EUVIMEDEUVIMED entdecken
Open Access

Sociodemographic bias in large language model clinical trial screening

Shelly Soffer iD, Mahmud Omar iD, Orly Efros, Donald U Apakama iD, Aya Mudrik iD, Robert Freeman iD, Girish N Nadkarni, Eyal Klang

Journal of the American Medical Informatics Association · 2026

DOI: 10.1093/jamia/ocag058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2026. Verfasst von Shelly Soffer und 7 weiteren Autor:innen. Beteiligte Einrichtung: Rabin Medical Center: 39 Jabotinski St., Petah Tikva 49100, Israel. Hauptthemen laut MEDLINE: Large Language Models, Randomized Controlled Trials as Topic, Eligibility Determination, Patient Selection. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Clinical and Translational Science Awards (CTSA), NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To assess whether large language model (LLM)-based clinical trial screening judgments vary by patient sociodemographic characteristics. Materials and Methods We conducted a cross-sectional evaluation of Phase II-III US adult randomized controlled trial (RCT) protocols (2023-2024). Physician-validated clinical vignettes were evaluated in a control version and 33 sociodemographic identity variants differing only by labels. Nine LLMs assessed eligibility and related domains. Mixed-effects models estimated adjusted differences vs control.

Results

Across 58 protocols and 5.3 million evaluations, eligibility judgments were largely stable across identities. Race and ethnicity showed minimal effects after accounting for socioeconomic status. Homelessness produced the largest negative eligibility shift and pronounced effects in adherence, resources, and trust. Discussion and Conclusion LLMs applied explicit eligibility criteria consistently, but disparities emerged in domains requiring inference about behavior or resources, underscoring the need for careful deployment to promote fair trial access.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsRandomized Controlled Trials as TopicEligibility DeterminationPatient SelectionHumansCross-Sectional StudiesSociodemographic FactorsAdultBias

Stichwörter der Autor:innen

clinical trial screeninglarge language models (LLMs)randomized controlled trials (RCTs)sociodemographic bias

Autor:innen und Institutionen

  • Rabin Medical Center: 39 Jabotinski St., Petah Tikva 49100, Israel.
  • Gray School of Medicine, Tel Aviv University, Tel Aviv, 69978, Israel.
  • Windreich Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY 10029, United States.
  • Department of Medicine, Icahn School of Medicine at Mount Sinai, The Hasso Plattner Institute for Digital Health at Mount Sinai, New York, NY 10019, United States.
  • National Hemophilia Center and Thrombosis & Hemostasis Institute, Sheba Medical Center, Ramat Gan, 52621, Israel.
  • Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, United States.

ORCID-Profile: Shelly Soffer, Mahmud Omar, Donald U Apakama, Aya Mudrik, Robert Freeman

Förderung

  • Clinical and Translational Science Awards (CTSA)
  • NCATS NIH HHS

Zitieren

APA

Soffer, S., Omar, M., Efros, O., Apakama, D. U., Mudrik, A., Freeman, R., Nadkarni, G. N., & Klang, E. (2026). Sociodemographic bias in large language model clinical trial screening. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag058

Vancouver

Soffer S, Omar M, Efros O, Apakama DU, Mudrik A, Freeman R, et al. Sociodemographic bias in large language model clinical trial screening. Journal of the American Medical Informatics Association. 2026. doi:10.1093/jamia/ocag058

BibTeX
@article{Soffer2026,
  author = {Soffer, Shelly and Omar, Mahmud and Efros, Orly and Apakama, Donald U and Mudrik, Aya and Freeman, Robert and Nadkarni, Girish N and Klang, Eyal},
  title = {Sociodemographic bias in large language model clinical trial screening},
  journal = {Journal of the American Medical Informatics Association},
  year = {2026},
  doi = {10.1093/jamia/ocag058}
}
Kostenlos starten →