EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Context is all you need: A causal framework for governing bias in clinical AI

Alon Gorenshtein iD, Mahmud Omar, Yiftach Barash, Girish N Nadkarni, Eyal Klang

PLOS Digital Health · 06.11.2026 · 5 (11) · e0001819

DOI: 10.1371/journal.pdig.0001819 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 06.11.2026. Verfasst von Alon Gorenshtein und 4 weiteren Autor:innen. Beteiligte Einrichtung: BRIDGE GenAI Lab, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NCATS NIH HHS, NIH Office of Research Infrastructure.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Clinical AI systems can produce different recommendations when a patient’s race, income, housing status, or gender identity changes, but a differential alone does not establish unjustified bias. What separates a clinically justified differential from an unjustified one is not its size or direction but its origin: whether the feature acts through a clinically justified pathway, or marks how patients of that group have been treated. That distinction is causal, and a model trained only to detect statistical association records that a feature carries information but never why. Existing evidence does not establish reliable recovery of this adjudication inside that model; we therefore argue for explicit causal and normative supervision, whether supplied by an external layer, built into training, or both. We set out a six-criterion rubric, four approaches to implementing it, and a two-sided evaluation reporting preserved clinical sensitivity alongside reduced bias.

Autor:innen und Institutionen

  • BRIDGE GenAI Lab, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America.
  • Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America.
  • The Windreich Department of Artificial Intelligence and Human Health, Mount Sinai Medical Center, New York, New York, United States of America.
  • The Hasso Plattner Institute for Digital Health at Mount Sinai, Mount Sinai Health System, New York, New York, United States of America.
  • Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America.
  • The Charles Bronfman Institute for Personalized Medicine at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York City, New York, United States of America.

ORCID-Profile: Alon Gorenshtein

Förderung

  • NIH HHS
  • NCATS NIH HHS
  • NIH Office of Research Infrastructure

Zitieren

APA

Gorenshtein, A., Omar, M., Barash, Y., Nadkarni, G. N., & Klang, E. (2026). Context is all you need: A causal framework for governing bias in clinical AI. PLOS Digital Health, 5(11), e0001819. https://doi.org/10.1371/journal.pdig.0001819

Vancouver

Gorenshtein A, Omar M, Barash Y, Nadkarni GN, Klang E. Context is all you need: A causal framework for governing bias in clinical AI. PLOS Digital Health. 2026;5(11):e0001819. doi:10.1371/journal.pdig.0001819

BibTeX
@article{Gorenshtein2026,
  author = {Gorenshtein, Alon and Omar, Mahmud and Barash, Yiftach and Nadkarni, Girish N and Klang, Eyal},
  title = {Context is all you need: A causal framework for governing bias in clinical AI},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {11},
  pages = {e0001819},
  doi = {10.1371/journal.pdig.0001819}
}
Kostenlos starten →