MedEasy: Designing AI Standardized Patients for Clinical Consultation Training

2026-06-16

AI Summary

Clinical medical students often lack a reproducible, structured training environment with standardized patients, hindering systematic practice of integrated competencies such as history-taking, physical examination, clinical decision-making, and medical documentation. To address this gap, this work proposes MedEasy, a multi-agent clinical training system that innovatively integrates natural language dialogue, clinical action modeling, dynamic feedback generation, and case trajectory tracking. The system implements case-based, phased clinical workflows, structured medical recordkeeping, action-dependent examination outcomes, and trajectory replay mechanisms to ensure contextual consistency and pedagogical efficacy. User studies indicate that medical students highly value the system’s coherent interview experience, opportunities for repeatable practice, and review functionality, while also offering suggestions for refining operational procedures and feedback standards.

Abstract

AI standardized patients are becoming a setting for professional training in clinical consultation. This paper presents MedEasy, a multi-agent system that organizes virtual-patient practice through patient dialogue, clinical actions, decision submission, documentation, and feedback. We first conducted a formative study with 12 clinical-year medical students through interviews and three co-design workshops. The findings informed a staged workflow, structured case records, action-contingent findings, and trajectory-based review. We then conducted an evaluative user study with a separate cohort of 12 clinical-year medical students, with each participant completing two counterbalanced cases. Learners interpreted MedEasy as a connected consultation environment. They used patient responses, examination findings, available actions, and feedback together to judge whether the represented case remained coherent. They valued repeatable practice and recorded review, while questioning missing actions and feedback criteria. The paper contributes design implications for AI-supported professional training systems that use case-specific standards to connect situated practice.

Problem

• AI standardized patients
• clinical consultation training
• medical education
• virtual patient
• professional training systems

Innovation

• AI standardized patients
• multi-agent system
• clinical consultation training
• trajectory-based review
• situated practice