{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:09:33Z","timestamp":1779098973799,"version":"3.51.4"},"reference-count":18,"publisher":"BMJ","issue":"6","funder":[{"name":"Somerset NHS Foundation Trust","award":["Somerset NHS Foundation Trust funded this work. Gr"],"award-info":[{"award-number":["Somerset NHS Foundation Trust funded this work. Gr"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Clin Pathol"],"accepted":{"date-parts":[[2026,3,21]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>To develop, deploy and evaluate artificial intelligence (AI) for triaging duodenal biopsies within a National Health Service (NHS) histopathology laboratory, with the aim of improving reporting turnaround times for clinically significant diagnoses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The pathway was developed in the UK in an NHS laboratory. Rule-based automation software was used to find all newly scanned duodenal biopsy slides. Those with case numbers ending in an odd number were exported for AI triage and if they had significant AI predicted abnormalities they were prioritised for reporting. The cases with even numbers followed the routine reporting pathway.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>313 cases (517 duodenal slides) were processed by the routine pathway, and 329 cases (533 duodenal slides) were processed by the AI triage pathway. AI processing took about 70\u2009s per slide. The AI classifier had a sensitivity and positive predictive value (PPV) as follows: normal small bowel: 99.6%, 95.7%; coeliac disease: 86.7%, 100%; gastric heterotopia: 84.6%, 95.7%; adenoma: 88.9%, 88.9%; adenocarcinoma: 50.0%, 100%. In the AI triage workstream coeliac disease, and non-neoplastic abnormalities as a group, were reported quicker than in the standard workstream (6\u2009days vs 10 days and 7\u2009days vs 10 days, respectively, both p&lt;0.005), but neoplastic lesions were not reported quicker. The cost of deployment and operation was reasonable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>An NHS histopathology laboratory successfully developed and implemented an AI-based triage system for duodenal biopsies, achieving high diagnostic accuracy and significantly improving turnaround times for coeliac disease and non-neoplastic abnormalities as a group. This study demonstrates the feasibility and clinical value of locally developed AI tools within routine diagnostic practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/jcp-2026-210658","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:20:40Z","timestamp":1776273640000},"page":"380-388","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["AI triage of duodenal biopsies improves workflow"],"prefix":"10.1136","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2799-5194","authenticated-orcid":false,"given":"Frederick George","family":"Mayall","sequence":"first","affiliation":[{"name":"Department of Cellular Pathology, Musgrove Park Hospital, Taunton, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Mayall","sequence":"additional","affiliation":[{"name":"Diagnostic Path Solutions Limited, Banbury, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Bodger","sequence":"additional","affiliation":[{"name":"Department of Cellular Pathology, Musgrove Park Hospital, Taunton, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry","family":"Mayall","sequence":"additional","affiliation":[{"name":"University Hospital of Wales, Cardiff, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"2026051802151970000_79.6.380.1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpi.2022.100151","article-title":"Multiple-instance-learning-based detection of coeliac disease in histological whole-slide images","volume":"13","author":"Denholm","year":"2022","journal-title":"J Pathol Inform"},{"key":"2026051802151970000_79.6.380.2","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2400738","article-title":"Machine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis","volume":"2","author":"Jaeckle","year":"2025","journal-title":"NEJM