{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T12:29:57Z","timestamp":1787228997392,"version":"build-2736575974"},"reference-count":61,"publisher":"BMJ","issue":"9","funder":[{"DOI":"10.13039\/100008149","name":"Royal College of Pathologists","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100008149","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Clin Pathol"],"accepted":{"date-parts":[[2026,6,28]]},"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Artificial intelligence (AI) tools for digital pathology have crossed the threshold from pilot project to clinical deployment, with regulatory approvals, commercial products and prospective trials now accumulating across multiple tumour types. However, global-scale implementation demands careful evaluation of both opportunities and challenges. Traditional histopathology faces mounting pressures including interobserver variability and escalating workloads. At the same time, molecular diagnostics have become increasingly complex, while core workflows have remained fundamentally unchanged for decades. Digital pathology infrastructure and AI algorithms promise solutions through enhanced diagnostic accuracy, improved efficiency, democratised access to expertise and unprecedented research capabilities. AI has already demonstrated clinical value across multiple subspecialties, including prostate, breast and colorectal cancer, with applications spanning automated biomarker quantification, molecular subtype prediction and prognostic modelling. Systematic reviews also identify important limitations that temper enthusiasm for AI adoption. These include heterogeneity in study design, publication bias favouring positive results, limited generalisability across diverse populations and practice settings, concentration of research in narrow subspecialties and insufficient external validation. Critical implementation barriers include substantial infrastructure requirements, concerns around data privacy and security, gaps in regulatory oversight and the risk that algorithmic bias may exacerbate health disparities. Professional bodies advocate for responsible deployment guided by evidence-based standards. Key priorities include rigorous validation, workforce training, workflow integration and continuous performance monitoring. Making transformation equitable, safe and effective requires balancing innovation with accountability. AI should augment rather than replace pathologist expertise and be supported by robust governance frameworks that prioritise patient safety and diagnostic quality over commercial consideration.<\/jats:p>","DOI":"10.1136\/jcp-2026-210720","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:20:36Z","timestamp":1783704036000},"page":"577-586","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Promise and pragmatism of AI in global-scale digital pathology: pan-cancer approaches for clinical practice"],"prefix":"10.1136","volume":"79","author":[{"given":"Sarah E","family":"Coupland","sequence":"first","affiliation":[{"name":"Liverpool University Hospitals Group, Liverpool, UK"},{"name":"Dept. of Eye and Vision Science, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arvind","family":"Rao","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny","family":"Jonigk","sequence":"additional","affiliation":[{"name":"Institute of Pathology, RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"B\u00fclow","sequence":"additional","affiliation":[{"name":"Institute of Pathology, RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-515X","authenticated-orcid":false,"given":"Runjan","family":"Chetty","sequence":"additional","affiliation":[{"name":"Brighton and Sussex University Hospitals NHS Trust, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5374-3903","authenticated-orcid":false,"given":"Swapnil Ulhas","family":"Rane","sequence":"additional","affiliation":[{"name":"Departments of Surgical Pathology & Digital-Computational Oncology, Tata Memorial Centre, Mumbai, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep","family":"Dave","sequence":"additional","affiliation":[{"name":"Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3807-3638","authenticated-orcid":false,"given":"Kikkeri N","family":"Naresh","sequence":"additional","affiliation":[{"name":"Pathology Program, Translational Science & Therapeutics, Fred Hutch Cancer Center, Seattle, Washington, USA"},{"name":"Department of Laboratory Medicine & Pathology, University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"2026082005150909000_79.9.577.1","doi-asserted-by":"publisher","DOI":"10.1007\/s00428-020-02894-6"},{"key":"2026082005150909000_79.9.577.2","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0253876","article-title":"Evolution of anatomic pathology workload from 2011 to 2019 assessed in a regional hospital laboratory via 574,093 pathology reports","volume":"16","author":"Bonert","year":"2021","journal-title":"PLoS One"},{"key":"2026082005150909000_79.9.577.3","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s10555-016-9607-3","article-title":"Molecular pathology in real time","volume":"35","author":"Ry\u0161ka","year":"2016","journal-title":"Cancer Metastasis Rev"},{"key":"2026082005150909000_79.9.577.