{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:08:02Z","timestamp":1774264082465,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    As artificial intelligence (AI) increasingly informs healthcare, understanding how large language models (LLMs) evaluate medical professionals is critical. This study quantified biases when LLMs assess neurosurgeon competency using demographic and practice characteristics. We prompted three prominent LLMs (ChatGPT-4o, Claude 3.7 Sonnet, and DeepSeek-V3) to score 6,500 synthetic neurosurgeon profiles. Profiles were created using demographically diverse names derived from public databases and randomly assigned professional attributes (experience, publications, institution, region, specialty) with statistical validation ensuring even distribution across groups. Multivariate regression analysis quantified how each factor influenced competency scores (0\u2013100). Despite identical profiles, LLMs produced inconsistent mean (SD) scores: ChatGPT 91.85 (6.60), DeepSeek 71.74 (10.30), and Claude 62.29 (13.59). All models showed regional biases; North American neurosurgeons received scores 3.09 (ChatGPT) and 2.48 (DeepSeek) points higher than identical African counterparts (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u2009.001). ChatGPT penalized East Asian (\u2212\u20090.83), South Asian (\u2212\u20090.91), and Middle Eastern (\u2212\u20090.80) neurosurgeons (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u2009.001). Practice setting bias was stronger, with ChatGPT and DeepSeek penalizing independent practitioners by 4.15 and 3.00 points, respectively, compared to hospital-employed peers (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u2009.001). Models also displayed inconsistent bias correction, with ChatGPT elevating scores for female (+\u20091.61) and Black-American (+\u20091.69) neurosurgeons while disadvantaging other groups (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u2009.001). This study provides evidence that LLMs incorporate distinct biases when evaluating neurosurgeons. As AI integration accelerates, uncritical adoption risks a self-reinforcing system where algorithmically preferred practitioners receive disproportionate advantages, independent of actual skills. These systems may also undermine global capacity-building by devaluing non-Western practitioners. Understanding and mitigating these biases is fundamental to responsibly navigating the intersection of medicine and AI.\n                  <\/jats:p>","DOI":"10.1007\/s43681-025-00860-z","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T11:20:25Z","timestamp":1764847225000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The algorithm will see you now: how AI evaluates neurosurgeons"],"prefix":"10.1007","volume":"6","author":[{"given":"Daniel","family":"Schneider","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ethan Devin Lockwood","family":"Brown","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Ward","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barnabas","family":"Obeng-Gyasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Sciubba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng-Fu","family":"Lo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"860_CR1","doi-asserted-by":"publisher","first-page":"100108","DOI":"10.1016\/j.glmedi.2024.100108","volume":"3","author":"DB Olawade","year":"2024","unstructured":"Olawade, D.B., David-Olawade, A.C., Wada, O.Z., et al.: Artificial intelligence in healthcare delivery: prospects and pitfalls. J. Med. Surg. Public Health 3, 100108 (2024). https:\/\/doi.org\/10.1016\/j.glmedi.2024.100108","journal-title":"J. Med. Surg. Public Health"},{"key":"860_CR2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1186\/s12909-025-06719-5","volume":"25","author":"E Feigerlova","year":"2025","unstructured":"Feigerlova, E., Hani, H., Hothersall-Davies, E.: A systematic review of the impact of artificial intelligence on educational outcomes in health professions education. BMC Med. Educ. 25, 129 (2025). https:\/\/doi.org\/10.1186\/s12909-025-06719-5","journal-title":"BMC Med. Educ."},{"key":"860_CR3","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1097\/ACM.0000000000005115","volume":"98","author":"GJ Booth","year":"2023","unstructured":"Booth, G.J., Ross, B., Cronin, W.A., et al.: Competency-based assessments: leveraging artificial intelligence to predict subcompetency content. Acad. Med. 98, 497 (2023). https:\/\/doi.org\/10.1097\/ACM.0000000000005115","journal-title":"Acad. Med."