Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma

David Villarreal-Zegarra; C. Mahony Reategui-Rivera; Yscenia Paredes-Gonzales; Gianfranco Centeno-Terrazas; Joseph Finkelstein

doi:10.3233/SHTI250661

Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma

David Villarreal-Zegarra, C. Mahony Reategui-Rivera, Yscenia Paredes-Gonzales, Gianfranco Centeno-Terrazas, Joseph Finkelstein

Producción científica: Libro o Capítulo del libro › Contribución a la conferencia › revisión exhaustiva

Resumen

This study evaluated GPT-based conversational agents in tasks related to healthcare provider stigma. The main finding was that GPT-4o models, using Role-Playing (RP) and Chain of Thought (CoT) techniques, outperformed other models in tasks such as defining healthcare provider stigma, identifying types of stigma, and explaining its consequences. The Personalized GPT model showed lower performance, particularly in areas related to treatment access, adherence, and stigma risk factors. These results suggest that advanced prompting techniques significantly enhance the agent’s ability to deliver complex and nuanced information about healthcare provider stigma. The study supports the potential of GPT-based agents as scalable educational tools for reducing stigma, especially in resource-limited settings.

Idioma original	Inglés estadounidense
Título de la publicación alojada	Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics
Editores	John Mantas, Arie Hasman, Parisis Gallos, Emmanouil Zoulias, Konstantinos Karitis
Editorial	IOS Press BV
Páginas	4-8
-	5
ISBN (versión digital)	9781643686004
DOI	https://doi.org/10.3233/SHTI250661
Estado	Indizado - 26 jun. 2025
Publicado de forma externa	Sí
Evento	23rd Annual International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2025 - Athens, Grecia Duración: 4 jul. 2025 → 6 jul. 2025

Serie de la publicación

Nombre	Studies in Health Technology and Informatics
Volumen	328
ISSN (versión impresa)	0926-9630
ISSN (versión digital)	1879-8365

Conferencia

Conferencia	23rd Annual International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2025
País/Territorio	Grecia
Ciudad	Athens
Período	4/07/25 → 6/07/25

Nota bibliográfica

Publisher Copyright:
© 2025 The Authors.

Acceder al documento

10.3233/SHTI250661

Citar esto

Villarreal-Zegarra, D., Reategui-Rivera, C. M., Paredes-Gonzales, Y., Centeno-Terrazas, G., & Finkelstein, J. (2025). Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma. En J. Mantas, A. Hasman, P. Gallos, E. Zoulias, & K. Karitis (Eds.), Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics (pp. 4-8). (Studies in Health Technology and Informatics; Vol. 328). IOS Press BV. https://doi.org/10.3233/SHTI250661

Villarreal-Zegarra, David ; Reategui-Rivera, C. Mahony ; Paredes-Gonzales, Yscenia et al. / Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma. Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics. editor / John Mantas ; Arie Hasman ; Parisis Gallos ; Emmanouil Zoulias ; Konstantinos Karitis. IOS Press BV, 2025. pp. 4-8 (Studies in Health Technology and Informatics).

@inproceedings{eb77745f37fa47089a95dfccaf085bc8,

title = "Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma",

abstract = "This study evaluated GPT-based conversational agents in tasks related to healthcare provider stigma. The main finding was that GPT-4o models, using Role-Playing (RP) and Chain of Thought (CoT) techniques, outperformed other models in tasks such as defining healthcare provider stigma, identifying types of stigma, and explaining its consequences. The Personalized GPT model showed lower performance, particularly in areas related to treatment access, adherence, and stigma risk factors. These results suggest that advanced prompting techniques significantly enhance the agent{\textquoteright}s ability to deliver complex and nuanced information about healthcare provider stigma. The study supports the potential of GPT-based agents as scalable educational tools for reducing stigma, especially in resource-limited settings.",

keywords = "ChatGPT, Generative Artificial Intelligence, Health Personnel, stigma",

author = "David Villarreal-Zegarra and Reategui-Rivera, \{C. Mahony\} and Yscenia Paredes-Gonzales and Gianfranco Centeno-Terrazas and Joseph Finkelstein",

note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 23rd Annual International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2025 ; Conference date: 04-07-2025 Through 06-07-2025",