AI"},{"key":"2026051802151970000_79.6.380.3","doi-asserted-by":"crossref","DOI":"10.4103\/jpi.jpi_87_18","article-title":"Automated Detection of Celiac Disease on Duodenal Biopsy Slides: A Deep Learning Approach","volume":"10","author":"Wei","year":"2019","journal-title":"J Pathol Inform"},{"key":"2026051802151970000_79.6.380.4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpi.2022.100181","article-title":"Artificial intelligence-based triage of large bowel biopsies can improve workflow","volume":"14","author":"Mayall","year":"2023","journal-title":"J Pathol Inform"},{"key":"2026051802151970000_79.6.380.5","unstructured":"Fast.ai . Available: https:\/\/github.com\/Fastai\/Fastai [Accessed 15 Mar 2026]."},{"key":"2026051802151970000_79.6.380.6","unstructured":"He K , Zhang X , Ren S , et al . Deep residual learning for image recognition. arXiv 2015. doi:10.48550\/arXiv.1512.03385"},{"key":"2026051802151970000_79.6.380.7","doi-asserted-by":"crossref","unstructured":"Deng J , Dong W , Socher R , et al . ImageNet: a large-scale hierarchical image database. IEEE conference on computer vision and pattern recognition. IEEE; 2009","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2026051802151970000_79.6.380.8","unstructured":"Pyisyntax . Available: https:\/\/pypi.org\/project\/pyisyntax [Accessed 15 Mar 2026]."},{"key":"2026051802151970000_79.6.380.9","unstructured":"NumPy . Numpy.var - NumPy v2.3 manual. Available: https:\/\/numpy.org\/doc\/2.3\/reference\/generated\/numpy.var.html [Accessed 15 Mar 2026]."},{"key":"2026051802151970000_79.6.380.10","unstructured":"Flask . Available: https:\/\/flask.palletsprojects.com\/en\/stable\/api\/ [Accessed 15 Mar 2026]."},{"key":"2026051802151970000_79.6.380.11","unstructured":"NumPy . Numpy.memmap - NumPy v2.5.dev0 manual. Available: https:\/\/numpy.org\/doc\/2.5.dev0\/reference\/generated\/numpy.memmap.html [Accessed 15 Mar 2026]."},{"key":"2026051802151970000_79.6.380.12","doi-asserted-by":"crossref","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav Brain Sci"},{"key":"2026051802151970000_79.6.380.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1"},{"key":"2026051802151970000_79.6.380.14","doi-asserted-by":"crossref","unstructured":"P\u00fcttmann S , Borras Ferris L , Marini N , et al . Automated classification of celiac disease in histopathological images: a multi-scale approach. Proc SPIE Med Imaging; 2024:12927:129272D.","DOI":"10.1117\/12.3006669"},{"key":"2026051802151970000_79.6.380.15","doi-asserted-by":"crossref","unstructured":"Breen J , Allen K , Zucker K , et al . A comprehensive evaluation of histopathology foundation models for ovarian cancer subtype classification. Npj Precis Onc 2025;9. doi:10.1038\/s41698-025-00799-8","DOI":"10.1038\/s41698-025-00799-8"},{"key":"2026051802151970000_79.6.380.16","doi-asserted-by":"publisher","DOI":"10.1136\/jcp-2025-210320"},{"key":"2026051802151970000_79.6.380.17","doi-asserted-by":"crossref","first-page":"155034","DOI":"10.1016\/j.prp.2023.155034","article-title":"Machine learning and machine teaching in histopathology","volume":"253","author":"Stokes","year":"2024","journal-title":"Pathol Res Pract"},{"key":"2026051802151970000_79.6.380.18","unstructured":"Position statement from the Royal College of Pathologists (RCPATH) on digital pathology and Artificial Intelligence (AI). 2023. Available: https:\/\/www.rcpath.org\/static\/90e5e248-4ad3-4d61-8247223f9faffc80\/RCPath-AI-position-statement-2022.pdf [Accessed 15 Mar 2026]."}],"container-title":["Journal of Clinical Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/jcp-2026-210658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T09:16:57Z","timestamp":1779095817000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcp.bmj.com\/lookup\/doi\/10.1136\/jcp-2026-210658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":18,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,5,18]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/jcp-2026-210658"],"URL":"https:\/\/doi.org\/10.1136\/jcp-2026-210658","relation":{},"ISSN":["0021-9746","1472-4146"],"issn-type":[{"value":"0021-9746","type":"print"},{"value":"1472-4146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]}}}