Abstract
Purpose of review
Artificial intelligence (AI) is quickly evolving and will be integral to the management of IBD patients. In this review, we provide an overview of technologies powering applications for Crohn’s disease and ulcerative colitis, with particular attention to information extraction from imaging and text records.
Recent findings
Recent data highlight machine learning capability to replicate expert interpretation and judgment at population scale with accuracy in endoscopic and histology disease grading. Computer vision techniques are also detecting important findings difficult for even expert clinicians to reliably appreciate, including dysplasia on colonoscopy and fibrosis on CT and MRI imaging. Further, segmentation and radiomics can extract more information than manually possible, enabling new possibilities for disease measurement. Finally, natural language processing (NLP) is showing promise automatically extracting IBD-related medical concepts from text and generating conversational responses for both clinicians and patients.
Summary
Quickly mounting evidence supports AI reliability grading disease severity in endoscopy, histology, and imaging. In particular use cases, AI can surpass the ability of humans for disease feature detecting and the generation of new measures of IBD activity. Ultimately, AI-powered information extraction will provide significant incremental improvement in the personalization predictions of outcomes and treatment course in IBD.
Similar content being viewed by others
References and Recommended Reading
Papers of particular interest, published recently, have been highlighted as: • Of importance •• Of major importance
Puylaert CAJ, et al. Comparison of MRI activity scoring systems and features for the terminal ileum in patients with Crohn disease. Am J Roentgenol. 2019;212:W25–31.
Lamash Y, Kurugol S, Warfield SK. Semi-automated extraction of Crohn’s disease MR imaging markers using a 3D residual CNN with distance prior. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support. 2018;11045:218–26.
Enchakalody BE. et al. Machine learning methods to predict presence of intestine damage in patients with Crohn’s disease. in Medical imaging 2020: computer-aided diagnosis vol. 11314 1131436 (Medical Imaging 2020: Computer-Aided Diagnosis, 2020).
• Stidham RW et al. Assessing small bowel stricturing and morphology in Crohn’s disease using semi-automated image analysis. Inflamm Bowel Dis 11, 274 (2019). Exemplar methodology for cross sectional imagine segmentation of enterography in Crohn’s disease. Demonstrates ability to automatically collect detailed bowel measurements related to Crohn’s disease severity and phenotype with similar accuracy as IBD-specialist radiologists.
Carter D et al. Automatized detection of Crohn’s disease in intestinal ultrasound using convolutional neural network. Inflamm. Bowel Dis. 2023;doi:10.1093/ibd/izad014.
Li X et al. Development and validation of a novel computed-tomography enterography radiomic approach for characterization of intestinal fibrosis in Crohn’s disease. Gastroenterology (2021) doi:https://doi.org/10.1053/j.gastro.2021.02.027.
Meng J et al. Intestinal fibrosis classification in patients with Crohn’s disease using CT enterography–based deep learning: comparisons with radiomics and radiologists. Eur Radiol (2022) doi:https://doi.org/10.1007/s00330-022-08842-z.
Rong, C. et al. CTE-based radiomics models can identify mucosal healing in patients with Crohn’s disease. Acad. Radiol. (2023) doi:https://doi.org/10.1016/j.acra.2023.04.022.
Ruiqing L et al. A novel radiomics model integrating luminal and mesenteric features to predict mucosal activity and surgery risk in Crohn’s disease patients: a multicenter study. Acad. Radiol. (2023) doi:https://doi.org/10.1016/j.acra.2023.03.023.
Yao J, et al. Computed tomography-based radiomics nomogram using machine learning for predicting 1-year surgical risk after diagnosis of Crohn’s disease. Méd Phys. 2023;50:3862–72.
Shen X, et al. Preoperative computed tomography enterography-based radiomics signature: a potential predictor of postoperative anastomotic recurrence in patients with Crohn’s disease. Eur J Radiol. 2023;162:110766.
Vashist NM, et al. Endoscopic scoring indices for evaluation of disease activity in ulcerative colitis. Cochrane Database Syst Rev. 2018;1:CD011450.
Stidham RW, et al. Performance of a deep learning model vs human reviewers in grading endoscopic disease severity of patients with ulcerative colitis. JAMA Netw Open. 2019;2:e193963.
Ozawa T et al. Novel computer-assisted diagnosis system for endoscopic disease activity in patients with ulcerative colitis. Gastrointest Endosc. 2019;89, 416-421.e1.
