EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas

Rezaur Rashid, Saba Kheirinejad, Brianna M White, Soheil Hashtarkhani, Parnian Kheirkhah Rahimabad, Fekede A Kumsa, Lokesh Chinthala, Janet A Zink, Christopher L Brett, Robert L Davis, David L Schwartz, Arash Shaban-Nejad

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251498 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Rezaur Rashid und 11 weiteren Autor:innen. Beteiligte Einrichtung: Center for Biomedical Informatics, Department of Pediatrics, College of Medicine, University of Tennessee Health Science Center (UTHSC), Memphis, Ten…. Hauptthemen laut MEDLINE: Empathy, Neoplasms, Artificial Intelligence. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unplanned interruptions in radiation therapy (RT) increase clinical risks, yet proactive, personalized psychosocial support remains limited. This study presents a proof-of-concept framework that simulates and evaluates Empathic AI-patient interactions using large language models (LLMs) and synthetic oncology patient personas. Leveraging a de-identified dataset of patient demographics, clinical features, and social determinants of health (SDoH), we created realistic personas that interact with an empathic AI assistant in simulated dialogues. The system uses dual LLMs, one for persona generation and another for empathic response, which engage in multi-turn dialogue pairs per persona. We evaluated the outputs using statistical similarity tests, quantitative metrics (BERTScore, SDoH relevance, empathy, persona distinctness), and qualitative human assessment. The results demonstrate the feasibility of scalable, secure, and context-aware dialogue for early-stage AI development. This HIPAA/GDPR compliant framework supports ethical testing of empathic clinical support tools and lays the groundwork for AI-driven interventions to improve RT adherence.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmpathyNeoplasmsArtificial IntelligenceHumans

Stichwörter der Autor:innen

EmpathyLLMLarge Language ModelsPersonasRadiation Therapy

Autor:innen und Institutionen

  • Center for Biomedical Informatics, Department of Pediatrics, College of Medicine, University of Tennessee Health Science Center (UTHSC), Memphis, Tennessee, USA.
  • The University of Tennessee Graduate School of Medicine, Knoxville, Tennessee, USA.
  • Department of Radiation Oncology, UTHSC, Memphis, TN, USA.

Zitieren

APA

Rashid, R., Kheirinejad, S., White, B. M., Hashtarkhani, S., Kheirkhah Rahimabad, P., Kumsa, F. A., Chinthala, L., Zink, J. A., Brett, C. L., Davis, R. L., Schwartz, D. L., & Shaban-Nejad, A. (2025). Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251498

Vancouver

Rashid R, Kheirinejad S, White BM, Hashtarkhani S, Kheirkhah Rahimabad P, Kumsa FA, et al. Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251498

BibTeX
@article{Rashid2025,
  author = {Rashid, Rezaur and Kheirinejad, Saba and White, Brianna M and Hashtarkhani, Soheil and Kheirkhah Rahimabad, Parnian and Kumsa, Fekede A and Chinthala, Lokesh and Zink, Janet A and Brett, Christopher L and Davis, Robert L and Schwartz, David L and Shaban-Nejad, Arash},
  title = {Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251498}
}
Kostenlos starten →