PMO-10 Survey on the use of artificial intelligence in IBD patients in the USA and UK
Bibliographic record
Abstract
<h3>Introduction</h3> Artificial intelligence (AI) is making rapid in-roads in various aspects of gastroenterology (GI). Early studies have shown potential for the use of AI in the diagnosis and management of inflammatory bowel disease (IBD). Our aim was to explore the current understanding of clinicians for the role of AI in GI and IBD in particular. <h3>Methods</h3> A 15-question survey was developed in consultation amongst the authors and distributed to members of the American College of Gastroenterology (ACG) & British Society of Gastroenterology (BSG) in May 2020. The questionnaire was approved by the ACG Research Committee and the BSG IBD Committee for the USA and the UK, respectively. Data was analysed using R software Version 3.5.2. <h3>Results</h3> A total of 249 members (USA-175, UK-74) responded. IBD surveillance colonoscopies were being performed by 84.7%. A total of 171 (68.7%) respondents were aware of the potential use of AI in GI. Specifically, 140 (81.9%) were aware of current use of AI for colonic polyp detection, 82 (47.9%) for Barrett’s surveillance, 72 (42.1%) for capsule endoscopy, 41 (24%) in early gastric cancer detection and 7 (4.1%) for IBD. Furthermore, 86.5% thought that AI could potentially improve IBD care in the future. The 3 most unmet needs in surveillance colonoscopy in patients with IBD were appropriate surveillance intervals (58.6%); accurate histopathology and dysplasia detection (57.4%); and yield from different biopsy protocols (51.4%). Suggested areas for use of AI in IBD were real time assessment and endoscopic scoring (73.1%), earlier detection of colorectal cancer (70.2%), facilitating ‘personalised’ care (50.9%) and distinguishing Crohn’s disease from ulcerative colitis at index colonoscopy (31.6%). Respondents projected that AI would be available in clinical practice for IBD soon; 13.4% in <1 year; 34.5% < 2 years and 52.1% < 5 years. The potential perceived barriers for use of AI in gastroenterology were cost (66.7%), uncertainty about technology (61.4%) and access to AI courses (47.3%). Respondents had concerns regarding patient safety with use of AI (26.3%) and concerns regarding patient confidentiality (39.8%). <h3>Conclusions</h3> There is a high level of awareness for AI in polyp detection but significantly less in IBD. Respondents felt that AI could improve endoscopic assessment in IBD, dysplasia surveillance and aid personalised care. Cost, unfamiliarity with AI technology and access to AI courses were perceived as likely barriers.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".