EUVIMEDEUVIMED entdecken
Open Access

Evaluating for Evidence of Sociodemographic Bias in Conversational AI for Mental Health Support

Yee Hui Yeo iD, Yuxin Peng, Muskaan Mehra, Jamil Samaan, Joshua Hakimian, Allistair Clark, Karisma Suchak, Zoe Krut, Taiga Andersson, Susan Persky iD, Omer Liran, Brennan Spiegel

Cyberpsychology, Behavior, and Social Networking · 2025

DOI: 10.1089/cyber.2024.0199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cyberpsychology, Behavior, and Social Networking, 2025. Verfasst von Yee Hui Yeo und 11 weiteren Autor:innen. Beteiligte Einrichtung: Karsh Division of Gastroenterology and Hepatology, Cedars-Sinai Medical Center, Los Angeles, California, USA. Hauptthemen laut MEDLINE: Communication, Physician-Patient Relations, Mental Health Services. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of large language models (LLMs) into healthcare highlights the need to ensure their efficacy while mitigating potential harms, such as the perpetuation of biases. Current evidence on the existence of bias within LLMs remains inconclusive. In this study, we present an approach to investigate the presence of bias within an LLM designed for mental health support. We simulated physician–patient conversations by using a communication loop between an LLM-based conversational agent and digital standardized patients (DSPs) that engaged the agent in dialogue while remaining agnostic to sociodemographic characteristics. In contrast, the conversational agent was made aware of each DSP’s characteristics, including age, sex, race/ethnicity, and annual income. The agent’s responses were analyzed to discern potential systematic biases using the Linguistic Inquiry and Word Count tool. Multivariate regression analysis, trend analysis, and group-based trajectory models were used to quantify potential biases. Among 449 conversations, there was no evidence of bias in both descriptive assessments and multivariable linear regression analyses. Moreover, when evaluating changes in mean tone scores throughout a dialogue, the conversational agent exhibited a capacity to show understanding of the DSPs’ chief complaints and to elevate the tone scores of the DSPs throughout conversations. This finding did not vary by any sociodemographic characteristics of the DSP. Using an objective methodology, our study did not uncover significant evidence of bias within an LLM-enabled mental health conversational agent. These findings offer a complementary approach to examining bias in LLM-based conversational agents for mental health support.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CommunicationPhysician-Patient RelationsMental Health ServicesHumansMaleFemaleAdultMiddle AgedMental HealthLanguageSociodemographic Factors

Stichwörter der Autor:innen

artificial intelligencebiasdisparitylarge language modellinguistic inquiry and word countmental health

Autor:innen und Institutionen

  • Karsh Division of Gastroenterology and Hepatology, Cedars-Sinai Medical Center, Los Angeles, California, USA.
  • School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China.
  • Division of Health Services Research, Cedars-Sinai Medical Center, Center for Outcomes Research and Education (CS-CORE), Los Angeles, California, USA.
  • Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.
  • Social and Behavioral Research Branch, National Human Genome Research Institute, Bethesda, Maryland, USA.

ORCID-Profile: Yee Hui Yeo, Susan Persky

Zitieren

APA

Yeo, Y. H., Peng, Y., Mehra, M., Samaan, J., Hakimian, J., Clark, A., Suchak, K., Krut, Z., Andersson, T., Persky, S., Liran, O., & Spiegel, B. (2025). Evaluating for Evidence of Sociodemographic Bias in Conversational AI for Mental Health Support. Cyberpsychology, Behavior, and Social Networking. https://doi.org/10.1089/cyber.2024.0199

Vancouver

Yeo YH, Peng Y, Mehra M, Samaan J, Hakimian J, Clark A, et al. Evaluating for Evidence of Sociodemographic Bias in Conversational AI for Mental Health Support. Cyberpsychology, Behavior, and Social Networking. 2025. doi:10.1089/cyber.2024.0199

BibTeX
@article{Yeo2025,
  author = {Yeo, Yee Hui and Peng, Yuxin and Mehra, Muskaan and Samaan, Jamil and Hakimian, Joshua and Clark, Allistair and Suchak, Karisma and Krut, Zoe and Andersson, Taiga and Persky, Susan and Liran, Omer and Spiegel, Brennan},
  title = {Evaluating for Evidence of Sociodemographic Bias in Conversational AI for Mental Health Support},
  journal = {Cyberpsychology, Behavior, and Social Networking},
  year = {2025},
  doi = {10.1089/cyber.2024.0199}
}
Kostenlos starten →