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03780-x"},{"key":"2026082005150909000_79.9.577.5","doi-asserted-by":"crossref","DOI":"10.3390\/cancers18030421","article-title":"Smart Lies and Sharp Eyes: Pragmatic Artificial Intelligence for Cancer Pathology: Promise, Pitfalls, and Access Pathways","volume":"18","author":"Bani","year":"2026","journal-title":"Cancers (Basel)"},{"key":"2026082005150909000_79.9.577.6","doi-asserted-by":"crossref","DOI":"10.1038\/s41698-025-01094-2","article-title":"Deepath-MSI: a clinic-ready deep learning model for microsatellite instability detection in colorectal cancer using whole-slide imaging","volume":"9","author":"Feng","year":"2025","journal-title":"NPJ Precis Oncol"},{"key":"2026082005150909000_79.9.577.7","unstructured":"Martin J . National pathology programme digital first: clinical transformation through pathology innovation. 2014. Available: https:\/\/www.england.nhs.uk\/wp-content\/uploads\/2014\/02\/pathol-dig-first.pdf"},{"key":"2026082005150909000_79.9.577.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.labinv.2023.100255"},{"key":"2026082005150909000_79.9.577.9","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1038\/s43018-024-00788-z","article-title":"Clinical implementation of artificial-intelligence-assisted detection of breast cancer metastases in sentinel lymph nodes: the CONFIDENT-B single-center, non-randomized clinical trial","volume":"5","author":"van Dooijeweert","year":"2024","journal-title":"Nat Cancer"},{"key":"2026082005150909000_79.9.577.10","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"2026082005150909000_79.9.577.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-020-0551-y"},{"key":"2026082005150909000_79.9.577.12","doi-asserted-by":"publisher","DOI":"10.1007\/s00428-023-03518-5"},{"key":"2026082005150909000_79.9.577.13","doi-asserted-by":"crossref","first-page":"100216","DOI":"10.1016\/j.modpat.2023.100216","article-title":"Artificial Intelligence-Aided Diagnosis of Breast Cancer Lymph Node Metastasis on Histologic Slides in a Digital Workflow","volume":"36","author":"Challa","year":"2023","journal-title":"Mod Pathol"},{"key":"2026082005150909000_79.9.577.14","doi-asserted-by":"crossref","first-page":"100033","DOI":"10.1016\/j.modpat.2022.100033","article-title":"Noninferiority of Artificial Intelligence-Assisted Analysis of Ki-67 and Estrogen\/Progesterone Receptor in Breast Cancer Routine Diagnostics","volume":"36","author":"Abele","year":"2023","journal-title":"Mod Pathol"},{"key":"2026082005150909000_79.9.577.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2021.09.007"},{"key":"2026082005150909000_79.9.577.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42453-6"},{"key":"2026082005150909000_79.9.577.17","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1038\/s41746-024-01294-3","article-title":"Public evidence on AI products for digital pathology","volume":"7","author":"Matthews","year":"2024","journal-title":"npj Digit Med"},{"key":"2026082005150909000_79.9.577.18","doi-asserted-by":"publisher","DOI":"10.5858\/135.2.233"},{"key":"2026082005150909000_79.9.577.19","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1038\/s41598-020-58467-9","article-title":"Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumours","volume":"10","author":"Iizuka","year":"2020","journal-title":"Sci Rep"},{"key":"2026082005150909000_79.9.577.20","doi-asserted-by":"crossref","first-page":"19","DOI":"10.4103\/jpi.jpi_10_20","article-title":"Deep Learning to Estimate Human Epidermal Growth Factor Receptor 2 Status from Hematoxylin and Eosin-Stained Breast Tissue Images","volume":"11","author":"Anand","year":"2020","journal-title":"J Pathol Inform"},{"key":"2026082005150909000_79.9.577.21","doi-asserted-by":"publisher","DOI":"10.1002\/path.5773"},{"key":"2026082005150909000_79.9.577.22","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-17678-4","article-title":"A deep learning model to predict RNA-Seq expression of tumours from whole slide images","volume":"11","author":"Schmauch","year":"2020","journal-title":"Nat Commun"},{"key":"2026082005150909000_79.9.577.23","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-75708-z","article-title":"Spatial