• Yao H et al. Fully automated endoscopic disease activity assessment in ulcerative colitis. Gastrointest Endosc. 2021;93, 728-736.e1. Application demonstrating automated AI analysis of full motion video in could provide similar endoscopic scoring compared to paired central reviewers in a Phase 2 randomized controlled clinical trial in UC.
•• Gottlieb K et al. Endoscopy and central reading in inflammatory bowel disease clinical trials: achievements, challenges and future developments. Gut 70, 418–426 (2021). Another demonstration of AI for accurate automated endoscopic scoring using both Mayo endoscopic score and UCEIS in the Phase 2 randomized controlled study of mirikizumab for ulcerative colitis. This group showed no significant difference between AI and central reviewers.
Moen S, Vuik FER, Kuipers EJ, Spaander MC. Artificial intelligence in colon capsule endoscopy—a systematic review. Diagnostics. 2022 https://doi.org/10.3390/diagnostics12081994
• Klang, E. et al. Automated detection of Crohn’s disease intestinal strictures on capsule endoscopy images using deep neural networks. J Crohns Colitis. 2020 doi:10.1093/ecco-jcc/jjaa234. Excellent study demonstrating ability to apply AI image classification to capsule endoscopy imaging. They reported high accuracy for detecting ulceration, bleeding, and suspcious lesions, accellerating review time. This work will aid in making capsule endosocpy feasible by reducing the labor needed for interpreation.
Barash Y, et al. Ulcer severity grading in video capsule images of patients with Crohn’s disease: an ordinal neural network solution. Gastrointest Endosc. 2021;93:187–92.
Kratter T, et al. Deep learning multi-domain model provides accurate detection and grading of mucosal ulcers in different capsule endoscopy types. Diagnostics. 2022;12:2490.
Brodersen JB et al. Artificial intelligence-assisted analysis of pan-enteric capsule endoscopy in patients with suspected Crohn’s disease. A study on diagnostic performance. J. Crohn’s Colitis 2023 doi:https://doi.org/10.1093/ecco-jcc/jjad131.
Polat G et al. Improving the computer-aided estimation of ulcerative colitis severity according to mayo endoscopic score by using regression-based deep learning. Inflamm Bowel Dis. 2022 doi:https://doi.org/10.1093/ibd/izac226.
Higuchi N, et al. Automated evaluation of colon capsule endoscopic severity of ulcerative colitis using ResNet50. PLoS One. 2022;17:e0269728.
Chierici M et al. Automatically detecting Crohn’s disease and ulcerative colitis from endoscopic imaging. BMC Méd Inform Decis Mak. 2022;22, 300.
Guimarães P, et al. Artificial-intelligence-based decision support tools for the differential diagnosis of colitis. Eur J Clin Investig. 2023;53:e13960.
Kellerman R, et al. Spatiotemporal analysis of small bowel capsule endoscopy videos for outcomes prediction in Crohn’s disease. Ther Adv Gastroenterol. 2023;16:17562848231172556.
• Maeda, Y. et al. Evaluation in real-time use of artificial intelligence during colonoscopy to predict relapse of ulcerative colitis: a prospective study. Gastrointest Endosc. 2022;95, 747-756.e2. Study highlights the potential for automated endoscopic video analysis to predict patient outcomes in real time at the point of care. Machine prediction significantly separated those patients more likely to undergo clinical flare compared to remaining in remission over a 12 month period.
•• Iacucci, M. et al. Artificial intelligence enabled histological prediction of remission or activity and clinical outcomes in ulcerative colitis. Gastroenterology 2023;164, 1180-1188.e2. Landmark study detailing histologic image segmentation for ulcerative colitis. Show that automated detection and localization of neutrophils and other histologic features is possible. Further, automatically extract histologic information was used to power a prediction score significantly correlating with future clinical relapse in UC.
Pai RK, et al. The emerging role of histologic disease activity assessment in ulcerative colitis. Gastrointest Endosc. 2018;88:887–98.
Ohara J, et al. Deep learning-based automated quantification of goblet cell mucus using histological images as a predictor of clinical relapse of ulcerative colitis with endoscopic remission. J Gastroenterol. 2022;57:962–70.
Barkin JA, Sussman DA, Abreu MT. Chromoendoscopy and advanced imaging technologies for surveillance of patients with IBD. Gastroenterol Hepatol (N Y) 2012; 8, 796–802.
