Consumer-to-Clinical Language Shifts in Ambient AI Draft Notes and Clinician-Finalized Documentation: A Multi-level Analysis
🤖 AI Summary
This study investigates how clinicians revise AI-generated, patient-friendly draft notes into professionally compliant clinical documentation, with a focus on the poorly understood mechanisms of translating consumer language into standardized clinical terminology. Leveraging a dictionary-based mapping framework, we conducted a multi-level analysis of 71,173 real-world draft–final note pairs, systematically quantifying physicians’ standardization behaviors across different note sections for the first time. Results reveal that 5.8% of segments contained 7,576 valid term conversions, with the “Assessment and Plan” section accounting for the highest proportion (59.3%). The overall deletion rate of consumer terms was 1.2%, and significant inter-physician variability in conversion intensity was observed (p < 0.001). These findings highlight both section-specific patterns and individual heterogeneity in revision practices, offering empirical support for the design of section-aware ambient AI systems.
Application Category
📝 Abstract
Ambient AI generates draft clinical notes from patient-clinician conversations, often using lay or consumer-oriented phrasing to support patient understanding instead of standardized clinical terminology. How clinicians revise these drafts for professional documentation conventions remains unclear. We quantified clinician editing for consumer-to- clinical normalization using a dictionary-confirmed transformation framework. We analyzed 71,173 AI-draft and finalized-note section pairs from 34,726 encounters. Confirmed transformations were defined as replacing a consumer expression with its dictionary-mapped clinical equivalent in the same section. Editing significantly reduced terminology density across all sections (p < 0.001). The Assessment and Plan accounted for the largest transformation volume (59.3%). Our analysis identified 7,576 transformation events across 4,114 note sections (5.8%), representing 1.2% consumer-term deletions. Transformation intensity varied across individual clinicians (p < 0.001). Overall, clinician post-editing demonstrates consistent shifts from conversational phrasing toward standardized, section- appropriate clinical terminology, supporting section-aware ambient AI design.
Problem
Research questions and friction points this paper is trying to address.
Ambient AI
clinical documentation
consumer language
clinical terminology
language shift
Innovation
Methods, ideas, or system contributions that make the work stand out.
ambient AI
consumer-to-clinical normalization
clinical documentation
terminology transformation
section-aware editing
🔎 Similar Papers
2024-08-26arXiv.orgCitations: 3
