Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas.

Rashid, R; Kheirinejad, S; White, BM; Hashtarkhani, S; Kheirkhah Rahimabad, P; Kumsa, FA; Chinthala, L; Zink, JA; Brett, CL; Davis, RL; Schwartz, DL; Shaban-Nejad, A

Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas.

Rashid, R Kheirinejad, S White, BM Hashtarkhani, S Kheirkhah Rahimabad, P Kumsa, FA Chinthala, L Zink, JA Brett, CL Davis, RL Schwartz, DL Shaban-Nejad, A

Permalink

Publisher:: IOS Press
Publication Type:: Journal Article
Citation:: Stud Health Technol Inform, 2025, 332, pp. 72-76
Issue Date:: 2025-10-02

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (394.45 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Rashid, R
dc.contributor.author	Kheirinejad, S
dc.contributor.author	White, BM
dc.contributor.author	Hashtarkhani, S
dc.contributor.author	Kheirkhah Rahimabad, P
dc.contributor.author	Kumsa, FA
dc.contributor.author	Chinthala, L
dc.contributor.author	Zink, JA
dc.contributor.author	Brett, CL
dc.contributor.author	Davis, RL
dc.contributor.author	Schwartz, DL
dc.contributor.author	Shaban-Nejad, A
dc.date.accessioned	2026-05-01T04:54:57Z
dc.date.available	2026-05-01T04:54:57Z
dc.date.issued	2025-10-02
dc.identifier.citation	Stud Health Technol Inform, 2025, 332, pp. 72-76
dc.identifier.issn	0926-9630
dc.identifier.issn	1879-8365
dc.identifier.uri	http://hdl.handle.net/10453/194857
dc.description.abstract	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.
dc.format	Print
dc.language	eng
dc.publisher	IOS Press
dc.relation.ispartof	Stud Health Technol Inform
dc.relation.isbasedon	10.3233/SHTI251498
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject	0807 Library and Information Studies, 1117 Public Health and Health Services
dc.subject.classification	Medical Informatics
dc.subject.classification	4203 Health services and systems
dc.subject.classification	4601 Applied computing
dc.subject.mesh	Humans
dc.subject.mesh	Empathy
dc.subject.mesh	Neoplasms
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Humans
dc.subject.mesh	Neoplasms
dc.subject.mesh	Empathy
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Humans
dc.subject.mesh	Empathy
dc.subject.mesh	Neoplasms
dc.subject.mesh	Artificial Intelligence
dc.title	Simulating Empathic Interactions with Synthetic LLM-Generated Cancer Patient Personas.
dc.type	Journal Article
utslib.citation.volume	332
utslib.location.activity	Netherlands
utslib.for	0807 Library and Information Studies
utslib.for	1117 Public Health and Health Services
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Health
pubs.organisational-group	University of Technology Sydney/Faculty of Health/School of Public Health
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by-nc/4.0/
dc.date.updated	2026-05-01T04:54:55Z
pubs.publication-status	Published
pubs.volume	332

Abstract:

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.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/194857