},{"key":"860_CR4","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1227\/neu.0000000000002632","volume":"93","author":"R Ali","year":"2023","unstructured":"Ali, R., Tang, O.Y., Connolly, I.D., et al.: Performance of ChatGPT and GPT-4 on neurosurgery written board examinations. Neurosurgery 93, 1353\u20131365 (2023). https:\/\/doi.org\/10.1227\/neu.0000000000002632","journal-title":"Neurosurgery"},{"key":"860_CR5","doi-asserted-by":"publisher","first-page":"e86","DOI":"10.1016\/j.wneu.2024.05.172","volume":"189","author":"EDL Brown","year":"2024","unstructured":"Brown, E.D.L., Ward, M., Maity, A., et al.: Enhancing diagnostic support for Chiari malformation and syringomyelia: a comparative study of contextualized ChatGPT models. World Neurosurg. 189, e86\u2013e107 (2024). https:\/\/doi.org\/10.1016\/j.wneu.2024.05.172","journal-title":"World Neurosurg."},{"key":"860_CR6","doi-asserted-by":"publisher","first-page":"362","DOI":"10.23736\/S0390-5616.25.06502-6","volume":"69","author":"ED Brown","year":"2025","unstructured":"Brown, E.D., Pelcher, I., Leon, S., et al.: Artificial intelligence applications in the screening and classification of glioblastoma. J. Neurosurg. Sci. 69, 362\u2013370 (2025). https:\/\/doi.org\/10.23736\/S0390-5616.25.06502-6","journal-title":"J. Neurosurg. Sci."},{"key":"860_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2025.07.014","author":"D Schneider","year":"2025","unstructured":"Schneider, D., Brown, E.D.L., Elsamadicy, A.A., et al.: The hidden cost of robotic spine surgery: real-world adverse events cause 58-minute delays and undermine economic viability. Spine J. (2025). https:\/\/doi.org\/10.1016\/j.spinee.2025.07.014","journal-title":"Spine J."},{"key":"860_CR8","doi-asserted-by":"publisher","DOI":"10.1097\/BRS.0000000000005492","author":"D Schneider","year":"2025","unstructured":"Schneider, D., Brown, E.D.L., Toscano, D., et al.: Expandable, but at what cost? Failure patterns in corpectomy cages from 373 real-world adverse events. Spine (2025). https:\/\/doi.org\/10.1097\/BRS.0000000000005492","journal-title":"Spine"},{"key":"860_CR9","doi-asserted-by":"publisher","first-page":"e769","DOI":"10.1016\/j.wneu.2024.04.165","volume":"187","author":"NA Shlobin","year":"2024","unstructured":"Shlobin, N.A., Ward, M., Shah, H.A., et al.: Ethical incorporation of artificial intelligence into neurosurgery: a generative pretrained transformer chatbot-based, human-modified approach. World Neurosurg. 187, e769\u2013e791 (2024). https:\/\/doi.org\/10.1016\/j.wneu.2024.04.165","journal-title":"World Neurosurg."},{"key":"860_CR10","doi-asserted-by":"publisher","first-page":"e273","DOI":"10.1016\/j.wneu.2024.09.086","volume":"192","author":"M Ward","year":"2024","unstructured":"Ward, M., Maity, A., Brown, E.D.L., et al.: Analysis of ChatGPT in the triage of common spinal complaints. World Neurosurg. 192, e273\u2013e280 (2024). https:\/\/doi.org\/10.1016\/j.wneu.2024.09.086","journal-title":"World Neurosurg."},{"key":"860_CR11","doi-asserted-by":"publisher","first-page":"e77561","DOI":"10.7759\/cureus.77561","volume":"17","author":"O Basubrin","year":"2025","unstructured":"Basubrin, O.: Current status and future of artificial intelligence in medicine. Cureus 17, e77561 (2025). https:\/\/doi.org\/10.7759\/cureus.77561","journal-title":"Cureus"},{"key":"860_CR12","doi-asserted-by":"publisher","first-page":"18005","DOI":"10.1007\/s11042-023-16029-x","volume":"83","author":"A Kumar","year":"2024","unstructured":"Kumar, A., Aelgani, V., Vohra, R., et al.: Artificial intelligence bias in medical system designs: a systematic review. Multimed. Tools Appl. 83, 18005\u201318057 (2024). https:\/\/doi.org\/10.1007\/s11042-023-16029-x","journal-title":"Multimed. Tools Appl."},{"key":"860_CR13","doi-asserted-by":"publisher","first-page":"105780","DOI":"10.1016\/j.ijmedinf.2024.105780","volume":"195","author":"M Mohsin Khan","year":"2025","unstructured":"Mohsin Khan, M., Shah, N., Shaikh, N., et al.: Towards secure and trusted AI in healthcare: a systematic review of emerging innovations and ethical challenges. Int. J. Med. Inf. 195, 105780 (2025). https:\/\/doi.org\/10.1016\/j.ijmedinf.2024.105780","journal-title":"Int. J. Med. Inf."},{"key":"860_CR14","doi-asserted-by":"publisher","first-page":"115","DOI":"10.51594\/csitrj.v3i3.1559","volume":"3","author":"OC Oyeniran","year":"2022","unstructured":"Oyeniran, O.C., Adewusi, A.O., Adeleke, A.G., et al.: Ethical AI: Addressing bias in machine learning models and software applications. Comput. Sci. IT Res. J. 3, 115\u2013126 (2022). https:\/\/doi.org\/10.51594\/csitrj.v3i3.1559","journal-title":"Comput. Sci. IT Res. J."