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

2025/12/01 by Jessica Dai, Anwen Huang, Dai, Jessica +17
Medicine · Health Professions · Computer Science · #Artificial Intelligence in Healthcare and Education #Electronic Health Records Systems #Explainable Artificial Intelligence (XAI)

paper · pdf · doi:10.48550/arxiv.2512.04118

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.

Citations

• Aggregated Individual Reporting for Post-Deployment Evaluation
• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Related

• Beyond human ears: navigating the uncharted risks of AI scribes in clinical practice
• Improving Clinical Documentation with AI: A Comparative Study of Sporo AI Scribe and GPT-4o mini
• Safety challenges of AI in medicine in the era of large language models
• Assessing the Quality of AI-Generated Clinical Notes: A Validated Evaluation of a Large Language Model Scribe
• Evaluation of an <scp>AI</scp> Scribe Tool in the Emergency Department: A Single‐Arm Observational Study