Identifying Bias at Scale in Clinical Notes Using Large Language Models
The study showed that GPT-4 accurately detects biased language in clinical notes, identifies modifiable contributors to that bias, and delivers physician-endorsed revisions. This approach may help mitigate documentation bias and reduce disparities in care.
Authors
- Arash Negahdari Kia (ORCID: https://orcid.org/0000-0002-3675-0239)
- Donald U. Apakama (ORCID: https://orcid.org/0000-0001-6217-1620)
- Kim-Anh-Nhi Nguyen (ORCID: https://orcid.org/0000-0002-3446-9750)
- Rebecca Anderson (ORCID: https://orcid.org/0000-0001-8925-7002)
- Rohan Khera (ORCID: https://orcid.org/0000-0001-9467-6199)
- Patricia Kovatch (ORCID: https://orcid.org/0000-0001-8368-1742)
- Allison Glasser (ORCID: https://orcid.org/0000-0002-6582-2684)
- Prem Timsina (ORCID: https://orcid.org/0000-0002-6047-887X)
- Brendan G. Carr (ORCID: https://orcid.org/0000-0002-9147-9701)
- Clair Kronk (ORCID: https://orcid.org/0000-0001-8397-8810)
- Prathamesh Parchure (ORCID: https://orcid.org/0009-0001-9383-691X)
- Eyal Klang (ORCID: https://orcid.org/0000-0002-4567-3108)
- Girish N. Nadkarni (ORCID: https://orcid.org/0000-0001-6319-4314)
- Masoud Edalati (ORCID: https://orcid.org/0000-0002-1132-9480)
- Lili Chan (ORCID: https://orcid.org/0000-0003-4300-5760)
- Robert Freeman (ORCID: https://orcid.org/0000-0003-4946-6533)
- Lynne D. Richardson (ORCID: https://orcid.org/0000-0002-5425-1601)
- Shelly Soffer (ORCID: https://orcid.org/0000-0002-7853-2029)
- Matthew A. Levin (ORCID: https://orcid.org/0000-0002-6013-2684)
- Alexander W. Charney (ORCID: https://orcid.org/0000-0001-8135-6858)
- Aya Mudrik (ORCID: https://orcid.org/0009-0002-3429-9242)
- Allon E. Moses (ORCID: https://orcid.org/0000-0003-2077-5754)
- Carol R. Horowitz
- E. Ling (ORCID: https://orcid.org/0009-0007-9036-0411)
- Evajoyce Woullard
- Daphnee Hyppolite
- Ivanka Temnycky
Institutions
- Ben-Gurion University of the Negev (IL)
- Mount Sinai Health System (US)
- Rabin Medical Center (IL)
- Yale University (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Mayo Clinic Proceedings Digital Health
- Published
- 2025-10-15
- DOI
- https://doi.org/10.1016/j.mcpdig.2025.100296
- Citations
- 1
- Primary Topic
- Health Promotion and Cardiovascular Prevention
- Type
- article
- Field-Weighted Citation Impact
- 1.88