{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:11:30Z","timestamp":1788757890681,"version":"build-2803163510"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Malignant melanoma is an aggressive skin cancer with rising incidence. Accurate early staging and standardized treatment are crucial for prognosis. This study evaluates seven large language models (LLMs)-including GPT-5.2, Gemini-3.1, and medically enhanced models-in assisting non-metastatic melanoma management amid clinical complexities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Employing a prospective, simulated expert-blinded design, 59 virtual cases across TNM stages, ages, and comorbidities were assessed. Multiple senior oncologists independently evaluated model outputs using a 6-point Likert scale for staging accuracy, treatment rationality, and protocol standardization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>GPT-5.2 (5.56\u2009\u00b1\u20091.12) and Gemini-3.1 (5.25\u2009\u00b1\u20091.3) achieved the highest staging accuracy, while AntAngelMed performed worst (2.93\u2009\u00b1\u20091.67). Performance declined significantly in complex Stage III cases. GPT-5.2 and Gemini-3.1 also led in treatment rationality, showing stability, whereas model performances converged in early stages but diverged in advanced ones. Gemini-3.1 excelled in protocol standardization (5.17\u2009\u00b1\u20090.57), though some models posed risks like insufficient surgical margin recommendations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Leading LLMs demonstrate potential for high-quality melanoma management but exhibit inconsistent performance influenced by architecture and case complexity, with reduced reliability in advanced stages. Future tools require risk-stratified guidelines and real-world validation to improve patient outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1908569","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T04:23:26Z","timestamp":1788755006000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating LLMs in non-metastatic melanoma care: a comparative analysis"],"prefix":"10.3389","volume":"13","author":[{"given":"Xizhi","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Shaoxing, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangyan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Shaoxing, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanli","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Shaoxing, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueying","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Oncology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Zhejiang, Shaoxing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Shaoxing, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Oncology, Shaoxing People\u2019s Hospital, The First Hospital of Shaoxing University","place":["Zhejiang, Shaoxing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"39300","DOI":"10.1038\/s41598-025-23066-z","article-title":"Global assessment of surface ultraviolet radiation and malignant skin melanoma incidence from 1990 to 2021","volume":"15","author":"Feng","year":"2025","journal-title":"Sci Rep"},{"key":"B2","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1684\/ejd.2016.2845","article-title":"A prospective population-based study, aiming to support decision-making in a follow-up programme for patients with cutaneous malignant melanoma, based on patterns of recurrence","volume":"26","author":"Maroti","year":"2016","journal-title":"Eur J Dermatol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1200\/JCO.2017.75.7724","article-title":"Sentinel lymph node biopsy and management of regional lymph nodes in melanoma: american society of clinical oncology and society of surgical oncology clinical practice guideline update","volume":"36","author":"Wong","year":"2018","journal-title":"J Clin Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"4204","DOI":"10.1200\/JCO.23.00255","article-title":"Debating sentinel lymph node biopsy for melanoma in the modern adjuvant era","volume":"41","author":"Zhang","year":"2023","journal-title":"J Clin Oncol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s40257-024-00852-5","article-title":"Rapidly evolving Pre- and post-surgical systemic treatment of melanoma","volume":"25","author":"Augustin","year":"2024","journal-title":"Am J Clin Dermatol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1111\/ddg.15963","article-title":"Real-world management of adjuvant systemic melanoma therapy: multi-center survey of 51 DeCOG skin cancer centers","volume":"24","author":"Reitmajer","year":"2025","journal-title":"J Dtsch Dermatol Ges"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1001\/jamadermatol.2020.1729","article-title":"Prognostic gene expression profiling in cutaneous melanoma: identifying the knowledge gaps and assessing the clinical benefit","volume":"156","author":"Grossman","year":"2020","journal-title":"JAMA Dermatol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"100943","DOI":"10.1016\/j.patter.2024.100943","article-title":"Can