[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121507-en":3,"doc-seo-121507-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121507,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis","Machine-learning methods enable automated diagnosis of coeliac disease (CD) from duodenal biopsy whole-slide images, addressing limited interpathologist agreement and heavy clinical workload. A model is trained with weak supervision using multiple-instance learning on 3,383 H&E-stained WSI scans from four hospitals and evaluated on 644 unseen scans from an independent NHS Trust. Results show accuracy, sensitivity, specificity above 95% and AUROC above 99%. Inter-observer agreement with four specialist pathologists on unseen data is statistically indistinguishable (>96%), with performance also generalizing across hospitals.","Edinburgh Research Explorer  \nMachine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis  \nCitation for published version:  \nJaekle, F, Denholm, J, Schreiber, B, Evans, SC, Wicks, MN, Chan, JYH, Bateman, AC, Natu, S, Arends, MJ & Soilleux, E 2025, 'Machine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis', NEJM AI. [https://doi.org/10.1056/AIoa2400738](https://doi.org/10.1056/AIoa2400738)  \nDigital Object Identifier (DOI):  \n10.1056/AIoa2400738  \nLink:  \nLink to publication record in Edinburgh Research Explorer  \nDocument Version:  \nPeer reviewed version  \nPublished In:  \nNEJM AI  \nGeneral rights  \nCopyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights.  \nTake down policy  \nThe University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 29. Nov. 2025  \nMachine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis  \nF. Jaeckle,1, 2, *,† J. Denholm,1, 2, 3, * B. Schreiber,1, 3, * S. C. Evans,1 M. N. Wicks,4  \nJ. Y. H. Chan,5 A. C. Bateman,6 S. Natu,7 M. J. Arends,4 and E. Soilleux1, 2  \n1Department of Pathology, University of Cambridge, Tennis Court Road, CB2 1QP, Cambridge, England, UK.  \n2Lyzeum Ltd, Cambridge, CB1 2LA, England, UK.  \n3Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Wilberforce Road, CB3 0WA, Cambridge, England, UK.  \n4Edinburgh Pathology & Centre for Comparative Pathology, Institute of Genetics & Cancer,  \nUniversity of Edinburgh, Crewe Road, Edinburgh EH4 2XR, UK  \n5Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK  \n6University Hospital Southampton NHS Foundation Trust, Southampton, UK  \n7University Hospital of North Tees, North Tees and Hartlepool NHS Foundation Trust, Hardwick, Stockton on Tees, England, UK.  \nAbstract  \nBackground: The diagnosis of coeliac disease (CD), an autoimmune disorder with an estimated global prevalence of around 1%, generally relies on the histological examination of duodenal biopsies. However, interpathologist agreement when diagnosing coeliac disease is estimated to be no more than 80% . We aim to improve coeliac disease diagnosis by developing a novel, accurate machine-learning-based diagnostic classifier. Methods: We present a machine learning model that diagnoses the presence or absence of coeliac disease from a set of duodenal biopsies representative of real-world clinical data. Our model was trained on a diverse dataset of 3383 Whole-Slide-Images (WSIs) of H&E-stained duodenal biopsies from four hospitals featuring five different WSI scanners along with their clinical diagnoses. We trained our model using the multiple-instancelearning paradigm in a weakly-supervised manner with cross-validation and evaluated it on an independent test set featuring 644 unseen scans from a different regional NHS Trust. Additionally, we compared the model’s predictions to independent diagnoses from four specialist pathologists on a subset of the test data.  \nResults: Our model diagnosed coeliac disease on an independent test set from a previously unseen source, with accuracy, sensitivity and specificity exceeding 95% and an area under the ROC curve exceeding 99% . These results indicate that the model has the potential to outperform pathologists. In comparing the model’s predictions to diagnoses from four independent pathologists, on unseen test data, we found statistically indistinguishable results between pathologist-pathologist and pathologist-model inter-ob","cbCaiaApy8gxbK1F","https://ap.wps.com/l/cbCaiaApy8gxbK1F","pdf",437620,1,16,"English","en",105,"# Abstract\n## Background and Aim\n## Methods\n## Results\n## Conclusions","[{\"question\":\"Why is coeliac disease diagnosis challenging with current practice?\",\"answer\":\"Diagnosis typically depends on histology of duodenal biopsies, but interpathologist agreement is estimated to be no more than about 80%, creating variability in decisions.\"},{\"question\":\"How was the machine-learning model trained and validated?\",\"answer\":\"The model used multiple-instance learning with weak supervision, training on 3,383 H\\u0026E-stained WSI scans from four hospitals, then evaluating on 644 unseen scans from a different NHS Trust with cross-validation.\"},{\"question\":\"How did the model perform compared with pathologists?\",\"answer\":\"On independent test data, the model achieved over 95% for accuracy, sensitivity, and specificity, with AUROC above 99%. Agreement between pathologist-model predictions and pathologist-pathologist predictions on unseen data was statistically indistinguishable, with inter-observer agreement exceeding 96%.\"}]","Machine Learning Achieves Pathologist-Level Coeliac Disease Diagnosis | PDF",1785735998,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-achieves-pathologist-level-coeliac-disease-diagnosis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-achieves-pathologist-level-coeliac-disease-diagnosis/121507/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is coeliac disease diagnosis challenging with current practice?","Question",{"text":75,"@type":76},"Diagnosis typically depends on histology of duodenal biopsies, but interpathologist agreement is estimated to be no more than about 80%, creating variability in decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the machine-learning model trained and validated?",{"text":80,"@type":76},"The model used multiple-instance learning with weak supervision, training on 3,383 H&E-stained WSI scans from four hospitals, then evaluating on 644 unseen scans from a different NHS Trust with cross-validation.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the model perform compared with pathologists?",{"text":84,"@type":76},"On independent test data, the model achieved over 95% for accuracy, sensitivity, and specificity, with AUROC above 99%. Agreement between pathologist-model predictions and pathologist-pathologist predictions on unseen data was statistically indistinguishable, with inter-observer agreement exceeding 96%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]