You are here

  • Home
  • Archive
  • Volume 14, Issue 3
  • The importance of high-quality ‘big data’ in the application of artificial intelligence in inflammatory bowel disease

Article Text

Article menu
Download PDFPDF
Education
Opinion
The importance of high-quality ‘big data’ in the application of artificial intelligence in inflammatory bowel disease
  1. James J Ashton1,2,
  2. Johanne Brooks-Warburton3,4,
  3. Patrick B Allen5,
  4. Tony C Tham5,
  5. Sami Hoque6,
  6. Nicholas A Kennedy7,8,
  7. Anjan Dhar9,10,
  8. Shaji Sebastian11,12
  9. On behalf of the British Society of Gastroenterology artificial intelligence in IBD special interest group
  1. 1 Department of Paediatric Gastroenterology, Southampton Children's Hospital, Southampton, UK
  2. 2 Human Genetics and Genomic Medicine, University of Southampton, Southampton, UK
  3. 3 Department of Clinical Pharmacology and Biological Sciences, University of Hertfordshire, Hatfield, UK
  4. 4 Gastroenterology Department, Lister Hospital, Stevenage, UK
  5. 5 Department of Gastroenterology, Ulster Hospital, Dundonald, Belfast, UK
  6. 6 Department of Gastroenterology, Barts Health NHS Trust, London, UK
  7. 7 Department of Gastroenterology, Royal Devon and Exeter NHS Foundation Trust, Exeter, UK
  8. 8 IBD Pharmacogenetics, University of Exeter, Exeter, UK
  9. 9 Department of Gastroenterology, County Durham & Darlington NHS Foundation Trust, Darlington, Co. Durham, UK
  10. 10 Teesside University, Middlesbrough, UK
  11. 11 Department of Gastroenterology, Hull University Teaching Hospitals NHS Trust, Hull, UK
  12. 12 Hull York Medical School, Hull, UK
  1. Correspondence to Dr James J Ashton, Paediatric Gastroenterology, Southampton University Hospitals NHS Trust, Southampton SO16 6YD, UK; j.ashton{at}soton.ac.uk

https://doi.org/10.1136/flgastro-2022-102342

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    The rise of artificial intelligence (AI) in healthcare provides an opportunity to improve clinical care and patient outcomes. Gastroenterology may be seen as a leader in the application of AI, through automatic image recognition and interpretation in endoscopy, and analysis of images gathered through video capsule endoscopy.1 Despite this, the clinical translation of AI into routine practice has lagged behind its application in research settings. Inflammatory bowel disease (IBD) presents specific clinical challenges for which AI may have solutions, including prediction of therapeutic response, novel subgroup classification, precise molecular diagnosis, complication risk stratification and endoscopic image analysis for scoring of severity of mucosal inflammation in both ulcerative colitis and Crohn’s disease.2 We are also moving to an era of big data in IBD research, with consortia collecting and collating large cohorts of patients with available genomic, and other multiomic, data.3 4 This resource presents an unrivalled opportunity to alter the landscape of disease prediction and classification in IBD, and usher in routine personalisation of diagnosis and treatment (figure 1). A key part of reliable, reproducible and applicable use of AI for patients, is the quality of the clinical phenotyping. Lack of in-depth clinical data, systemic bias in data entry, lack of longitudinal outcomes and missing data all pose huge challenges to application of AI, with algorithms reliant on high-quality data input to give high-quality output.5 While this constitutes a challenge, it also creates an opportunity to develop robust systems to gather prospective and retrospective data, in structured ways and to use routinely collected data for alternative purposes.

    Figure 1

    Potential applications of artificial intelligence and ‘big data’ to personalise management in inflammatory bowel disease. Created with BioRender.com.

    Within this opinion article, we focus on the use of AI to predict outcomes, response to therapy, complications and novel disease …

    View Full Text

    Footnotes

    • Twitter @James_Ashton, @johanne_brooks, @samiHoque2, @DrNickKennedy, @anjan_dhar6

    • Contributors JA conceived the article with SS and JB-W. JA wrote the article with help from all authors. All authors approved the final version of the manuscript prior to submission.

    • Funding JA is funded by an NIHR clinical lectureship.

    • Competing interests JB-W holds research grants from AbbVie, and has received speaker fees from Dr Falk Pharma. JA no COI to declare. AD Advisory and consultancy for Pfizer UK, Tillotts Pharma UK, Dr Falk Pharma, Pharmacosmos, Takeda UK, Honoraria and Speaker Fees from Dr Falk Pharma, Pfizer, Janssen, Tillotts Pharma, Pharmacosmos, Takeda UK. PBA received research grants from Pfizer and speaker fees from Takaeda, AbbVie, GSK, Janssen, MSD and Tillotts. TCT no COI to declare. SH no COI to declare. SS holds research grants from Biogen, Takeda, AbbVie, TillottsPharma, Ferring and Biohit; served on the advisory boards of Takeda,AbbVie, Merck, Ferring, Pharmacocosmos, Warner Chilcott, Janssen, Falk Pharma, Biohit, TriGenix, Celgene and Tillots Pharma; and has received speaker fees from AbbVie, Biogen, AbbVie, Janssen, Merck,Warner Chilcott and Falk Pharma. NAK has served as a speaker and/or advisory board member for AbbVie, Allergan, BMS, Falk, Ferring, Janssen, Mylan, Pharmacosmos, Pfizer, Sandoz, Takeda and Tillotts. He is the director of a company that handles central reading of endoscopy. His department has received research funding from AbbVie, Biogen, Celgene, Celtrion, Galapagos, MSD, Napp, Pfizer, Pharmacosmos, Roche and Takeda.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • © Author(s) (or their employer(s)) 2023. No commercial re-use. See rights and permissions. Published by BMJ.