{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T17:12:49Z","timestamp":1788369169572,"version":"build-2803163510"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:00:00Z","timestamp":1778284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["GNT2033299"],"award-info":[{"award-number":["GNT2033299"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["GNT1172900"],"award-info":[{"award-number":["GNT1172900"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["NT1193955"],"award-info":[{"award-number":["NT1193955"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["GNT2033299"],"award-info":[{"award-number":["GNT2033299"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diagnosing anogenital dermatological conditions often requires specialist expertise that is unavailable in many clinical settings. Large language models (LLMs) are increasingly accessible to clinicians, but their diagnostic accuracy for anogenital dermatology has not been evaluated. We evaluated the diagnostic accuracy of 3 LLMs (Gemini 2.5 Pro, Claude Opus 4.1, and ChatGPT 5 Thinking) for anogenital dermatological conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study was conducted between September and November 2025, using deidentified clinical images of anogenital conditions from the STI Atlas (stiatlas.org) and other publicly available sources. Primary outcomes were correct classification of images identified as sexually transmitted infections (STIs) vs non-STIs and the inclusion of the correct diagnosis among the LLMs\u2019 top-ranked (top-1), top-3, or top-5 differential diagnoses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 218 images, Gemini achieved the highest accuracy for STI binary classification (76.2% [95% CI, 70.5%\u201381.9%]) and differential diagnosis (top-1, 39.0% [95% CI, 32.7%\u201345.7%]; top-3, 54.6% [95% CI, 47.9%\u201361.1%]; top-5, 60.6% [95% CI, 53.9%\u201366.9%]), followed by ChatGPT and Claude. In subgroup analysis, all LLMs showed substantially reduced accuracy for diagnostically challenging images (top-5 accuracy range, 29.2%\u201340.0%). Gemini consistently outperformed Claude across most subgroups (P &amp;lt; .05). None of the LLMs could identify any mpox correctly.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLMs showed limited accuracy for diagnosing anogenital dermatological conditions, particularly for challenging images. The best-performing model (Gemini) achieved only 39.0% for top-1 diagnosis, indicating that current LLMs cannot reliably diagnose anogenital conditions. These tools may support supervised clinical triage but need further validation before routine clinical use. Future studies should compare LLMs with clinicians and explore how they can assist clinical diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/infdis\/jiag258","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:46:50Z","timestamp":1778154410000},"page":"e330-e337","source":"Crossref","is-referenced-by-count":3,"title":["Diagnostic Accuracy of Commercial Large Language Models for Anogenital Skin Lesion Images: A Comparative Study of Gemini, Claude, and ChatGPT"],"prefix":"10.1093","volume":"234","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4554-3549","authenticated-orcid":false,"given":"Nyi Nyi","family":"Soe","sequence":"first","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5880-5731","authenticated-orcid":false,"given":"Phyu Mon","family":"Latt","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5423-4525","authenticated-orcid":false,"given":"David","family":"Lee","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2560-3233","authenticated-orcid":false,"given":"Ei T","family":"Aung","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6459-4235","authenticated-orcid":false,"given":"Ryan","family":"Horn","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5784-7403","authenticated-orcid":false,"given":"Jason J","family":"Ong","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher K","family":"Fairley","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric P F","family":"Chow","sequence":"additional","affiliation":[{"name":"Melbourne Sexual Health Centre, Bayside Health , Melbourne, Victoria ,","place":["Australia"]},{"name":"School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University , Melbourne, Victoria ,","place":["Australia"]},{"name":"Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne , Melbourne, Victoria ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,9]]},"reference":[{"key":"2026090212182759800_jiag258-B1","volume-title":"Global