English

Patient Safety Risks from AI Scribes: Signals from End-User Feedback

Computers and Society 2025-12-05 v1 Machine Learning

Abstract

AI scribes are transforming clinical documentation at scale. However, their real-world performance remains understudied, especially regarding their impacts on patient safety. To this end, we initiate a mixed-methods study of patient safety issues raised in feedback submitted by AI scribe users (healthcare providers) in a large U.S. hospital system. Both quantitative and qualitative analysis suggest that AI scribes may induce various patient safety risks due to errors in transcription, most significantly regarding medication and treatment; however, further study is needed to contextualize the absolute degree of risk.

Keywords

Cite

@article{arxiv.2512.04118,
  title  = {Patient Safety Risks from AI Scribes: Signals from End-User Feedback},
  author = {Jessica Dai and Anwen Huang and Catherine Nasrallah and Rhiannon Croci and Hossein Soleimani and Sarah J. Pollet and Julia Adler-Milstein and Sara G. Murray and Jinoos Yazdany and Irene Y. Chen},
  journal= {arXiv preprint arXiv:2512.04118},
  year   = {2025}
}

Comments

ML4H Findings 2025

R2 v1 2026-07-01T08:08:17.147Z