{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T10:24:20Z","timestamp":1787048660712,"version":"build-2736575974"},"reference-count":34,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Multimodal large language models are increasingly used for dermatologic queries, but whether Fitzpatrick skin type (FST) labels affect diagnostic accuracy is unknown. We evaluated 656 biopsy-confirmed photographs from the Diverse Dermatology Images (DDI) dataset under no-FST, DDI-concordant FST, and two DDI-discordant FST conditions using ChatGPT 5.2 Edu and Gemini 3.1 Pro browser configurations (5248 evaluations). Confirmed malignant diagnosis omission from the top three differential diagnoses (\u201clethal miss\u201d) was a prespecified exploratory outcome. Gemini had higher ordinal accuracy than ChatGPT (odds ratio 2.32; 95% confidence interval 2.01\u20132.67; false discovery rate-adjusted p &lt; 0.001). No FST prompt condition significantly improved accuracy over no-FST prompting; an equal-image-weighted sensitivity analysis yielded similar results. Among malignant images eligible for extreme discordance, extreme DDI-discordant prompting was associated with more ChatGPT lethal misses than no-FST prompting (paired odds ratio 5.0; p = 0.043); Gemini showed no significant paired shift (p = 1.00). Post hoc binary malignancy detection showed low no-FST specificity for ChatGPT (42.5%) and Gemini (22.9%), indicating frequent overcalling. Gemini showed lower no-FST accuracy for malignant FST V\u2013VI images than for FST I\u2013II and III\u2013IV images. FST prompting provided no measurable diagnostic benefit. Neither configuration supports autonomous dermatologic use.<\/jats:p>","DOI":"10.3390\/bioengineering13080932","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:06:41Z","timestamp":1787044001000},"page":"932","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effect of Fitzpatrick Skin Type Prompting on Diagnostic Accuracy in Multimodal Large Language Models: A Within-Image Experimental Study"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6004-6222","authenticated-orcid":false,"given":"Manoj","family":"Bhagwat","sequence":"first","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0993-205X","authenticated-orcid":false,"given":"Tyler","family":"Wittles","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3601-3999","authenticated-orcid":false,"given":"Jeffery","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1304-9722","authenticated-orcid":false,"given":"Joshua","family":"Mijares","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil K.","family":"Jairath","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"},{"name":"Ronald O. Perelman Department of Dermatology, New York University Grossman School of Medicine, New York, NY 10016, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syril Keena T.","family":"Que","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Indiana University School of Medicine, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1111\/jdv.18814","article-title":"Determining the clinical applicability of machine learning models through assessment of reporting across skin phototypes and rarer skin cancer types: A systematic review","volume":"37","author":"Steele","year":"2023","journal-title":"J. Eur. Acad. Dermatol. Venereol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mijares, J., Bisch, E.J., DeGuzman, E., Garg, K., Pontes, D., Jairath, N.K., Ramachandran, V., Jeha, G., Nemcevic, A., and Que, S.K.T. (2026). Validation of a dermatology-focused multimodal image-and-data assistant in diagnosis and management of common dermatologic conditions. Medicina, 62.","DOI":"10.3390\/medicina62040715"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1881","DOI":"10.1111\/ijd.17729","article-title":"Diagnostic performance of GPT-4o and Gemini Flash 2.0 in acne and rosacea","volume":"64","author":"Boostani","year":"2025","journal-title":"Int. J. Dermatol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Khamaysi, Z., Awwad, M., Jiryis, B., Bathish, N., and Shapiro, J. (2025). The role of ChatGPT in dermatology diagnostics. Diagnostics, 15.","DOI":"10.3390\/diagnostics15121529"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e202","DOI":"10.1111\/ajd.14484","article-title":"A systemic review of large language models and their implications in dermatology","volume":"66","author":"Lewandowski","year":"2025","journal-title":"Australas. J. Dermatol."},{"key":"ref_6","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":"ref_7","doi-asserted-by":"crossref","first-page":"108044","DOI":"10.1016\/j.cmpb.2024.108044","article-title":"Understanding skin color bias in deep learning-based skin lesion segmentation","volume":"245","author":"Habijan","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e240955","DOI":"10.1148\/radiol.240955","article-title":"Toward foundation models in radiology? Quantitative assessment of GPT-4V\u2019s multimodal and multianatomic region capabilities","volume":"313","author":"Strotzer","year":"2024","journal-title":"Radiology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e240153","DOI":"10.1148\/radiol.240153","article-title":"Performance of GPT-4 with vision on text- and image-based ACR diagnostic radiology in-training examination questions","volume":"312","author":"Hayden","year":"2024","journal-title":"Radiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"214","DOI":"10.3348\/kjr.2025.1045","article-title":"Evaluating the accuracy and diagnostic reasoning of multimodal large language models in interpreting neuroradiology cases from RadioGraphics","volume":"27","author":"Suh","year":"2026","journal-title":"Korean J. