{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:06:59Z","timestamp":1789081619205,"version":"build-2803163510"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["F30 MD020264"],"award-info":[{"award-number":["F30 MD020264"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Gender disparities in academic medicine have been previously reported, but prior analyses have relied on either manual labor or fixed databases of name-gender pairs that fail to generalize across different populations and cultures. The objective of this work is to evaluate the utility of large language models (LLMs) as a potential tool to facilitate systematic bibliometric analysis of academic research trends.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We introduce an LLM-based pipeline that aggregates gender labels from multiple LLM instances to predict the genders of manuscript authors based on their first names.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our proposed method outperforms alternative algorithms relying on lookup from finite databases of name-gender pairs, while also offering the scalability to tens of millions of authors that is unfeasible with other manual, human-based methods alone.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion and Conclusion<\/jats:title>\n                    <jats:p>Our results suggest that LLMs can be a powerful tool to scalably track gender-based trends in academic medical research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooag173","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T11:56:00Z","timestamp":1786017360000},"source":"Crossref","is-referenced-by-count":0,"title":["Large language model-based evaluation of the impact of gender in medical research"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7008-6028","authenticated-orcid":false,"given":"Michael S","family":"Yao","sequence":"first","affiliation":[{"name":"University of Pennsylvania Perelman School of Medicine, , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"2026091018123992300_ooag173-B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3122\/jabfm.2022.AP.220122","article-title":"Race and gender disparities among leadership in academic family medicine","volume":"38","author":"Adetoye","year":"2022","journal-title":"J Am Board Fam Med"},{"key":"2026091018123992300_ooag173-B2","doi-asserted-by":"publisher","first-page":"e2114509","DOI":"10.1001\/jamanetworkopen.2021.14509","article-title":"Gender disparity in citations in high-impact journal articles","volume":"4","author":"Chatterjee","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2026091018123992300_ooag173-B3","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1001\/jamasurg.2018.0040","article-title":"Association of author gender with sex bias in surgical research","volume":"153","author":"Xiao","year":"2018","journal-title":"JAMA Surg"},{"key":"2026091018123992300_ooag173-B4","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41390-022-02010-1","article-title":"Gender disparities in pediatric research: a descriptive bibliometric study on scientific authorships","volume":"92","author":"B\u00f6hme","year":"2022","journal-title":"Pediatr Res"},{"key":"2026091018123992300_ooag173-B5","doi-asserted-by":"publisher","first-page":"1714","DOI":"10.1016\/j.acra.2022.10.031","article-title":"Gender disparities in academic radiology authorship: a 13-year review","volume":"30","author":"Xiao","year":"2023","journal-title":"Acad Radiol"},{"key":"2026091018123992300_ooag173-B6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.2214\/AJR.15.15116","article-title":"Gender trends in radiology authorship: a 35-year analysis","volume":"206","author":"Piper","year":"2016","journal-title":"Am J Roentgenol"},{"key":"2026091018123992300_ooag173-B7","doi-asserted-by":"publisher","first-page":"831","DOI":"10.2214\/AJR.18.19741","article-title":"Influences for gender disparity in the radiology societies in North America","volume":"211","author":"Hamidizadeh","year":"2018","journal-title":"Am J Roentgenol"},{"key":"2026091018123992300_ooag173-B8","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1016\/j.acra.2020.08.004","article-title":"National Institutes of Health: gender differences in radiology funding","volume":"29","author":"Jutras","year":"2022","journal-title":"Acad Radiol"},{"key":"2026091018123992300_ooag173-B9","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1016\/j.acra.2021.05.016","article-title":"Academic radiology in the United States: defining gender disparities in faculty leadership and academic rank","volume":"29","author":"Goswami","year":"2022","journal-title":"Acad Radiol"},{"key":"2026091018123992300_ooag173-B10","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1016\/j.jacr.2020.03.019","article-title":"Trends in gender and racial profiles of US academic radiology faculty","volume":"17","author":"Niu","year":"2020","journal-title":"J Am Coll Radiol"},{"key":"2026091018123992300_ooag173-B11","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1161\/STROKEAHA.119.027016","article-title":"Females are less likely invited speakers to the International Stroke Conference: time\u2019s up to address sex disparity","volume":"51","author":"Fournier","year":"2020","journal-title":"Stroke"},{"key":"2026091018123992300_ooag173-B12","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1001\/jamainternmed.2016.9646","article-title":"Representation