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

Zhiqi Gao; Guo Zhu; Huarui Luo; Dongyijie Primo Pan; Haoming Tang; Bingquan Zhang; Jiahuan Pei; Jie Li; Benyou Wang

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

Human-Computer Interaction 2026-04-07 v1

Authors: Zhiqi Gao , Guo Zhu , Huarui Luo , Dongyijie Primo Pan , Haoming Tang , Bingquan Zhang , Jiahuan Pei , Jie Li , Benyou Wang

View on arXiv ↗ PDF ↗

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.

Keywords

standardized patients large language model co-design medical education AI-SP instructional usability

Cite

@article{arxiv.2602.05856,
  title  = {"It Talks Like a Patient, But Feels Different": Co-Designing AI Standardized Patients with Medical Learners},
  author = {Zhiqi Gao and Guo Zhu and Huarui Luo and Dongyijie Primo Pan and Haoming Tang and Bingquan Zhang and Jiahuan Pei and Jie Li and Benyou Wang},
  journal= {arXiv preprint arXiv:2602.05856},
  year   = {2026}
}

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

Abstract

Keywords

Cite

Related papers