{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:07:44Z","timestamp":1789024064647,"version":"build-2803163510"},"reference-count":29,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["World j. otorhinolaryngol.-head neck surg."],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Large language models (LLM) are being rapidly integrated into healthcare, particularly to streamline time\u2010 and labor\u2010intensive administrative processes. However, the potential for artificial intelligence (AI) systems to demonstrate bias when employed for insurance authorization remains poorly understood. As insurers increasingly adopt AI to make coverage decisions, this study examined bias in LLM\u2010driven prior authorization in otolaryngology, using oral cavity squamous cell carcinoma (SCC) as a case study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using OpenAI's generative transformer GPT\u20104o, this study assessed for LLM bias when simulating insurance coverage decisions for head and neck cancer reconstruction. A standardized clinical scenario was constructed involving patients with T2N2 oral cavity SCC, all requiring surgical resection and reconstruction. The LLM was prompted to choose between a radial forearm free flap (RFFF) and split\u2010thickness skin graft (STSG) for reconstruction, across 19,900 simulations. Patient profiles were systematically varied by age, sex, race\/ethnicity, zip code\u2010based income level, socioeconomic status (SES), and substance use history.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The LLM output showed significant disparities in approval decisions. RFFF was more frequently approved for younger, Asian, or white patients from high\u2010income zip codes or high SES backgrounds (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.0001). Older, Black, and Hispanic patients, and those from lower\u2010income areas or with substance use histories, were less likely to receive RFFF authorization (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.0001). On sensitivity analysis, inclusion of tumor\u2010specific information markedly skewed recommendations towards RFFF across sociodemographic backgrounds.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this experimental study, the LLM's outputs exhibited significant disparities for oral cavity cancer reconstruction based on patient demographic variables in the setting of limited clinical information. Inputs to LLMs for clinical decision\u2010making should include pertinent and detailed information to reduce the risk of bias. As insurers increasingly integrate AI for prior authorization, recognition of its biases, rigorous safeguards, and increased regulatory governance are needed to promote equitable health care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/wjo2.70130","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:04:04Z","timestamp":1782475444000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disparities in AI\u2010Based Prior Authorization for Head and Neck Reconstruction: A Large Language Model Analysis"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0809-9143","authenticated-orcid":false,"given":"Shannon S.","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Stanford University School of Medicine Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mugil V.","family":"Shanmugam","sequence":"additional","affiliation":[{"name":"Department of Quantitative and Computational Biology, Dornsife College of Letters, Arts, and Sciences University of Southern California Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu\u2010Jin","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Stanford University School of Medicine Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1867-994X","authenticated-orcid":false,"given":"Noel F.","family":"Ayoub","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Stanford University School of Medicine Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1"},{"key":"e_1_2_12_3_1","unstructured":"A.ToumiandA.Koziell\u2010Pipe \u201cFunctorial Language Models \u201d published 2021 https:\/\/doi.org\/10.48550\/arXiv.2103.14411."},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03626-6"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpdig.2024.03.003"},{"key":"e_1_2_12_6_1","unstructured":"P.Rucker The Capitol Forum M.Miller andD.Armstrong \u201cProPublica. How Cigna Saves Millions by Having Its Doctors Reject Claims Without Reading Them \u201d ProPublica published2023 https:\/\/www.propublica.org\/article\/cigna-pxdx-medical-health-insurance-rejection-claims."