{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T09:58:09Z","timestamp":1785491889239,"version":"3.56.0"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"publisher","award":["CL-2024-06-004"],"award-info":[{"award-number":["CL-2024-06-004"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"publisher","award":["CL-2023-06-002"],"award-info":[{"award-number":["CL-2023-06-002"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"publisher","award":["NIHR203308"],"award-info":[{"award-number":["NIHR203308"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100024724","name":"NIHR Manchester Clinical Research Facility","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100024724","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The use of artificial intelligence (AI) in many aspects of society is expanding rapidly. AI has recently been employed in the National Health Service skin cancer referral pathway. We sought to assess the real-world diagnostic performance of AI in this setting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To assess the real-world diagnostic performance, at the histopathological level, of AI employed in the urgent skin cancer screening pathway.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This was a prospective observational study of the first 3 months of skin cancer referrals assessed by the Deep Ensemble for Recognition of Malignancy (DERM) AI algorithm in a tertiary care dermatology department in the North West of England. All lesions assessed by the algorithm were included in the analysis. Participant data were retrieved from medical records. Outcomes assessed included the AI diagnosis, whether a human review of AI diagnosis occurred, the face-to-face dermatologist\u2019s diagnosis and the outcome of the dermatologist\u2019s assessment. Comparison was made particularly between the final histopathological diagnosis, and AI and dermatologist diagnoses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>AI had a sensitivity of 95.3% [95% confidence interval (CI) 90.5\u201398.1], which compared favourably with dermatologists (88.5%, 95% CI 82.3\u201393.2; P = 0.006). The positive predictive value of the AI algorithm was lower, at 46.5% (95% CI 44.6\u201348.5). This compared with 62.1% (95% CI 53.9\u201367.7) in dermatologists. A total of 318 AI assessments with no remote human review went on to have their lesions reviewed by a dermatologist and biopsied. AI correctly identified the precise diagnosis 28.6% of the time, compared with dermatologists 61.6% of the time (P &amp;lt; 0.001). The correct tumour\/lesion type was identified by AI 51.4% of the time and by dermatologists 75.5% (P &amp;lt; 0.001). In lesions that the AI deemed benign, and that would have been discharged with no human review, four cancers were diagnosed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>AI has high sensitivity in the detection of skin cancer. However, the diagnostic accuracy of the information provided by AI to clinicians is low and could be further optimized to reduce the risk of automation bias. Furthermore, this study suggests the removal of human validation of AI decisions may be premature due to the potential for missed cancer diagnoses.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/skinhd\/vzag068","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T11:35:57Z","timestamp":1777116957000},"page":"550-556","source":"Crossref","is-referenced-by-count":0,"title":["Real-world diagnostic performance of artificial intelligence in skin cancer screening"],"prefix":"10.1093","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7926-8506","authenticated-orcid":false,"given":"Charles H","family":"Earnshaw","sequence":"first","affiliation":[{"name":"Dermatology Centre, Northern Care Alliance NHS Foundation Trust & Division of Musculoskeletal and Dermatological Sciences, Manchester NIHR Biomedical Research Centre, Manchester Academic Health Science Centre, University of Manchester , Manchester ,","place":["UK"]},{"name":"Cancer Research UK Manchester Institute, University of Manchester , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karmen","family":"Cheung","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Salford Royal Hospital, Northern Care Alliance NHS Foundation Trust , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fasiha","family":"Arshad","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Salford Royal Hospital, Northern Care Alliance NHS Foundation Trust , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Moore","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Salford Royal Hospital, Northern Care Alliance NHS Foundation Trust , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Al-Janabi","sequence":"additional","affiliation":[{"name":"Dermatology Centre, Northern Care Alliance NHS Foundation Trust & Division of Musculoskeletal and Dermatological Sciences, Manchester NIHR Biomedical Research Centre, Manchester Academic Health Science Centre, University of Manchester , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"McMullen","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Salford Royal Hospital, Northern Care Alliance NHS Foundation Trust , Manchester ,","place":["UK"]},{"name":"Greater Manchester Skin Pathway Board, Greater Manchester Integrated Care Board , Manchester ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"2026073105073648500_vzag068-B1","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1056\/NEJMra1708701","article-title":"Update on keratinocyte carcinomas","volume":"379","author":"Nehal","year":"2018","journal-title":"N Engl J Med"},{"key":"2026073105073648500_vzag068-B2","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1056\/NEJMoa2407417","article-title":"Final, 10-year outcomes with nivolumab plus ipilimumab in advanced melanoma","volume":"392","author":"Wolchok","year":"2024","journal-title":"N Engl J Med"},{"key":"2026073105073648500_vzag068-B3","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1056\/NEJMoa2109970","article-title":"Relatlimab and nivolumab