{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:54:03Z","timestamp":1781553243819,"version":"3.54.5"},"reference-count":13,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/ http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>To evaluate the diagnostic proficiency of well-established multimodal Large Language Models (LLMs)\u2014specifically Gemini, Claude, and Copilot\u2014in interpreting cervical cytopathology (PAP smears). This diagnostic accuracy study used 30 representative cases from the \u201cCytopathology of the Uterine Cervix\u2014Digital Atlas,\u201d which represented the gold standard. The models were tested using a standardized, zero-shot prompt to distinguish between normal cells, benign modifications (infections), and cervical cell abnormalities. The models demonstrated significant variability. While Gemini and Copilot showed high proficiency (90%) in identifying normal physiological morphology, performance declined sharply for infectious pathogens and dysplastic\/neoplastic lesions. Notably, all models misclassified several invasive carcinomas as benign or low-grade lesions. Claude exhibited a high rate of \u201cdiagnostic escalation,\u201d frequently misidentifying normal cells as having abnormalities. Current LLMs are inadequate for the definitive diagnosis of cervical dysplasia and malignancy due to significant rates of overdiagnosis and failure to detect invasive carcinomas. They should be viewed as emerging educational aids rather than autonomous diagnostic tools, requiring rigorous human oversight.<\/jats:p>","DOI":"10.1097\/pgp.0000000000001168","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T23:00:10Z","timestamp":1778108410000},"page":"297-303","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Diagnostic Proficiency of Large Language Models in the Interpretation of Cervical Cytopathology"],"prefix":"10.1097","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8516-6242","authenticated-orcid":false,"given":"Iason","family":"Psilopatis","sequence":"first","affiliation":[{"name":"Department of Gynecology and Obstetrics, University Hospital Basel, Basel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kleio","family":"Vrettou","sequence":"additional","affiliation":[{"name":"Department of Cytopathology, Sismanogleio General Hospital, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"R2-20260615","doi-asserted-by":"crossref","first-page":"16","DOI":"10.25259\/Cytojournal_24_2021","article-title":"Squamous intraepithelial lesions (SIL: LSIL, HSIL, ASCUS, ASC-H, LSIL-H) of uterine cervix and Bethesda System","volume":"18","author":"Alrajjal","year":"2021","journal-title":"Cytojournal"},{"key":"R3-20260615","doi-asserted-by":"crossref","first-page":"810","DOI":"10.7326\/0003-4819-132-10-200005160-00009","article-title":"Accuracy of the Papanicolaou test in screening for and follow-up of cervical cytologic abnormalities: a systematic review","volume":"132","author":"Nanda","year":"2000","journal-title":"Ann Intern Med"},{"key":"R4-20260615","doi-asserted-by":"crossref","first-page":"1768","DOI":"10.3390\/biomedicines13071768","article-title":"Advancements in cervical cancer screening: enhancing HPV testing and triage strategies for improved risk assessment","volume":"13","author":"Merdzhanova-Gargova","year":"2025","journal-title":"Biomedicines"},{"key":"R5-20260615","doi-asserted-by":"crossref","first-page":"29","DOI":"10.25259\/CMAS_03_08_2021","article-title":"The Pap smear in inflammation and repair","volume":"19","author":"Kamal","year":"2022","journal-title":"Cytojournal"},{"key":"R6-20260615","doi-asserted-by":"crossref","first-page":"2776","DOI":"10.3390\/healthcare11202776","article-title":"Leveraging generative AI and large language models: a comprehensive roadmap for healthcare integration","volume":"11","author":"Yu","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"R7-20260615","doi-asserted-by":"crossref","first-page":"102900","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: a review","volume":"154","author":"Nerella","year":"2024","journal-title":"Artif Intell Med"},{"key":"R8-20260615","doi-asserted-by":"crossref","first-page":"900","DOI":"10.3348\/kjr.2025.0599","article-title":"Multimodal large language models in medical imaging: current state and future directions","volume":"26","author":"Nam","year":"2025","journal-title":"Korean J Radiol"},{"key":"R9-20260615","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.21037\/qims-23-892","article-title":"The role of large language models in medical image processing: a narrative review","volume":"14","author":"Tian","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"R10-20260615","doi-asserted-by":"crossref","first-page":"1571","DOI":"10.1007\/s00404-025-08145-w","article-title":"A comparative evaluation of publicly available large language models in the assessment of CTG traces according to the FIGO criteria","volume":"312","author":"Psilopatis","year":"2025","journal-title":"Arch Gynecol Obstet"},{"key":"R11-20260615","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.ejogrb.2025.01.007","article-title":"The role of artificial intelligence in gynecologic and obstetric emergencies","volume":"306","author":"Psilopatis","year":"2025","journal-title":"Eur J Obstet Gynecol Reprod Biol"},{"key":"R12-20260615","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1159\/000544751","article-title":"The role of artificial intelligence in gynecologic oncology decision-making: a feasibility study","volume":"90","author":"Psilopatis","year":"2025","journal-title":"Gynecol Obstet Invest"},{"key":"R14-20260615","doi-asserted-by":"crossref","first-page":"156159","DOI":"10.1016\/j.prp.2025.156159","article-title":"Evaluation of general-purpose large language models as diagnostic support tools in cervical cytology","volume":"274","author":"Laohawetwanit","year":"2025","journal-title":"Pathol Res Pract"},{"key":"R15-20260615","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1038\/s41698-025-00916-7","article-title":"Evaluating the performance of large language & visual-language models in cervical cytology screening","volume":"9","author":"Hong","year":"2025","journal-title":"NPJ Precis Oncol"}],"container-title":["International Journal of Gynecological Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/PGP.0000000000001168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:01:33Z","timestamp":1781550093000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/PGP.0000000000001168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":13,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/pgp.0000000000001168","relation":{},"ISSN":["0277-1691","1538-7151"],"issn-type":[{"value":"0277-1691","type":"print"},{"value":"1538-7151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"2026-01-05","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-26","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}