large language models reason about medical questions?","volume":"5","author":"Li\u00e9vin","year":"2024","journal-title":"Patterns (N Y)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Adapted large language models can outperform medical experts in clinical text summarization","volume":"30","author":"Van Veen","year":"2024","journal-title":"Nat Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/s41591-024-03416-6","article-title":"A generalist medical language model for disease diagnosis assistance","volume":"31","author":"Liu","year":"2025","journal-title":"Nat Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1093\/bjd\/ljae377","article-title":"Do large language model chatbots perform better than established patient information resources in answering patient questions? A comparative study on melanoma","volume":"192","author":"Kamminga","year":"2025","journal-title":"Br J Dermatol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"262","DOI":"10.3233\/SHTI251540","article-title":"Medprompteval: a comprehensive framework for systematic evaluation of clinical question answering systems","volume":"332","author":"Rahrooh","year":"2025","journal-title":"Stud Health Technol Inform"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4019","DOI":"10.1016\/j.csbj.2024.10.050","article-title":"Assessment of large language models (LLMs) in decision-making support for gynecologic oncology","volume":"23","author":"Gumilar","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"B14","doi-asserted-by":"publisher","first-page":"20552076251390001","DOI":"10.1177\/20552076251390001","article-title":"Blinded evaluation of GPT-4 and physician responses to patient inquiries across multiple specialties","volume":"11","author":"Sallabi","year":"2025","journal-title":"Digit Health"},{"key":"B15","doi-asserted-by":"publisher","first-page":"651","DOI":"10.4149\/neo_2018_170701N452","article-title":"AJCC 8th Edition (2017) versus AJCC 7th edition (2010) in thin melanoma staging","volume":"65","author":"Roncati","year":"2018","journal-title":"Neoplasma"},{"key":"B16","doi-asserted-by":"publisher","first-page":"3969","DOI":"10.1245\/s10434-013-3092-5","article-title":"Reproducibility of AJCC staging parameters in primary cutaneous melanoma: an analysis of 4,924 cases","volume":"20","author":"Niebling","year":"2013","journal-title":"Ann Surg Oncol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1002\/cncr.21189","article-title":"Inefficacy of F-18 fluorodeoxy-D-glucose-positron emission tomography scans for initial evaluation in early-stage cutaneous melanoma","volume":"104","author":"Wagner","year":"2005","journal-title":"Cancer"},{"key":"B19","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e7","DOI":"10.1016\/S1470-2045(22)00703-3","article-title":"Distant metastasis-free survival with adjuvant pembrolizumab for resected stage IIB or IIC melanoma","volume":"24","author":"Mo","year":"2023","journal-title":"Lancet Oncol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1186\/s12885-018-4016-3","article-title":"Performance of a prognostic 31-gene expression profile in an independent cohort of 523 cutaneous melanoma patients","volume":"18","author":"Zager","year":"2018","journal-title":"BMC Cancer"},{"key":"B22","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1038\/s41746-025-02304-8","article-title":"EvoMDT: a self-evolving multi-agent system for structured clinical decision-making in multi-cancer","volume":"9","author":"Liu","year":"2026","journal-title":"NPJ Digit Med"},{"key":"B23","doi-asserted-by":"publisher","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":"B24","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1245\/s10434-018-6470-1","article-title":"1 Versus 2-cm excision margins for pT2-pT4 primary cutaneous melanoma (MelMarT): a feasibility study","volume":"25","author":"Moncrieff","year":"2018","journal-title":"Ann Surg Oncol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"502413","DOI":"10.1016\/j.rce.2025.502413","article-title":"Generative AI: foundational models. Natural language processing (NLP) and LARGE language models (LLM)","volume":"226","author":"Mora-Delgado","year":"2026","journal-title":"Rev Clin Esp (Barc)"},{"key":"B26","doi-asserted-by":"publisher","first-page":"115366","DOI":"10.1016\/j.ejca.2025.115366","article-title":"Reconsidering the surgical approach in cutaneous melanoma: does wide local excision after a complete diagnostic excision reduce the risk of recurrence?","volume":"220","author":"Stekelenburg","year":"2025","journal-title":"Eur J Cancer"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1908569\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T04:23:27Z","timestamp":1788755007000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1908569\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":26,"alternative-id":["10.3389\/fmed.2026.1908569"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1908569","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"article-number":"1908569"}}