"It Talks Like a Patient, But Feels Different": Co-Designing AI Standardized Patients with Medical Learners

TL;DR

This study explores how medical students co-designed AI standardized patients to improve clinical communication training, emphasizing usability and learner trust over realism.

Contribution

It introduces a learner-centered design process for AI-SPs, highlighting usability as key to trust and educational effectiveness.

Findings

Learners value usability and trust more than realism in AI-SPs.

Co-design workshops identified six learner needs for AI-SP development.

A conceptual workflow for AI-SPs was synthesized from learner input.

Abstract

Standardized patients (SPs) play a central role in clinical communication training but are costly, difficult to scale, and inconsistent. Large language model (LLM) based AI standardized patients (AI-SPs) promise flexible, on-demand practice, yet learners often report that they talk like a patient but feel different. We interviewed 12 clinical-year medical students and conducted three co-design workshops to examine how learners experience constraints of SP encounters and what they expect from AI-SPs. We identified six learner-centered needs, translated them into AI-SP design requirements, and synthesized a conceptual workflow. Our findings position AI-SPs as tools for deliberate practice and show that instructional usability, rather than conversational realism alone, drives learner trust, engagement, and educational value.