{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:25:42Z","timestamp":1787923542721,"version":"build-2784847793"},"reference-count":27,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Pers. Med.","JPM"],"abstract":"<jats:p>Objective: The objective was to quantify whether demographic and social attributes that were irrelevant to stated clinical need, prognosis, and expected benefit altered resource-allocation decisions made by a general-purpose large language model (LLM). Methods: We conducted a cross-sectional audit of the gpt-5-chat-latest API model alias on 8 October 2025, across seven clinical vignettes, generating 30,618 forced-choice comparisons between patient profiles. Profiles varied across a full-factorial combination of eight demographic and social attributes while clinical need, prognosis, and expected benefit were held constant. Forced choices were analyzed using pooled logistic regression with separate Patient A and Patient B attribute terms and vignette-specific position effects; position-averaged odds ratios and position-balanced absolute probabilities were derived from this model. Priority-score differences were analyzed using an analogous linear model. Results: The model showed large position-averaged associations between non-clinical patient attributes and allocation decisions. Indigenous and Black race were associated with substantially higher odds of selection relative to White race (Indigenous: OR 16.48, 95% CI 14.85\u201318.28; Black: OR 8.07, 95% CI 7.32\u20138.90), corresponding to position-balanced absolute increases in selection probability of 30.7 and 16.3 percentage points, respectively. Conversely, high-status occupation (OR 0.064, 95% CI 0.058\u20130.071), friendship with institutional leadership (OR 0.121, 95% CI 0.111\u20130.131), and major donor status (OR 0.092, 95% CI 0.084\u20130.101) were associated with markedly lower odds of selection. Choice-score concordance was 95.1%. Conclusions: In this controlled audit, the LLM\u2019s allocation decisions varied substantially according to demographic and social characteristics despite identical stated clinical need, prognosis, and expected benefit. Although some patterns could be interpreted differently under competing ethical frameworks, their implicit and unexplained incorporation into resource-allocation decisions raises concerns regarding transparency, accountability, and clinical governance. Clinical use of LLM-based allocation support should therefore require explicit safeguards and systematic auditing for non-clinical influences.<\/jats:p>","DOI":"10.3390\/jpm16090448","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T12:27:46Z","timestamp":1787920066000},"page":"448","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Social Status and Clinical Resource Allocation by a Large Language Model: An Evaluation of 30,618 Decisions"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4839-5182","authenticated-orcid":false,"given":"Siddharth","family":"Gandhi","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Queen\u2019s University, Kingston, ON K7L 3J4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5948-0331","authenticated-orcid":false,"given":"Michael","family":"Balas","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, ON M5T 3A9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s12939-025-02419-0","article-title":"Evaluating and Addressing Demographic Disparities in Medical Large Language Models: A Systematic Review","volume":"24","author":"Omar","year":"2025","journal-title":"Int. J. Equity Health"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/s12939-025-02581-5","article-title":"Potential to Perpetuate Social Biases in Health Care by Chinese Large Language Models: A Model Evaluation Study","volume":"24","author":"Liu","year":"2025","journal-title":"Int. J. Equity Health"},{"key":"ref_4","doi-asserted-by":"crossref","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":"ref_5","doi-asserted-by":"crossref","first-page":"102323","DOI":"10.1016\/j.xcrm.2025.102323","article-title":"Large Language Model as Clinical Decision Support System Augments Medication Safety in 16 Clinical Specialties","volume":"6","author":"Ong","year":"2025","journal-title":"Cell Rep. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1038\/s41575-025-01108-1","article-title":"Large Language Models for Clinical Decision Support in Gastroenterology and Hepatology","volume":"22","author":"Wiest","year":"2025","journal-title":"Nat. Rev. Gastroenterol. Hepatol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e73603","DOI":"10.2196\/73603","article-title":"Large Language Models\u2019 Clinical Decision-Making on When to Perform a Kidney Biopsy: Comparative Study","volume":"27","author":"Toal","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3590","DOI":"10.1038\/s41591-024-03258-2","article-title":"A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models","volume":"30","author":"Pfohl","year":"2024","journal-title":"Nat. Med."