Evaluating an Ambient Artificial Intelligence Scribe for Documentation Quality and Efficiency in Psychiatric Consultations: A Simulation-based Study

BackgroundDocumentation demands in psychiatric practice diminish time for direct patient care and are associated with clinician burnout. Ambient artificial intelligence (AI) scribes may facilitate more efficient and higher-quality documentation while reducing clinician workload and preserving the integrity of the clinical encounter. This study aims to determine the impact of an ambient AI scribe in improving documentation quality and efficiency while reducing clinician workload during simulated psychiatric consultations. MethodsWe conducted a prospective, cross-over, within-subject simulation study to compare conventional keyboard-based documentation (traditional condition) with documentation assisted by an ambient artificial-intelligence scribe (AI-scribe condition). The study was conducted at an academic simulation centre comprising of eight clinicians with psychiatric experience who completed both documentation conditions. Clinician workload (NASA Task Load Index [NASA-TLX]), documentation quality (Sheffield Assessment Instrument for Letters [SAIL]), video-verified screen time during documentation, and bespoke clinician and patient experience questionnaires were administered. ResultsAI-scribe use was associated with substantially lower workload versus traditional documentation (NASA-TLX total, 25.0 versus 461.3; mean difference, 436.25; 95% CI, 389.93-482.57; p<0.001), with significant improvements in 5 of 6 subscales, including temporal demand (mean difference, 50.00; p<0.001), frustration (mean difference, 33.75; p=0.04), and perceived performance (mean difference, 30.0; p=0.03). Documentation quality improved with AI-scribe (SAIL; 22.88 versus 14.38; t(7)=2.55; p=0.038; Cohens dz=0.90); checklist completeness was [&ge;]75% on 17 of 20 items, with 9 items at 100%. Screen time decreased (7.46 versus 5.31 minutes; mean difference, -2.15; 95% CI, -2.10-+6.41; p=0.27; Hedges g=0.38); 5 of 8 clinicians showed individual reductions. Overall clinician satisfaction was higher with AI-scribe (100% versus 50%), and 87.5% agreed that AI assistance reduced cognitive load. Patient-reported experience favoured the AI-scribe condition. ConclusionAmbient AI scribe can assist in improving documentation quality and substantially reducing clinician workload while maintaining favourable patient-perceived consultation quality.