tan, G. S. W., Schmetterer, L., Keane, P. A., & Wong, T. Y. (2019) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2018-313173 · Cited by 1,554
Research works printed but not linked: 1
- Sun Y, Guo C, Li Y. ReAct: Out-of-distribution detection with rectified activations. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, eds. Advances in Neural Information Processing Systems, 34 (NeurIPS 2021), pp 1–13.
Cited by
Iacucci, M., Santacroce, G., Majumder, S., Morael, J., Zammarchi, I., Maeda, Y., Ryan, D., Sabatino, A. D., Rescigno, M., Aburto, M. R., et al. (2024) · Gut · doi:10.1136/gutjnl-2023-331579 · Cited by 114
“16 17 This narrative review comprehensively illustrates the latest cutting-edge evidence on the intestinal barrier and gut-brain axis in IBD, specifically providing the most recent and updated evidence on novel advanced technologies for cellular, molecular and ultrastructural barrier assessment.”
BackgroundSelf-citationCannarozzi, A. L., Latiano, A., Massimino, L., Bossa, F., Giuliani, F., Riva, M., Ungaro, F., Guerra, M., Brina, A. L. D., Biscaglia, G., et al. (2024) · United European Gastroenterology Journal · doi:10.1002/ueg2.12655 · Cited by 65
Self-citationArtificial intelligence to revolutionize IBD clinical trials: a comprehensive review
Sedaño, R., Solitano, V., Vuyyuru, S. K., Yuan, Y., Hanžel, J., Ma, C., Nardone, O. M., & Jairath, V. (2025) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848251321915 · Cited by 67
“97 Moreover, AI models offer the opportunity to identify a pio-neering gut barrier-protective agents for IBD and forecasts the potential success of candidate agents in phase III trials.”
Iacucci, M., Santacroce, G., Maeda, Y., & Ghosh, S. (2025) · Gastroenterology · doi:10.1053/j.gastro.2025.03.005 · Cited by 56
Self-citationA foundational architecture for AI agents in healthcare
Liu, F., Niu, Y., Zhang, Q., Wang, K., Dong, Z., Wong, I. N., Cheng, L., Li, T., Duan, L., Li, K., et al. (2025) · Cell Reports Medicine · doi:10.1016/j.xcrm.2025.102374 · Cited by 41
Metadata
- Authors
- Iacucci, M., Santacroce, G., Zammarchi, I., Maeda, Y., Del Amor, R., Meseguer, P., Kolawole, B. B., Chaudhari, U., Di Sabatino, A., Danese, S., Mori, Y., Grisan, E., Naranjo, V., & Ghosh, S.
- Affiliations
- University College Cork (IE)
- Universitat Politècnica de València (ES)
- London South Bank University (GB)
- Vita-Salute San Raffaele University (IT)
- University of Oslo (NO)
- Corresponding author
- Iacucci, Marietta
- ORCID
- Venue
- The Lancet Gastroenterology & Hepatology
- Publisher
- Elsevier BV
- Published
- 2024-08
- Volume
- 9
- Issue
- 8
- Pages
- 758-772
- ISSN
- 2468-1156 (ISSN-L)
- 2468-1253
- OpenAlex
- W4396936366
- Cited by
- 73
- References
- 117
- Citations by year
- 2026: 30 · 2025: 35 · 2024: 8
- FWCI
- 4.96
- Type
- journal article
- Language
- en
- Open access
- Licence
- cc-by
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Locations
- The Lancet. Gastroenterology & hepatology (publishedVersion)
- PubMed (publishedVersion)
- Research Open (London South Bank University) (acceptedVersion, cc-by)
- Topics
- Health Sciences › Medicine › Gastroenterology › Inflammatory Bowel Disease
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- artificial intelligence, inflammatory bowel disease, endoscopy, histology, precision medicine, disease activity assessment, endoscopic scoring, outcome prediction, patient stratification, personalized medicine, data quality, reproducibility, clinical implementation, regulatory challenges
- MeSH terms
- Artificial Intelligence, Humans, Inflammatory Bowel Diseases, Endoscopy, Gastrointestinal, Precision Medicine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease. https://app.cochat.ai/papers/10.1016/s2468-1253(24)00053-0
- The paper
- Iacucci, M., Santacroce, G., Zammarchi, I., Maeda, Y., Del Amor, R., Meseguer, P., Kolawole, B. B., Chaudhari, U., Di Sabatino, A., Danese, S., Mori, Y., Grisan, E., Naranjo, V., & Ghosh, S. (2024). Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease. The Lancet Gastroenterology & Hepatology. https://doi.org/10.1016/s2468-1253(24)00053-0
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.