of women among academic grand rounds speakers","volume":"177","author":"Boiko","year":"2017","journal-title":"JAMA Intern Med"},{"key":"2026091018123992300_ooag173-B13","doi-asserted-by":"publisher","first-page":"11809","DOI":"10.5555\/3666122.3666639","article-title":"Tree of thoughts: deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"2026091018123992300_ooag173-B14","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.5555\/3495724.3495883","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"2026091018123992300_ooag173-B15","doi-asserted-by":"publisher","first-page":"100378","DOI":"10.1016\/j.health.2024.100378","article-title":"An automated information extraction model for unstructured discharge letters using large language models and GPT-4","volume":"7","author":"Siepmann","year":"2025","journal-title":"Healthc Anal"},{"key":"2026091018123992300_ooag173-B16","doi-asserted-by":"publisher","first-page":"e243659","DOI":"10.1148\/radiol.243659","article-title":"Effective structured information extraction from chest radiography reports using open-weights large language models","volume":"314","author":"Gee","year":"2025","journal-title":"Radiol"},{"key":"2026091018123992300_ooag173-B17","doi-asserted-by":"publisher","first-page":"e101139","DOI":"10.1136\/bmjhci-2024-101139","article-title":"Large language models for data extraction from unstructured and semi-structured electronic health records: a multiple model performance evaluation","volume":"32","author":"Ntinopoulos","year":"2025","journal-title":"BMJ Health Care Inf"},{"key":"2026091018123992300_ooag173-B18","author":"National Library of Medicine","year":"2025"},{"key":"2026091018123992300_ooag173-B19","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3174\/ajnr.A5443","article-title":"Influences for gender disparity in academic neuroradiology","volume":"39","author":"Ahmadi","year":"2018","journal-title":"Am J Neuroradiol"},{"key":"2026091018123992300_ooag173-B20","doi-asserted-by":"publisher","first-page":"e2220726120","DOI":"10.1073\/pnas.2220726120","article-title":"Predicting implicit attitudes with natural language data","volume":"120","author":"Bhatia","year":"2023","journal-title":"Proc. Natl. Acad. Sci. U S A"},{"key":"2026091018123992300_ooag173-B21","doi-asserted-by":"publisher","first-page":"930","DOI":"10.18653\/v1\/2024.emnlp-main.54","volume-title":"Pitalic","author":"Tan","year":"2024"},{"key":"2026091018123992300_ooag173-B22","doi-asserted-by":"publisher","first-page":"470","DOI":"10.18653\/v1\/2025.naacl-industry.39","author":"Nalbandyan","year":"2025"},{"key":"2026091018123992300_ooag173-B23","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.18653\/v1\/2024.findings-emnlp.108","volume-title":"Findings","author":"Zhuo","year":"2024"},{"key":"2026091018123992300_ooag173-B24","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar","year":"2024","journal-title":"Nature"},{"key":"2026091018123992300_ooag173-B25","doi-asserted-by":"publisher","first-page":"11004","DOI":"10.18653\/v1\/2024.emnlp-main.617","author":"Wahle","year":"2024"},{"key":"2026091018123992300_ooag173-B26","volume-title":"Proceedings of the","author":"Kuhn","year":"2023"},{"key":"2026091018123992300_ooag173-B27","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.18653\/v1\/P19-1610","author":"Gan","year":"2019"},{"key":"2026091018123992300_ooag173-B28","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.1038\/s41597-025-06276-y","article-title":"An open dataset of chinese name-to-gender associations for gender prediction in broad scientific research","volume":"12","author":"Shi","year":"2025","journal-title":"Sci Data"},{"key":"2026091018123992300_ooag173-B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.34667\/tind.43980","article-title":"Expanding the world gender-name dictionary: WGND 2.0","volume":"64","author":"Mart\u00ednez","year":"2021","journal-title":"Econ Work Pap"},{"key":"2026091018123992300_ooag173-B30","author":"Elmas","year":"2013"},{"key":"2026091018123992300_ooag173-B31","doi-asserted-by":"crossref","first-page":"17","DOI":"10.32614\/RJ-2016-002","article-title":"Gender prediction methods based on first names with genderizeR","volume":"8","author":"Wais","year":"2016","journal-title":"R J"},{"key":"2026091018123992300_ooag173-B32","author":"Klaver","year":"2025"},{"key":"2026091018123992300_ooag173-B33","author":"R4r_gender","year":"2026"},{"key":"2026091018123992300_ooag173-B34","author":"Wydma\u0144ski","year":"2026"},{"key":"2026091018123992300_ooag173-B35","doi-asserted-by":"publisher","first-page":"75","DOI":"10.18848\/2575-5544\/CGP\/v09i02\/75-95","article-title":"Un dataset internacional acerca de nombres, g\u00e9nero y frecuencias en Damegender: contando hombres y mujeres en Debian GNU\/Linux","volume":"9","author":"Men\u00e9ndez","year":"2023","journal-title":"Rev Int Aprendiz"},{"key":"2026091018123992300_ooag173-B36","doi-asserted-by":"publisher","author":"OpenAI","year":"2025","DOI":"10.48550\/arXiv.2508.10925"},{"key":"2026091018123992300_ooag173-B37","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1186\/1471-2164-15-875","article-title":"Cohen\u2019s h for detection of disease association with rare genetic variants","volume":"15","author":"Wen","year":"2014","journal-title":"BMC