EUVIMEDEUVIMED entdecken
Crossref

Sociodemographic bias in LLMs’ clinical decision-making for dizziness

Idit Tessler iD, Mahmud Omar, Amit Wolfovitz, Yoav Gimmon, Sholem Hack iD, Noa Rozendorn iD, Nir Livneh, Eyal Klang

Journal of Vestibular Research · 08.08.2026

DOI: 10.1177/09574271261474218 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Vestibular Research, online erschienen am 08.08.2026. Verfasst von Idit Tessler und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology and Head and Neck Surgery, Sheba Medical Center, Tel-Hashomer, Israel. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

As large language models (LLMs) enter clinical decision support, concerns persist about sociodemographic bias. We assessed whether LLM recommendations for dizziness vary by patient descriptors and clinical detail.

Methods

We conducted a cross-randomized in-silico vignette study. One hundred synthetic emergency department dizziness cases were created using established diagnostic frameworks including the TiTrATE paradigm, SAEM GRACE-3 guidelines, and Bárány Society diagnostic criteria. Each vignette was tested in a neutral form and with 33 sociodemographic descriptor variants (34 total). Twelve instruction-tuned LLMs from multiple model families were evaluated. Models answered five binary clinical decision questions addressing etiology classification, triage disposition, neuroimaging, bedside vestibular examination, and mental health referral. Each model–vignette–descriptor combination was repeated 10 times, yielding 2,040,000 responses. Sociodemographic bias was quantified as descriptor-specific percentage-point deviations from neutral control recommendations with 95% confidence intervals.

Results

Sociodemographic descriptors influenced LLM recommendations, with the largest differences observed for mental health referral decisions in diagnostically ambiguous cases. Referral likelihood was lower for Black transgender women (−12.2 pp; 95% CI −14.0 to −10.3), Black patients experiencing homelessness (−9.1 pp; −11.0 to −7.3), and patients experiencing homelessness (−7.7 pp; −9.5 to −5.9). Differences were attenuated when vignettes contained clearer diagnostic information. Other effects were smaller, including increased neuroimaging recommendations for low-income descriptors (+4.0 pp; 95% CI 2.1–5.8).

Conclusion

LLM clinical recommendations varied by sociodemographic descriptors, particularly under diagnostic uncertainty. More detailed clinical information reduced these disparities, suggesting structured inputs may mitigate bias in clinical AI systems.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligenceclinical decision-makingdiagnostic biasdizzinesshealthcare disparitieslarge language modelssociodemographic factorsvertigo

Autor:innen und Institutionen

  • Department of Otolaryngology and Head and Neck Surgery, Sheba Medical Center, Tel-Hashomer, Israel.
  • Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
  • The Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, NY, USA.
  • Department of Physical Therapy, Faculty of Social Welfare & Health Sciences, University of Haifa, Haifa, Israel.
  • City St George's University London School of Medicine, Program Delivered by University of Nicosia at the Chaim Sheba Medical Center, Ramat Gan, Israel.

ORCID-Profile: Idit Tessler, Sholem Hack, Noa Rozendorn

Zitieren

APA

Tessler, I., Omar, M., Wolfovitz, A., Gimmon, Y., Hack, S., Rozendorn, N., Livneh, N., & Klang, E. (2026). Sociodemographic bias in LLMs’ clinical decision-making for dizziness. Journal of Vestibular Research. https://doi.org/10.1177/09574271261474218

Vancouver

Tessler I, Omar M, Wolfovitz A, Gimmon Y, Hack S, Rozendorn N, et al. Sociodemographic bias in LLMs’ clinical decision-making for dizziness. Journal of Vestibular Research. 2026. doi:10.1177/09574271261474218

BibTeX
@article{Tessler2026,
  author = {Tessler, Idit and Omar, Mahmud and Wolfovitz, Amit and Gimmon, Yoav and Hack, Sholem and Rozendorn, Noa and Livneh, Nir and Klang, Eyal},
  title = {Sociodemographic bias in LLMs’ clinical decision-making for dizziness},
  journal = {Journal of Vestibular Research},
  year = {2026},
  doi = {10.1177/09574271261474218}
}
Kostenlos starten →