transcriptomics inferred from pathology whole-slide images links tumor heterogeneity to survival in breast and lung cancer","volume":"10","author":"Levy-Jurgenson","year":"2020","journal-title":"Sci Rep"},{"key":"2026082005150909000_79.9.577.24","doi-asserted-by":"publisher","DOI":"10.1038\/modpathol.2017.98"},{"key":"2026082005150909000_79.9.577.25","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/path.6061","article-title":"Artificial intelligence-based digital scores of stromal tumour-infiltrating lymphocytes and tumour-associated stroma predict disease-specific survival in triple-negative breast cancer","volume":"260","author":"Albusayli","year":"2023","journal-title":"J Pathol"},{"key":"2026082005150909000_79.9.577.26","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jmoldx.2025.10.003","article-title":"Clinical Validation of Duoseq, a Novel Assay for Clinical DNA and RNA Sequencing","volume":"28","author":"Thacker","year":"2026","journal-title":"J Mol Diagn"},{"key":"2026082005150909000_79.9.577.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3"},{"key":"2026082005150909000_79.9.577.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"2026082005150909000_79.9.577.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03141-0"},{"key":"2026082005150909000_79.9.577.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102298"},{"key":"2026082005150909000_79.9.577.31","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2026082005150909000_79.9.577.32","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1038\/s41586-024-08378-w","article-title":"A vision-language foundation model for precision oncology","volume":"638","author":"Xiang","year":"2025","journal-title":"Nature"},{"key":"2026082005150909000_79.9.577.33","doi-asserted-by":"crossref","first-page":"11406","DOI":"10.1038\/s41467-025-66220-x","article-title":"A multimodal knowledge-enhanced whole-slide pathology foundation model","volume":"16","author":"Xu","year":"2025","journal-title":"Nat Commun"},{"key":"2026082005150909000_79.9.577.34","doi-asserted-by":"crossref","unstructured":"Ma J , Li W , Li J , et al . Generative AI for misalignment-resistant virtual staining to accelerate histopathology workflows. Nat Commun 2026;17. doi:10.1038\/s41467-026-71038-2","DOI":"10.1038\/s41467-026-71038-2"},{"key":"2026082005150909000_79.9.577.35","doi-asserted-by":"crossref","first-page":"115390","DOI":"10.1016\/j.ejca.2025.115390","article-title":"Artificial intelligence-based virtual staining platform for identifying tumor-associated macrophages from hematoxylin and eosin-stained images","volume":"220","author":"Aggarwal","year":"2025","journal-title":"Eur J Cancer"},{"key":"2026082005150909000_79.9.577.36","unstructured":"Gotadki R . Digital pathology market. 2024. Available: https:\/\/www.marketresearchfuture.com\/reports\/digital-pathology-market-1955?gad_source=1"},{"key":"2026082005150909000_79.9.577.37","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-024-01106-8","article-title":"Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy","volume":"7","author":"McGenity","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2026082005150909000_79.9.577.38","unstructured":"Thiringer E , Gustafsson FK , Eriksson KL , et al . Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models. arXiv 2026. doi:10.48550\/arXiv.2601.04163"},{"key":"2026082005150909000_79.9.577.39","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-24698-1","article-title":"The impact of site-specific digital histology signatures on deep learning model accuracy and bias","volume":"12","author":"Howard","year":"2021","journal-title":"Nat Commun"},{"key":"2026082005150909000_79.9.577.40","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpi.2024.100396","article-title":"Deep feature batch correction using ComBat for machine learning applications in computational pathology","volume":"15","author":"Murchan","year":"2024","journal-title":"J Pathol Inform"},{"key":"2026082005150909000_79.9.577.41","doi-asserted-by":"crossref","DOI":"10.1186\/s40644-023-00586-3","article-title":"Performance comparison between multi-center histopathology datasets of a weakly-supervised deep learning model for pancreatic ductal adenocarcinoma detection","volume":"23","author":"Carrillo-Perez","year":"2023","journal-title":"Cancer Imaging"},{"key":"2026082005150909000_79.9.577.42","doi-asserted-by":"publisher","DOI":"10.1038\/s41379-022-01147-y"},{"key":"2026082005150909000_79.9.577.43","doi-asserted-by":"crossref","first-page":"3468","DOI":"10.1200\/JCO-24-01501","article-title":"Foundation Model for Predicting Prognosis and Adjuvant Therapy Benefit