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Benkirane, K., Kay, J., and Perez-Ortiz, M. (2025). How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.naacl-long.114"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (2022). Training Language Models to Follow Instructions with Human Feedback. Proceedings of the Advances in Neural Information Processing Systems 35, Neural Information Processing Systems Foundation, Inc. (NeurIPS).","DOI":"10.52202\/068431-2011"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1038\/s41746-025-01576-4","article-title":"Mitigating the Risk of Health Inequity Exacerbated by Large Language Models","volume":"8","author":"Ji","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"68","DOI":"10.5339\/qmj.2024.68","article-title":"The Recommended Patient Syndrome: Charting New Frontiers","volume":"2024","author":"Alkhawaldeh","year":"2024","journal-title":"Qatar Med. J."},{"key":"ref_13","first-page":"215","article-title":"Celebrity Patients, VIPs, and Potentates","volume":"4","author":"Groves","year":"2002","journal-title":"Prim. Care Companion J. Clin. Psychiatry"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"E263","DOI":"10.1503\/cmaj.121383","article-title":"The Effect of Socioeconomic Status on Access to Primary Care: An Audit Study","volume":"185","author":"Olah","year":"2013","journal-title":"Can. Med. Assoc. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"E66","DOI":"10.1001\/amajethics.2023.66","article-title":"Why VIP Services Are Ethically Indefensible in Health Care","volume":"25","author":"Lever","year":"2023","journal-title":"AMA J. Ethics"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhu, J., Brenna, C.T.A., McCoy, L.G., Atkins, C.G.K., and Das, S. (2022). An Ethical Analysis of Clinical Triage Protocols and Decision-Making Frameworks: What Do the Principles of Justice, Freedom, and a Disability Rights Approach Demand of Us?. BMC Med. Ethics, 23.","DOI":"10.1186\/s12910-022-00749-0"},{"key":"ref_17","first-page":"19","article-title":"Triage and Ethics","volume":"4","author":"Kipnis","year":"2002","journal-title":"AMA J. Ethics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"505","DOI":"10.7205\/MILMED.170.6.505","article-title":"The Dynamics and Ethics of Triage: Rationing Care in Hard Times","volume":"170","author":"Repine","year":"2005","journal-title":"Mil. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1093\/geront\/gnw056","article-title":"Cumulative Advantage, Cumulative Disadvantage, and Evolving Patterns of Late-Life Inequality","volume":"57","author":"Crystal","year":"2017","journal-title":"Gerontologist"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.annemergmed.2006.05.019","article-title":"Triage in Medicine, Part I: Concept, History, and Types","volume":"49","author":"Iserson","year":"2007","journal-title":"Ann. Emerg. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5","DOI":"10.4103\/2229-5070.175024","article-title":"Utilitarian and Deontological Ethics in Medicine","volume":"6","author":"Mandal","year":"2016","journal-title":"Trop. Parasitol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1136\/medethics-2020-107071","article-title":"Should Age Matter in COVID-19 Triage? A Deliberative Study","volume":"47","author":"Kuylen","year":"2021","journal-title":"J. Med. Ethics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1056\/NEJMsb2005114","article-title":"Fair Allocation of Scarce Medical Resources in the Time of Covid-19","volume":"382","author":"Emanuel","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_24","first-page":"9","article-title":"Transparency in public health decision-making","volume":"30","author":"Argimon","year":"2016","journal-title":"Gac. Sanit."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13000-024-01464-7","article-title":"Challenges and Barriers of Using Large Language Models (LLM) Such as ChatGPT for Diagnostic Medicine with a Focus on Digital Pathology\u2014A Recent Scoping Review","volume":"19","author":"Ullah","year":"2024","journal-title":"Diagn. Pathol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"23779608261457722","DOI":"10.1177\/23779608261457722","article-title":"Navigating Professional Accountability in AI\u2013Assisted Nursing Practice: Ethical and Legal Imperatives for the Digital Age","volume":"12","author":"Shankar","year":"2026","journal-title":"Sage Open Nurs."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1136\/jme-2023-109549","article-title":"Exploring the Potential Utility of AI Large Language Models for Medical Ethics: An Expert Panel Evaluation of GPT-4","volume":"50","author":"Balas","year":"2024","journal-title":"J. Med. Ethics"}],"container-title":["Journal of Personalized Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4426\/16\/9\/448\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T12:41:40Z","timestamp":1787920900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4426\/16\/9\/448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":27,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jpm16090448"],"URL":"https:\/\/doi.org\/10.3390\/jpm16090448","relation":{},"ISSN":["2075-4426"],"issn-type":[{"value":"2075-4426","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}