year = "2025",

month = jun,

day = "26",

doi = "10.3233/SHTI250661",

language = "American English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press BV",

pages = "4--8",

editor = "John Mantas and Arie Hasman and Parisis Gallos and Emmanouil Zoulias and Konstantinos Karitis",

booktitle = "Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics",

address = "Netherlands",

}

Villarreal-Zegarra, D, Reategui-Rivera, CM, Paredes-Gonzales, Y, Centeno-Terrazas, G & Finkelstein, J 2025, Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma. En J Mantas, A Hasman, P Gallos, E Zoulias & K Karitis (eds.), Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics. Studies in Health Technology and Informatics, vol. 328, IOS Press BV, pp. 4-8, 23rd Annual International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2025, Athens, Grecia, 4/07/25. https://doi.org/10.3233/SHTI250661

Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma. / Villarreal-Zegarra, David; Reategui-Rivera, C. Mahony; Paredes-Gonzales, Yscenia et al.
Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics. ed. / John Mantas; Arie Hasman; Parisis Gallos; Emmanouil Zoulias; Konstantinos Karitis. IOS Press BV, 2025. p. 4-8 (Studies in Health Technology and Informatics; Vol. 328).

Producción científica: Libro o Capítulo del libro › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma

AU - Villarreal-Zegarra, David

AU - Reategui-Rivera, C. Mahony

AU - Paredes-Gonzales, Yscenia

AU - Centeno-Terrazas, Gianfranco

AU - Finkelstein, Joseph

PY - 2025/6/26

Y1 - 2025/6/26

N2 - This study evaluated GPT-based conversational agents in tasks related to healthcare provider stigma. The main finding was that GPT-4o models, using Role-Playing (RP) and Chain of Thought (CoT) techniques, outperformed other models in tasks such as defining healthcare provider stigma, identifying types of stigma, and explaining its consequences. The Personalized GPT model showed lower performance, particularly in areas related to treatment access, adherence, and stigma risk factors. These results suggest that advanced prompting techniques significantly enhance the agent’s ability to deliver complex and nuanced information about healthcare provider stigma. The study supports the potential of GPT-based agents as scalable educational tools for reducing stigma, especially in resource-limited settings.

AB - This study evaluated GPT-based conversational agents in tasks related to healthcare provider stigma. The main finding was that GPT-4o models, using Role-Playing (RP) and Chain of Thought (CoT) techniques, outperformed other models in tasks such as defining healthcare provider stigma, identifying types of stigma, and explaining its consequences. The Personalized GPT model showed lower performance, particularly in areas related to treatment access, adherence, and stigma risk factors. These results suggest that advanced prompting techniques significantly enhance the agent’s ability to deliver complex and nuanced information about healthcare provider stigma. The study supports the potential of GPT-based agents as scalable educational tools for reducing stigma, especially in resource-limited settings.

KW - ChatGPT

KW - Generative Artificial Intelligence

KW - Health Personnel

KW - stigma

UR - https://www.scopus.com/pages/publications/105010177115

U2 - 10.3233/SHTI250661

DO - 10.3233/SHTI250661

M3 - Conference contribution

C2 - 40588869

AN - SCOPUS:105010177115

T3 - Studies in Health Technology and Informatics

SP - 4

EP - 8

BT - Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics

A2 - Mantas, John

A2 - Hasman, Arie

A2 - Gallos, Parisis

A2 - Zoulias, Emmanouil

A2 - Karitis, Konstantinos

PB - IOS Press BV

T2 - 23rd Annual International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2025

Y2 - 4 July 2025 through 6 July 2025

ER -

Villarreal-Zegarra D, Reategui-Rivera CM, Paredes-Gonzales Y, Centeno-Terrazas G, Finkelstein J. Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma. En Mantas J, Hasman A, Gallos P, Zoulias E, Karitis K, editores, Global Healthcare Transformation in the Era of Artificial Intelligence and Informatics. IOS Press BV. 2025. p. 4-8. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI250661

Assessment of GPT-Based Conversational Agents Aimed to Reduce Healthcare Provider Stigma

Resumen

Serie de la publicación

Conferencia

Nota bibliográfica

Acceder al documento

Huella

Citar esto