HIV hepatitis and STIs programmes. Global health sector strategies 2022\u20132030","author":"World Health Organization","year":"2022"},{"key":"2026090212182759800_jiag258-B2","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/j.abd.2022.01.004","article-title":"Genital ulcers caused by sexually transmitted agents","volume":"97","author":"Cunha Ramos","year":"2022","journal-title":"An Bras Dermatol"},{"key":"2026090212182759800_jiag258-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1071\/SH22134","article-title":"Australian sexually transmitted infection (STI) management guidelines for use in primary care 2022 update","volume":"20","author":"Ong","year":"2023","journal-title":"Sex Health"},{"key":"2026090212182759800_jiag258-B4","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1136\/sti.2005.016931","article-title":"Sexual health problems managed in Australian general practice: a national, cross sectional survey","volume":"82","author":"Freedman","year":"2006","journal-title":"Sex Transm Infect"},{"key":"2026090212182759800_jiag258-B5","author":"World Health Organization"},{"key":"2026090212182759800_jiag258-B6","doi-asserted-by":"crossref","first-page":"SH25026","DOI":"10.1071\/SH25026","article-title":"Do Australian sexual health clinics have the capacity to meet demand? A mixed methods survey of directors of sexual health clinics in Australia","volume":"22","author":"Fairley","year":"2025","journal-title":"Sex Health"},{"key":"2026090212182759800_jiag258-B7","doi-asserted-by":"crossref","first-page":"915399","DOI":"10.3389\/fmed.2022.915399","article-title":"Time to healthcare seeking following the onset of symptoms among men and women attending a sexual health clinic in Melbourne, Australia","volume":"9","author":"Farquharson","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"2026090212182759800_jiag258-B8","doi-asserted-by":"crossref","first-page":"e467","DOI":"10.1016\/S2589-7500(21)00117-5","article-title":"Artificial intelligence and sexual health in the USA","volume":"3","author":"Young","year":"2021","journal-title":"Lancet Digital Health"},{"key":"2026090212182759800_jiag258-B9","doi-asserted-by":"crossref","first-page":"103198","DOI":"10.1016\/j.eclinm.2025.103198","article-title":"Beyond behavioural change: prioritising structural solutions to control bacterial sexually transmitted infections","volume":"83","author":"Ong","year":"2025","journal-title":"eClinicalMedicine"},{"key":"2026090212182759800_jiag258-B10","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1136\/sextrans-2025-056866","article-title":"How might AI transform sexual healthcare?","volume":"102","author":"Chow","year":"2026","journal-title":"Sex Transm Infect"},{"key":"2026090212182759800_jiag258-B11","author":"Data Studios"},{"key":"2026090212182759800_jiag258-B12","author":"Saab"},{"key":"2026090212182759800_jiag258-B13","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1186\/s12916-024-03512-x","article-title":"Evaluation of artificial intelligence-powered screening for sexually transmitted infections-related skin lesions using clinical images and metadata","volume":"22","author":"Soe","year":"2024","journal-title":"BMC Med"},{"key":"2026090212182759800_jiag258-B14","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1038\/s41746-025-01543-z","article-title":"A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians","volume":"8","author":"Takita","year":"2025","journal-title":"npj Digit Med"},{"key":"2026090212182759800_jiag258-B15","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1136\/jme-2023-109574","article-title":"Open AI meets open notes: surveillance capitalism, patient privacy and online record access","volume":"50","author":"Blease","year":"2024","journal-title":"J Med Ethics"},{"key":"2026090212182759800_jiag258-B16","doi-asserted-by":"crossref","first-page":"e101102","DOI":"10.1136\/bmjhci-2024-101102","article-title":"Generative artificial intelligence in primary care: an online survey of UK general practitioners","volume":"31","author":"Blease","year":"2024","journal-title":"BMJ Health Care Info"},{"key":"2026090212182759800_jiag258-B17","author":"Attwooll"},{"key":"2026090212182759800_jiag258-B18","doi-asserted-by":"crossref","first-page":"e2533512","DOI":"10.1001\/jamanetworkopen.2025.33512","article-title":"Use of AI in identification of sexually transmitted infections and anogenital dermatoses","volume":"8","author":"Soe","year":"2025","journal-title":"JAMA