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Eauchai, L., Ot\u00e1lora Gonz\u00e1lez, L., Shi, Y., McGinnis, M.T., Yovchev, A., Herasevich, S., Pickering, B.W., and Herasevich, V. (2026). Do multimodal vision-language models enhance the medical diagnostic process? A systematic review. Healthcare, 14.","DOI":"10.3390\/healthcare14131877"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hassanein, F.E.A., Hussein, R.R., Elgarhy, M.R., Maher, S.M., Hassen, A., Heidar, S., Ezz El Arab, M., Edress, A., Abou-Bakr, A., and Mekhemar, M. (2026). Artificial intelligence versus human dental expertise in diagnosing periapical pathosis on periapical radiographs: A multicenter study. Bioengineering, 13.","DOI":"10.3390\/bioengineering13020232"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"von der St\u00fcck, M.S., Vuskov, R., Westfechtel, S., Siepmann, R., Kuhl, C., Truhn, D., and Nebelung, S. (2026). Visual large language models in radiology: A systematic multimodel evaluation of diagnostic accuracy and hallucinations. Life, 16.","DOI":"10.3390\/life16010066"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"G\u00fcler, I., Grieb, G., Kraus, A., Lautenbach, M., and Stelling, H. (2026). Diagnostic accuracy and stability of multimodal large language models for hand fracture detection: A multi-run evaluation on plain radiographs. Diagnostics, 16.","DOI":"10.3390\/diagnostics16030424"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Nelles, C., Abou Zeid, N., Terzis, R., Iuga, A.-I., G\u00f6rtz, L., Spurek, M.A., Maintz, D., Lennartz, S., and Kottlors, J. (2026). Opportunities and challenges of visual large language models in imaging diagnostics: Lessons from brain metastasis detection in clinical MRI. Diagnostics, 16.","DOI":"10.3390\/diagnostics16050749"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hong, S., Matalia, M., and Toma, M. (2026). Chatting Ain\u2019t Diagnosing: Diagnostic Variability and Fundamental Errors in Multimodal LLM Interpretation in Radiology. Algorithms, 19.","DOI":"10.3390\/a19030170"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1093\/jamia\/ocae086","article-title":"Mixed methods assessment of the influence of demographics on medical advice of ChatGPT","volume":"31","author":"Andreadis","year":"2024","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1038\/s41591-025-03626-6","article-title":"Sociodemographic biases in medical decision making by large language models","volume":"31","author":"Omar","year":"2025","journal-title":"Nat. Med."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jia, Q., Wen, Y., Liu, Y., Zhao, H., Yu, Q., Long, Y., Sun, D., and Yu, Y. (2026). Implicit bias in safety-aligned large language models: A multi-faceted evaluation of clinical decision-making and health equity. PLoS ONE, 21.","DOI":"10.1371\/journal.pone.0348819"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1016\/j.jaad.2024.01.067","article-title":"Integrating skin color assessments into clinical practice and research: A review of current approaches","volume":"91","author":"Harvey","year":"2024","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1038\/s41746-024-01176-8","article-title":"A survey of skin tone assessment in prospective research","volume":"7","author":"Weir","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1038\/s41746-025-02245-2","article-title":"Evaluating skin tone scales for dermatologic dataset labeling: A prospective-comparative study","volume":"8","author":"Weir","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1093\/ced\/llae112","article-title":"From data to diagnosis: Skin cancer image datasets for artificial intelligence","volume":"49","author":"Wen","year":"2024","journal-title":"Clin. Exp. Dermatol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1111\/pcmr.13110","article-title":"Optimisation of skin phototype classification","volume":"36","author":"Lim","year":"2023","journal-title":"Pigment Cell Melanoma Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1001\/jamadermatol.2026.0151","article-title":"A pigment-informed dermatology framework\u2014Reimagining \u201cskin of color\u201d","volume":"162","author":"Sarkar","year":"2026","journal-title":"JAMA Dermatol."},{"key":"ref_26","unstructured":"(2026, March 30). Introducing ChatGPT Health. Available online: https:\/\/openai.com\/index\/introducing-chatgpt-health\/."},{"key":"ref_27","unstructured":"(2026, January 28). Introducing GPT-5.2. Available online: https:\/\/openai.com\/index\/introducing-gpt-5-2\/."},{"key":"ref_28","unstructured":"(2026, March 25). Gemini 3.1 Pro: A Smarter Model for Your Most Complex Tasks. Available online: https:\/\/blog.google\/innovation-and-ai\/models-and-research\/gemini-models\/gemini-3-1-pro\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1159\/000550153","article-title":"When jack of all trades is a master of none: Comparing the performance of GPT-4 Omni against specialised neural networks in identifying malignant dermatological lesions from smartphone images and structured clinical data","volume":"242","author":"Deng","year":"2026","journal-title":"Dermatology"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1001\/jamadermatol.2023.0905","article-title":"Assessment of diagnostic performance of dermatologists cooperating with a convolutional neural network in a prospective clinical study: Human with machine","volume":"159","author":"Winkler","year":"2023","journal-title":"JAMA Dermatol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1111\/ijd.17076","article-title":"Artificial intelligence in dermatology: Advancements and challenges in skin of color","volume":"63","author":"Fliorent","year":"2024","journal-title":"Int. J. Dermatol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1159\/000530225","article-title":"Artificial intelligence for the classification of pigmented skin lesions in populations with skin of color: A systematic review","volume":"239","author":"Liu","year":"2023","journal-title":"Dermatology"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e51837","DOI":"10.2196\/51837","article-title":"What\u2019s in a name? Experimental evidence of gender bias in recommendation letters generated by ChatGPT","volume":"26","author":"Kaplan","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Thakur, N., Cui, S., Khanna, K., Knieling, V., Duggal, Y.N., and Shao, M. (2023). Investigation of the gender-specific discourse about online learning during COVID-19 on Twitter using sentiment analysis, subjectivity analysis, and toxicity analysis. Computers, 12.","DOI":"10.20944\/preprints202310.0157.v1"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/8\/932\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:26:14Z","timestamp":1787045174000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/8\/932"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["bioengineering13080932"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13080932","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]}}}