versus nivolumab in untreated advanced melanoma","volume":"386","author":"Tawbi","year":"2022","journal-title":"N Engl J Med"},{"key":"2026073105073648500_vzag068-B4","author":"Cancer Research UK"},{"key":"2026073105073648500_vzag068-B5","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.jaad.2017.08.059","article-title":"Cutaneous squamous cell carcinoma: incidence, risk factors, diagnosis, and staging","volume":"78","author":"Que","year":"2018","journal-title":"J Am Acad Dermatol"},{"key":"2026073105073648500_vzag068-B6","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1093\/ced\/llad438","article-title":"International melanoma and non melanoma skin cancer mortality trends: is it time to refocus our attention?","volume":"49","author":"Venables","year":"2023","journal-title":"Clin Exp Dermatol"},{"key":"2026073105073648500_vzag068-B7","author":"NHS England"},{"key":"2026073105073648500_vzag068-B8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"2026073105073648500_vzag068-B9","doi-asserted-by":"crossref","first-page":"1836","DOI":"10.1093\/annonc\/mdy166","article-title":"Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists","volume":"29","author":"Haenssle","year":"2018","journal-title":"Ann Oncol"},{"key":"2026073105073648500_vzag068-B10","author":"NICE"},{"key":"2026073105073648500_vzag068-B11","article-title":"The crisis in dermatology","volume":"350","author":"Eedy","year":"2015","journal-title":"BMJ"},{"key":"2026073105073648500_vzag068-B12","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.13436","article-title":"Assessment of accuracy of an artificial intelligence algorithm to detect melanoma in images of skin lesions","volume":"2","author":"Phillips","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2026073105073648500_vzag068-B13","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1038\/s41746-024-01103-x","article-title":"A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis","volume":"7","author":"Salinas","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2026073105073648500_vzag068-B14","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1111\/ijd.17981","article-title":"Performance of artificial intelligence in skin cancer detection: an umbrella review of systematic reviews and meta-analyses","volume":"65","author":"Karimzadhagh","year":"2026","journal-title":"Int J Dermatol"},{"key":"2026073105073648500_vzag068-B15","author":"British Association of Dermatologists"},{"key":"2026073105073648500_vzag068-B16","author":"European Commission, Directorate-General for Health and Food Safety"},{"key":"2026073105073648500_vzag068-B17","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.jid.2023.10.004","article-title":"Artificial intelligence in skin cancer diagnosis: a reality check","volume":"144","author":"Brancaccio","year":"2024","journal-title":"J Invest Dermatol"},{"key":"2026073105073648500_vzag068-B18","doi-asserted-by":"crossref","first-page":"2285","DOI":"10.1056\/NEJMp1907407","article-title":"Machine learning and the cancer-diagnosis problem \u2013 no gold standard","volume":"381","author":"Adamson","year":"2019","journal-title":"N Engl J Med"},{"key":"2026073105073648500_vzag068-B19","doi-asserted-by":"crossref","first-page":"1264846","DOI":"10.3389\/fmed.2023.1264846","article-title":"Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance","volume":"10","author":"Thomas","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"2026073105073648500_vzag068-B20","author":"MedCalc Software Ltd"},{"key":"2026073105073648500_vzag068-B21","author":"Skene"},{"key":"2026073105073648500_vzag068-B22","first-page":"93","article-title":"The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more \u201cpersonalized\u201d approach to cancer staging","volume":"67","author":"Amin","year":"2017","journal-title":"CA Cancer J Clin"},{"key":"2026073105073648500_vzag068-B23","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/S2468-1253(25)00133-5","article-title":"Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study","volume":"10","author":"Budzy\u0144","year":"2025","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"2026073105073648500_vzag068-B24","doi-asserted-by":"crossref","first-page":"233","DOI":"10.3389\/fmed.2020.00233","article-title":"Artificial intelligence in skin cancer diagnostics: the patients\u2019 perspective","volume":"7","author":"Jutzi","year":"2020","journal-title":"Front Med (Lausanne)"},{"key":"2026073105073648500_vzag068-B25","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1038\/s41591-020-0942-0","article-title":"Human\u2013computer collaboration for skin cancer recognition","volume":"26","author":"Tschandl","year":"2020","journal-title":"Nat Med"},{"key":"2026073105073648500_vzag068-B26","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1089\/tmj.2024.0532","article-title":"When are single reader evaluations insufficient in teledermoscopic assessments? Analyses of a retrospective cohort study","volume":"31","author":"N\u00e4tterdahl","year":"2025","journal-title":"Telemed J E Health"},{"key":"2026073105073648500_vzag068-B27","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1093\/bjd\/ljaf024","article-title":"Real-world melanoma miss rate in an NHS hospital dermatology service: a retrospective study","volume":"192","author":"Anderson","year":"2025","journal-title":"Br J Dermatol"}],"container-title":["Skin Health and Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/skinhd\/article-pdf\/6\/4\/550\/68494363\/vzag068.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/skinhd\/article-pdf\/6\/4\/550\/68494363\/vzag068.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T09:07:44Z","timestamp":1785488864000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/skinhd\/article\/6\/4\/550\/8704399"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,6,9]]},"published-print":{"date-parts":[[2026,7,31]]}},"URL":"https:\/\/doi.org\/10.1093\/skinhd\/vzag068","relation":{},"ISSN":["2690-442X"],"issn-type":[{"value":"2690-442X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,6,9]]}}}