Network Open"},{"key":"2026090212182759800_jiag258-B19","first-page":"1","volume-title":"Opening up ChatGPT: tracking openness, transparency, and accountability in instruction-tuned text generators","author":"Liesenfeld","year":"2023"},{"key":"2026090212182759800_jiag258-B20","doi-asserted-by":"crossref","first-page":"e078378","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":"2026090212182759800_jiag258-B21","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1001\/jamadermatol.2021.4915","article-title":"Checklist for evaluation of image-based artificial intelligence reports in dermatology: CLEAR derm consensus guidelines from the international skin imaging collaboration artificial intelligence working group","volume":"158","author":"Daneshjou","year":"2022","journal-title":"JAMA Dermatol"},{"key":"2026090212182759800_jiag258-B22","author":"World Health Organization"},{"key":"2026090212182759800_jiag258-B23","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1001\/archderm.1988.01670060015008","article-title":"The validity and practicality of sun-reactive skin types I through VI","volume":"124","author":"Fitzpatrick","year":"1988","journal-title":"Arch Dermatol"},{"key":"2026090212182759800_jiag258-B24","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/s43856-025-01144-7","article-title":"Using deep learning systems for diagnosing common skin lesions in sexual health","volume":"5","author":"Soe","year":"2025","journal-title":"Commun Med"},{"key":"2026090212182759800_jiag258-B25","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1111\/ijd.17060","article-title":"The performance of an artificial intelligence-based computer vision mobile application for the image diagnosis of genital dermatoses: a prospective cross-sectional study","volume":"63","author":"Mehta","year":"2024","journal-title":"Int J Dermatol"},{"key":"2026090212182759800_jiag258-B26","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/s41591-023-02728-3","article-title":"Deep learning-aided decision support for diagnosis of skin disease across skin tones","volume":"30","author":"Groh","year":"2024","journal-title":"Nature Medicine"},{"key":"2026090212182759800_jiag258-B27","doi-asserted-by":"crossref","first-page":"eabq6147","DOI":"10.1126\/sciadv.abq6147","article-title":"Disparities in dermatology AI performance on a diverse, curated clinical image set","volume":"8","author":"Daneshjou","year":"2022","journal-title":"Sci Adv"},{"key":"2026090212182759800_jiag258-B28","doi-asserted-by":"crossref","first-page":"e52490","DOI":"10.2196\/52490","article-title":"Using AI to differentiate mpox from common skin lesions in a sexual health clinic: algorithm development and validation study","volume":"26","author":"Soe","year":"2024","journal-title":"J Med Internet Res"},{"key":"2026090212182759800_jiag258-B29","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1038\/s41591-020-0842-3","article-title":"A deep learning system for differential diagnosis of skin diseases","volume":"26","author":"Liu","year":"2020","journal-title":"Nat Med. Jun"},{"key":"2026090212182759800_jiag258-B30","author":"World Health Organization"},{"key":"2026090212182759800_jiag258-B31","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1186\/s12879-024-10285-4","article-title":"Accuracy of symptom checker for the diagnosis of sexually transmitted infections using machine learning and Bayesian network algorithms","volume":"24","author":"Soe","year":"2024","journal-title":"BMC Infect Dis"}],"container-title":["The Journal of Infectious Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jid\/advance-article-pdf\/doi\/10.1093\/infdis\/jiag258\/68260753\/jiag258.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jid\/article-pdf\/234\/2\/e330\/68260753\/jiag258.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jid\/article-pdf\/234\/2\/e330\/68260753\/jiag258.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T16:18:42Z","timestamp":1788365922000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jid\/article\/234\/2\/e330\/8675090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,9]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,5,9]]},"published-print":{"date-parts":[[2026,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/infdis\/jiag258","relation":{},"ISSN":["0022-1899","1537-6613"],"issn-type":[{"value":"0022-1899","type":"print"},{"value":"1537-6613","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8,15]]},"published":{"date-parts":[[2026,5,9]]}}}