},{"key":"e_1_2_12_7_1","unstructured":"C.RossandB.Herman \u201cDenied by AI: How Medicare AdvantagePlans Use Algorithms to Cut Off Care for Seniors in Need \u201d Stat published2023 https:\/\/www.statnews.com\/2023\/03\/13\/medicare-advantage-plans-denial-artificial-intelligence\/."},{"key":"e_1_2_12_8_1","volume-title":"GovInfo","author":"Senate Committee on Homeland Security and Governmental Affairs","year":"2024"},{"key":"e_1_2_12_9_1","unstructured":"J.Lubell \u201cHow AI Is Leading to More Prior Authorization Denials \u201d American Medical Association published2025 https:\/\/www.ama-assn.org\/practice-management\/prior-authorization\/how-ai-leading-more-prior-authorization-denials."},{"key":"e_1_2_12_10_1","unstructured":"Lokken v UnitedHealth Group Inc. (D. Minn. 2023)."},{"key":"e_1_2_12_11_1","unstructured":"Barrows et al. v (Kentucky Western: Humana Inc)."},{"key":"e_1_2_12_12_1","unstructured":"U.S. Census Bureau accessed July 24 2025 https:\/\/data.census.gov."},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/jso.24991"},{"key":"e_1_2_12_14_1","unstructured":"American Medical Association AMA Prior Authorization (PA) Physician Survey published 2024 https:\/\/www.ama-assn.org\/system\/files\/prior-authorization-survey.pdf."},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoto.2013.1132"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.31489"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-015-4386-6"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.SAP.0000044147.09310.E8"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/hed.23862"},{"key":"e_1_2_12_20_1","unstructured":"S.Al\u2010Haque V.Khanna S.Mandal M.Rayasam andP.Singh \u201cAI Ushers in Next\u2010Gen Prior Authorization in Healthcare\u201d McKinsey April 19 published2022 https:\/\/www.mckinsey.com\/industries\/healthcare\/our-insights\/ai-ushers-in-next-gen-prior-authorization-in-healthcare."},{"key":"e_1_2_12_21_1","unstructured":"Blue Cross Blue Shield of Massachusetts \u201cBlue Cross Blue Shield of Massachusetts Uses Artificial Intelligence to Speed Review Time Automate Authorizations & Eliminate Administrative Costs \u201d accessed June 20 2025 https:\/\/newsroom.bluecrossma.com\/2022-10-12-BLUE-CROSS-BLUE-SHIELD-OF-MASSACHUSETTS-USES-ARTIFICIAL-INTELLIGENCE-TO-SPEED-REVIEW-TIME -AUTOMATE-AUTHORIZATIONS-ELIMINATE-ADMINISTRATIVE-COSTS."},{"key":"e_1_2_12_22_1","unstructured":"C.RossandB.Herman \u201cUnitedhealth Faces Class Action Lawsuit Over Algorithmic Care Denials in Medicare Advantage Plans \u201d Stat November 14 2023 https:\/\/www.statnews.com\/2023\/11\/14\/unitedhealth-class-action-lawsuit-algorithm-medicare-advantage\/."},{"key":"e_1_2_12_23_1","unstructured":"Department of Health and Human Services \u201cNondiscrimination in Health Programs and Activities\u201d Federal Register May 6 2024 https:\/\/www.federalregister.gov\/documents\/2024\/05\/06\/2024-08711\/nondiscrimination-in-health-programs-and-activities."},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01700-4"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad016"},{"key":"e_1_2_12_26_1","unstructured":"A. I.Open \u201cGPT\u20104o System Card \u201d August 8 2024 https:\/\/openai.com\/index\/gpt-4o-system-card\/."},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"e_1_2_12_28_1","unstructured":"California State Senate \u201cBill Text\u2014SB\u20101120 Health Care Coverage: Utilization Review \u201d California Legislative Information September 28 2024 https:\/\/leginfo.legislature.ca.gov\/faces\/billNavClient.xhtml?bill_id=202320240SB1120."},{"key":"e_1_2_12_29_1","unstructured":"American College of Radiology \u201cState Legislators Introduce Artificial Intelligence Bills \u201d accessed June 19 2025 https:\/\/www.acr.org\/News-and-Publications\/State-Legislators-Introduce-Artificial-Intelligence-Bills."},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00611-y"}],"container-title":["World Journal of Otorhinolaryngology - Head and Neck Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/wjo2.70130","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/wjo2.70130","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/wjo2.70130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:56:33Z","timestamp":1789023393000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/wjo2.70130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":29,"alternative-id":["10.1002\/wjo2.70130"],"URL":"https:\/\/doi.org\/10.1002\/wjo2.70130","archive":["Portico"],"relation":{},"ISSN":["2095-8811","2589-1081"],"issn-type":[{"value":"2095-8811","type":"print"},{"value":"2589-1081","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"assertion":[{"value":"2025-07-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"wjo2.70130"}}