From Digital Pathology in GI Cancers","volume":"43","author":"Wang","year":"2025","journal-title":"J Clin Oncol"},{"key":"2026082005150909000_79.9.577.44","doi-asserted-by":"publisher","DOI":"10.1136\/jcp-2024-209910"},{"key":"2026082005150909000_79.9.577.45","doi-asserted-by":"crossref","DOI":"10.1186\/s13054-024-05134-4","article-title":"Representation of intensivists\u2019 race\/ethnicity, sex, and age by artificial intelligence: a cross-sectional study of two text-to-image models","volume":"28","author":"Gisselbaek","year":"2024","journal-title":"Crit Care"},{"key":"2026082005150909000_79.9.577.46","doi-asserted-by":"crossref","first-page":"104879","DOI":"10.1016\/j.jbi.2025.104879","article-title":"Digital twins in increasing diversity in clinical trials: A systematic review","volume":"169","author":"Tubbs","year":"2025","journal-title":"J Biomed Inform"},{"key":"2026082005150909000_79.9.577.47","doi-asserted-by":"crossref","DOI":"10.1016\/j.xcrm.2023.101230","article-title":"Artificial intelligence education: An evidence-based medicine approach for consumers, translators, and developers","volume":"4","author":"Ng","year":"2023","journal-title":"Cell Rep Med"},{"key":"2026082005150909000_79.9.577.48","doi-asserted-by":"crossref","first-page":"100657","DOI":"10.1016\/j.modpat.2024.100657","article-title":"Making Pathologists Ready for the New Artificial Intelligence Era: Changes in Required Competencies","volume":"38","author":"Vos","year":"2025","journal-title":"Mod Pathol"},{"key":"2026082005150909000_79.9.577.49","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"},{"key":"2026082005150909000_79.9.577.50","doi-asserted-by":"publisher","DOI":"10.1002\/path.5331"},{"key":"2026082005150909000_79.9.577.51","unstructured":"College of American Pathologists . Building an AI-ready America: adopting AI at work. 2026."},{"key":"2026082005150909000_79.9.577.52","article-title":"Artificial intelligence and digital pathology: clinical promise and deployment considerations","volume":"10","author":"Zarella","year":"2023","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026082005150909000_79.9.577.53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104349"},{"key":"2026082005150909000_79.9.577.54","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1093\/ajcp\/aqaf024","article-title":"Optimizing electronic health records: Integration of human factors engineering for enhanced pathology report display and accessibility","volume":"164","author":"Larsen","year":"2025","journal-title":"Am J Clin Pathol"},{"key":"2026082005150909000_79.9.577.55","doi-asserted-by":"crossref","DOI":"10.4103\/jpi.jpi_98_20","article-title":"Integrating the Health-care Enterprise Pathology and Laboratory Medicine Guideline for Digital Pathology Interoperability","volume":"12","author":"Dash","year":"2021","journal-title":"J Pathol Inform"},{"key":"2026082005150909000_79.9.577.56","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/14737159.2025.2581687","article-title":"Digital pathology and AI: enhancing molecular diagnostics in low- and middle-income countries","volume":"25","author":"Rahman","year":"2025","journal-title":"Expert Rev Mol Diagn"},{"key":"2026082005150909000_79.9.577.57","doi-asserted-by":"publisher","DOI":"10.1016\/j.labinv.2024.102111"},{"key":"2026082005150909000_79.9.577.58","doi-asserted-by":"crossref","DOI":"10.1002\/cai2.160","article-title":"MOGAN for LUAD Subtype Classification by Integrating Three Omics Data Types","volume":"4","author":"He","year":"2025","journal-title":"Cancer Innov"},{"key":"2026082005150909000_79.9.577.59","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026082005150909000_79.9.577.60","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-1037-7"},{"key":"2026082005150909000_79.9.577.61","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.m3164","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension","volume":"26","author":"Liu","year":"2020","journal-title":"BMJ"}],"container-title":["Journal of Clinical Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/jcp-2026-210720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T12:15:44Z","timestamp":1787228144000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcp.bmj.com\/lookup\/doi\/10.1136\/jcp-2026-210720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":61,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,8,20]]},"published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1136\/jcp-2026-210720"],"URL":"https:\/\/doi.org\/10.1136\/jcp-2026-210720","relation":{},"ISSN":["0021-9746","1472-4146"],"issn-type":[{"value":"0021-9746","type":"print"},{"value":"1472-4146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]}}}