AI Standardized Patient Improves Human Conversations in Advanced Cancer Care

📅 2025-05-05
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Late-stage serious illness communication (SIC) training faces persistent challenges—including high cost, low flexibility, and poor scalability—while conventional standardized patient approaches fail to meet evolving clinical demands. To address this, we introduce SOPHIE: the first AI-powered training platform integrating evidence-based clinical guidelines, embodied virtual avatars, and large language models (LLMs) to deliver remote, on-demand, high-fidelity SIC simulation. SOPHIE innovatively implements a clinical literature–driven automated feedback system that enables real-time, multidimensional assessment and personalized intervention across three core competencies: empathy, clarity of expression, and patient empowerment. In a randomized controlled trial, trainees demonstrated statistically significant improvements in all three domains (p < 0.01), confirming SOPHIE’s efficacy in enhancing advanced interpersonal communication skills. This work establishes a scalable, low-cost, and high-fidelity paradigm for SIC education.

Technology Category

Application Category

📝 Abstract
Serious illness communication (SIC) in end-of-life care faces challenges such as emotional stress, cultural barriers, and balancing hope with honesty. Despite its importance, one of the few available ways for clinicians to practice SIC is with standardized patients, which is expensive, time-consuming, and inflexible. In this paper, we present SOPHIE, an AI-powered standardized patient simulation and automated feedback system. SOPHIE combines large language models (LLMs), a lifelike virtual avatar, and automated, personalized feedback based on clinical literature to provide remote, on-demand SIC training. In a randomized control study with healthcare students and professionals, SOPHIE users demonstrated significant improvement across three critical SIC domains: Empathize, Be Explicit, and Empower. These results suggest that AI-driven tools can enhance complex interpersonal communication skills, offering scalable, accessible solutions to address a critical gap in clinician education.
Problem

Research questions and friction points this paper is trying to address.

AI addresses challenges in serious illness communication training
SOPHIE provides scalable, on-demand practice with automated feedback
Enhancing clinician skills in empathy, clarity, and patient empowerment
Innovation

Methods, ideas, or system contributions that make the work stand out.

AI-powered standardized patient simulation
Large language models and virtual avatar
Automated personalized feedback system
🔎 Similar Papers
No similar papers found.
K
K. Haut
Computer Science, University of Rochester, 2513 Wegmans Hall, Rochester, 14627-0226, NY, United States
Masum Hasan
Masum Hasan
PhD Student, Computer Science, University of Rochester
Natural Language ProcessingMachine LearningHuman Computer InteractionSoftware Engineering
T
Thomas M. Carroll
Medical Center, University of Rochester, 601 Elmwood Avenue, Rochester, 14642, NY, USA
R
Ron Epstein
Medical Center, University of Rochester, 601 Elmwood Avenue, Rochester, 14642, NY, USA
T
Taylan K. Sen
Computer Science, University of Rochester, 2513 Wegmans Hall, Rochester, 14627-0226, NY, United States
Ehsan Hoque
Ehsan Hoque
Professor of Computer Science, University of Rochester
affective computingcomputer visionspeech processingautism