Genomics"},{"key":"2026091018123992300_ooag173-B38","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"Cohen","year":"2013"},{"key":"2026091018123992300_ooag173-B39","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1177\/00131644241278928","article-title":"Interpretation of the standardized mean difference effect size when distributions are not normal or homoscedastic","volume":"85","author":"Hedges","year":"2025","journal-title":"Educ Psychol Meas"},{"key":"2026091018123992300_ooag173-B40","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1186\/s13054-025-05649-4","article-title":"Female first and senior authorship in high-impact critical care journals 2005-2024","volume":"29","author":"Bruns","year":"2025","journal-title":"Crit Care"},{"key":"2026091018123992300_ooag173-B41","doi-asserted-by":"publisher","first-page":"e2022014","DOI":"10.29392\/001c.33616","article-title":"Geography, gender, and collaboration trends among global health authors","volume":"6","author":"Yao","year":"2022","journal-title":"J Glob Health Rep"},{"key":"2026091018123992300_ooag173-B42","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.jacr.2018.08.024","article-title":"Authorship and impact of gender-specific research in major radiology journals","volume":"16","author":"Campbell","year":"2019","journal-title":"J Am Coll Radiol"},{"key":"2026091018123992300_ooag173-B43","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1056\/NEJMsa053910","article-title":"The \u201cgender gap\u201d in authorship of academic medical literature - a 35-year perspective","volume":"355","author":"Jagsi","year":"2006","journal-title":"N Engl J Med"},{"key":"2026091018123992300_ooag173-B44","doi-asserted-by":"publisher","first-page":"e75098","DOI":"10.7759\/cureus.75098","article-title":"What are the trends in women\u2019s representation among principal investigators of US clinical trials in the field of genetics?","volume":"16","author":"Karimi","year":"2024","journal-title":"Cureus"},{"key":"2026091018123992300_ooag173-B45","doi-asserted-by":"publisher","first-page":"885275","DOI":"10.3389\/fonc.2022.885275","article-title":"Trends in women\u2019s leadership of oncology clinical trials","volume":"12","author":"Waldhorn","year":"2022","journal-title":"Front Oncol"},{"key":"2026091018123992300_ooag173-B46","doi-asserted-by":"publisher","first-page":"i847","DOI":"10.1136\/bmj.i847","article-title":"Trends and comparison of female first authorship in high impact medical journals: observational study (1994-2014)","volume":"352","author":"Filardo","year":"2016","journal-title":"BMJ"},{"key":"2026091018123992300_ooag173-B47","doi-asserted-by":"publisher","first-page":"101118","DOI":"10.1016\/j.patter.2024.101118","article-title":"A survey of multilingual large language models","volume":"6","author":"Qin","year":"2025","journal-title":"Patterns"},{"key":"2026091018123992300_ooag173-B48","doi-asserted-by":"publisher","first-page":"e58329","DOI":"10.2196\/58329","article-title":"Evaluation framework of large language models in medical documentation: development and usability study","volume":"26","author":"Seo","year":"2024","journal-title":"J Med Internet Res."},{"key":"2026091018123992300_ooag173-B49","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1093\/tbm\/ibad014","article-title":"Gender as a social and structural variable: research perspectives from the National Institutes of Health (NIH)","volume":"14","author":"Barr","year":"2024","journal-title":"Transl Behav Med"},{"key":"2026091018123992300_ooag173-B50","doi-asserted-by":"publisher","first-page":"111503","DOI":"10.1016\/j.compbiomed.2026.111503","article-title":"Gender-based data bias and model fairness evaluation in benchmarked open-access disease prediction datasets","volume":"203","author":"Uddin","year":"2026","journal-title":"Comput Biol Med"},{"key":"2026091018123992300_ooag173-B51","doi-asserted-by":"publisher","first-page":"103216","DOI":"10.1016\/j.artmed.2025.103216","article-title":"Toward fair medical advice: addressing and mitigating bias in large language model-based healthcare applications","volume":"168","author":"Lu","year":"2025","journal-title":"Artif Intell Med"},{"key":"2026091018123992300_ooag173-B52","doi-asserted-by":"publisher","first-page":"5653","DOI":"10.18653\/v1\/2025.findings-emnlp.303","author":"Kang","year":"2025"},{"key":"2026091018123992300_ooag173-B53","doi-asserted-by":"publisher","first-page":"4363","DOI":"10.18653\/v1\/2024.findings-acl.259","author":"Huang","year":"2024"},{"key":"2026091018123992300_ooag173-B54","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1038\/s41746-025-02250-5","article-title":"Multi-step retrieval and reasoning improves radiology question answering with large language models","volume":"8","author":"Wind","year":"2025","journal-title":"NPJ Digit Med"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/5\/ooag173\/71022830\/ooag173.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/5\/ooag173\/71022830\/ooag173.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:12:56Z","timestamp":1789078376000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooag173\/8790213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":54,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,9]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooag173","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,9,9]]},"article-number":"ooag173"}}