Bessissow T, Bisschops R. Advanced endoscopic imaging for dysplasia surveillance in ulcerative colitis. Expert Rev Gastroenterol Hepatol. 2013;7:57–67.
• Vitali F et al. Endocytoscopy for assessing histologic inflammation in ulcerative colitis: development and prospective validation of the ELECT (ErLangen Endocytoscopy in ColiTis) score (with videos). Gastrointest Endosc 2023;97, 100-111.e1. Study highlighting ability of AI image recognition systems for automatically interpreting endocytoscopy. Excellent example of useful applied AI, removing the for clinician’s to learn interpretation of this tedious and challenging modality.
Graham S et al. CoNIC: colon nuclei identification and counting challenge 2022. arXiv (2021) doi:10.48550/arxiv.2111.14485.
Remedios LW et al. Predicting Crohn’s disease severity in the colon using mixed cell nucleus density from pseudo labels. Méd Imaging 2023: Digit Comput Pathol. 2023;12471, 1247116-1247116–8.
Sninsky JA, Shore BM, Lupu GV, Crockett SD. Risk factors for colorectal polyps and cancer. Gastrointest Endosc Clin North Am. 2022;32:195–213.
Din S et al. Mutational analysis identifies therapeutic biomarkers in inflammatory bowel disease-associated colorectal cancers. Clin Cancer Res. 2018;24, clincanres.3713.2017.
Porter RJ, Din S, Bankhead P, Oniscu A, Arends MJ. QuPath algorithm accurately identifies MLH1-deficient inflammatory bowel disease-associated colorectal cancers in a tissue microarray. Diagnostics. 2023;13:1890.
Masanz J et al. Open source clinical NLP - more than any single system. AMIA Jt Summits Transl Sci Proc 2014;2014, 76–82.
Soysal E, et al. CLAMP - a toolkit for efficiently building customized clinical natural language processing pipelines. J Am Med Inform Assoc. 2018;25:331–6.
Ananthakrishnan AN, et al. Improving case definition of Crohn’s disease and ulcerative colitis in electronic medical records using natural language processing: a novel informatics approach. Inflamm Bowel Dis. 2013;19:1411–20.
• Stidham RW et al. Identifying the presence, activity, and status of extraintestinal manifestations of inflammatory bowel disease using natural language processing of clinical notes. Inflamm Bowel Dis. 2022;29, 503–510. Demonstration of applying NLP for extracting detailed information from clinical office notes. Here, this group designed an NLP pipeline for collecting EIM information from electronic medical records. While restricted to a very specific type of information relevant to the IBD clinician, this work shows the potential of NLP to automatically review charts and organize information in text reports.
Gomollón F, et al. Clinical characteristics and prognostic factors for Crohn’s disease relapses using natural language processing and machine learning: a pilot study. Eur J Gastroenterol Hepatol. 2022;34:389–97.
Kurowski JA, et al. Differences in biologic utilization and surgery rates in pediatric and adult Crohn’s disease: results from a large electronic medical record-derived cohort. Inflamm Bowel Dis. 2020; https://doi.org/10.1093/ibd/izaa239.
Coulson N. Patterns of engagement with inflammatory bowel disease online support groups. Gastroenterol Nurs. 2015;38:348–53.
Ricci L, et al. Web-based and machine learning approaches for identification of patient-reported outcomes in inflammatory bowel disease. Dig Liver Dis. 2022;54:483–9.
Grow HM, McPhillips HA, Batra M. Understanding physician burnout. Curr Probl Pediatr Adolesc Heal Care. 2019;49:100656.
Funding
RWS is supported by the National Institute of Health NIDDK (R01DK124779).
Author information
Authors and Affiliations
Contributions
MS performed literature search and drafted manuscript. RS revised the manuscript.
Corresponding author
Ethics declarations
Conflict of Interest
Molly Stone declares that she has no conflict of interest. Ryan Stidham declares that he has no conflict of interest. RWS has served as a consultant or on advisory boards for AbbVie, Bristol Myers Squibb, Janssen, Takeda, Gilead, Eli Lilly, Exact Sciences, and CorEvitas and holds intellectual property on cross-sectional imaging and endoscopic analysis technologies licensed by the University of Michigan to AMI, llc, EIQ, llc, and PathwaysGI, Inc.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Stone, M.L., Stidham, R.W. Artificial Intelligence in IBD: How Will It Change Patient Management?. Curr Treat Options Gastro 21, 365–377 (2023). https://doi.org/10.1007/s11938-023-00437-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11938-023-00437-x