},{"key":"860_CR15","doi-asserted-by":"publisher","DOI":"10.1148\/rg.230067","author":"AS Tejani","year":"2024","unstructured":"Tejani, A.S., Ng, Y.S., Xi, Y., Rayan, J.C.: Understanding and mitigating bias in imaging artificial intelligence. Radiographics (2024). https:\/\/doi.org\/10.1148\/rg.230067","journal-title":"Radiographics"},{"key":"860_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100347","author":"N Norori","year":"2021","unstructured":"Norori, N., Hu, Q., Aellen, F.M., et al.: Addressing bias in big data and AI for health care: a call for open science. Patterns (2021). https:\/\/doi.org\/10.1016\/j.patter.2021.100347","journal-title":"Patterns"},{"key":"860_CR17","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1007\/s00701-024-06061-7","volume":"166","author":"C Karekezi","year":"2024","unstructured":"Karekezi, C.: Global neurosurgery partnership: need for more adequate collaborations between high-income countries and low-income countries. Acta Neurochir. (Wien) 166, 176 (2024). https:\/\/doi.org\/10.1007\/s00701-024-06061-7","journal-title":"Acta Neurochir. (Wien)"},{"key":"860_CR18","doi-asserted-by":"publisher","first-page":"e217572","DOI":"10.14503\/THIJ-21-7572","volume":"49","author":"Z Krajcer","year":"2022","unstructured":"Krajcer, Z.: Artificial intelligence for education, proctoring, and credentialing in cardiovascular medicine. Tex. Heart Inst. J. 49, e217572 (2022). https:\/\/doi.org\/10.14503\/THIJ-21-7572","journal-title":"Tex. Heart Inst. J."},{"key":"860_CR19","doi-asserted-by":"publisher","DOI":"10.1056\/CAT.22.0187","author":"S Strongwater","year":"2022","unstructured":"Strongwater, S.: Physician practice consolidation: considerations for the remaining independents. NEJM Catal. Innov. Care Deliv. (2022). https:\/\/doi.org\/10.1056\/CAT.22.0187","journal-title":"NEJM Catal. Innov. Care Deliv."},{"key":"860_CR20","doi-asserted-by":"crossref","unstructured":"Dai T., & Abr\u00e0moff MD, Incorporating artificial intelligence into healthcare workflows: Models and insights. In: Tutorials in Operations Research: Advancing the Frontiers of OR\/MS: From Methodologies to Applications. pp. 133-155 (2023)","DOI":"10.1287\/educ.2023.0257"},{"key":"860_CR21","doi-asserted-by":"publisher","DOI":"10.1177\/02683962211010356","author":"O Marjanovic","year":"2021","unstructured":"Marjanovic, O., Cecez-Kecmanovic, D., Vidgen, R.: Algorithmic pollution: making the invisible visible. J. Inf. Technol. (2021). https:\/\/doi.org\/10.1177\/02683962211010356","journal-title":"J. Inf. Technol."},{"key":"860_CR22","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2025.1534139","author":"A Boshnjaku","year":"2025","unstructured":"Boshnjaku, A., Krasniqi, E., Kamberi, F.: The emerging need to integrate digital health literacy as a course into health-related and care-related profession curricula. Front. Public Health (2025). https:\/\/doi.org\/10.3389\/fpubh.2025.1534139","journal-title":"Front. Public Health"},{"key":"860_CR23","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1001\/jamasurg.2020.7208","volume":"156","author":"CN Johnson-Mann","year":"2021","unstructured":"Johnson-Mann, C.N., Loftus, T.J., Bihorac, A.: Equity and artificial intelligence in surgical care. JAMA Surg. 156, 509\u2013510 (2021). https:\/\/doi.org\/10.1001\/jamasurg.2020.7208","journal-title":"JAMA Surg."},{"key":"860_CR24","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","volume":"7","author":"RJ Chen","year":"2023","unstructured":"Chen, R.J., Wang, J.J., Williamson, D.F.K., et al.: Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat. Biomed. Eng. 7, 719\u2013742 (2023). https:\/\/doi.org\/10.1038\/s41551-023-01056-8","journal-title":"Nat. Biomed. Eng."},{"key":"860_CR25","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","volume":"20","author":"J Amann","year":"2020","unstructured":"Amann, J., Blasimme, A., Vayena, E., et al.: Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med. Inform. Decis. Mak. 20, 310 (2020). https:\/\/doi.org\/10.1186\/s12911-020-01332-6","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"860_CR26","doi-asserted-by":"crossref","unstructured":"Ng HKY, Chan LCH Revolutionizing Literature Search: AI vs. Traditional Methods in Digital Divide Literature Screening and Reviewing. In: 2024 6th International Workshop on Artificial Intelligence and Education (WAIE). pp 144\u2013148 (2024)","DOI":"10.1109\/WAIE63876.2024.00033"}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-025-00860-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-025-00860-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-025-00860-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T10:23:49Z","timestamp":1774261429000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43681-025-00860-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["860"],"URL":"https:\/\/doi.org\/10.1007\/s43681-025-00860-z","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"20 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study was considered exempt from IRB approval due to its use of synthetic, anonymized data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"34"}}