EUVIMEDEUVIMED entdecken
KommentarOpen Access

From Context to Care: Rethinking Stigma Detection in Clinical Language Models

Shefali Haldar iD, Oliver Bear Don't Walk Iv iD, Sadia Akter iD

JMIR Medical Informatics · 2025

DOI: 10.2196/82484 ↗

Kurz gefasst

Kommentar in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Shefali Haldar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Merck Research Laboratories, Merck & Co Inc, 33 Avenue Louis Pasteur, Boston, MA, 02115, United States. Hauptthemen laut MEDLINE: Electronic Health Records, Natural Language Processing, Social Stigma, Language. Die Arbeit nennt 7 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NLM NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural language processing techniques are useful for identifying stigmatizing language in electronic health records but require careful consideration. This commentary article builds on “ Efficient Detection of Stigmatizing Language in Electronic Health Records via In-Context Learning ” by Chen et al, which highlights the importance of incorporating situational and temporal contexts in annotation and modeling efforts. We emphasize the need for researchers to explicitly articulate their paradigms and positionality, particularly when working with populations disproportionately affected by stigmatizing language. We also explore the differences arising from conflicting preferences across communities about what constitutes destigmatizing language. We discuss participatory and trust-centered approaches for model development to work toward unbiased impact. Such strategies have a crucial role in raising awareness and fostering inclusive health care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsNatural Language ProcessingSocial StigmaLanguageStereotypingHumans

Stichwörter der Autor:innen

NLPcontext modelinghealth equityinclusive languagenatural language processing

Autor:innen und Institutionen

  • Merck Research Laboratories, Merck & Co Inc, 33 Avenue Louis Pasteur, Boston, MA, 02115, United States.
  • Department of Biomedical and Health Informatics, University of Washington, Seattle, WA, United States.
  • Department of Biomedical Sciences, Marshall University, Huntington, WV, United States.

ORCID-Profile: Shefali Haldar, Oliver Bear Don't Walk Iv, Sadia Akter

Förderung

  • NLM NIH HHS

Zitieren

APA

Haldar, S., Bear Don't Walk Iv, O., & Akter, S. (2025). From Context to Care: Rethinking Stigma Detection in Clinical Language Models. JMIR Medical Informatics. https://doi.org/10.2196/82484

Vancouver

Haldar S, Bear Don't Walk Iv O, Akter S. From Context to Care: Rethinking Stigma Detection in Clinical Language Models. JMIR Medical Informatics. 2025. doi:10.2196/82484

BibTeX
@article{Haldar2025,
  author = {Haldar, Shefali and Bear Don't Walk Iv, Oliver and Akter, Sadia},
  title = {From Context to Care: Rethinking Stigma Detection in Clinical Language Models},
  journal = {JMIR Medical Informatics},
  year = {2025},
  doi = {10.2196/82484}
}
Kostenlos starten →