Pre-Post Evaluation of Documentation Burden, Time Perception, and Cognitive Workload of Ambient AI Scribe Tools.

Abstract

Documentation burden and cognitive load contribute to clinician burnout, and ambient AI scribes offer a promising solution, though real-world evaluations remain limited. This study evaluated the impact of an ambient AI scribe on documentation burden, cognitive workload, and perceived burnout in clinical practice. Forty clinicians participated in a 60-day pilot during which the AI scribe generated draft notes from encounter audio. Pre- and post-implementation surveys included validated single-item burnout measure, workflow assessments, NASA Task Load Index (NASA-TLX) scores, and EHR-autologged data on after-hours documentation. Clinicians reported significant reductions in perceived documentation time and after-hours work (all p < 0.001), with large effect sizes (r = 0.73-0.80). NASA-TLX domains demonstrated significant decreases in mental demand, physical demand, effort, time pressure, and stress (all p ≤0.001; g = 0.76-1.54). In contrast, objective EHR documentation minutes did not change significantly (t (15) = 1.52, p = 0.15, g = 0.36). Perceived documentation time aligned more closely with objective EHR-derived categories following implementation. These findings suggest that ambient AI scribes meaningfully reduce perceived workload and improve calibration of documentation burden, even when measurable documentation time remains stable.