Ambient Listening Devices as a Feedback Tool in the Simulated Learning Environment

The use of artificial intelligence (AI) in medical education is expanding, yet evidence supporting its role in delivering formative feedback during simulated clinical encounters remains limited. Ambient listening (AL) technology has demonstrated utility for clinical documentation but is underexplored as an educational feedback tool. This study aimed to evaluate the feasibility, perceived quality, and learner acceptance of AI-generated feedback produced by an AL transcription system during simulated patient encounters in undergraduate medical education.

First- and second-year medical students at a single U.S. medical school voluntarily participated in the study during their scheduled simulated patient encounters. Encounters were recorded using an AI-powered AL application. Students submitted a standardized skills rubric and predefined prompt to generate automated feedback and SMART goals following their encounter. Learners completed an anonymized post-encounter survey on the perceived quality of AI-provided feedback, using the validated Quality of Assessment for Learning index and optional free-text responses.

A total of 10 learner evaluations were collected. All participants reported that the AI-generated feedback provided sufficient evidence of performance, included suggestions for improvement, and linked feedback directly to observed behaviors. Qualitative responses consistently described the feedback as accurate, sustainable, and closely aligned with standardized patient feedback and learner self-assessment. Suggested areas for improvement included greater contextual awareness and more specific, example-driven feedback.

This study is best viewed as a promising pilot study. The findings suggest AI-powered AL may serve as an easily integrated and well-accepted method for supplementing formative feedback in simulated clinical encounters. Early findings suggest it may serve as a scalable supplement to direct observation, particularly in settings with limited faculty availability. Larger, multi-institutional studies are needed to evaluate generalizability, educational impact, and effectiveness across learner levels and clinical environments.