This is a single-site pragmatic randomized control trial studying the effect of ambient artificial intelligence (AI) scribes on the delivery of medical care to patients in the ambulatory setting. The study will last 150 days and include up to 65 providers in the intervention group. Providers will be recruited from three medical specialties, including primary care, oncology, and urology. The study will enroll providers and randomize them to an intervention group (access to the ambient AI scribe product) or a control group (routine patient care). Providers will be evaluated for burnout and task load measures through digital surveys at the beginning, middle, and end of the study. Provider electronic health record (EHR) usage data will also be evaluated for time spent documenting, time spent after hours on days with scheduled clinical care, and time between the start of the clinical encounter and signing it.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE
Enrollment
139
Ambient artificial intelligence (AI) scribes are a clinical documentation tool that uses automated speech recognition and large-scale language models to capture and transcribe synchronous patient-provider encounters in real time. Clinicians then review, edit, and authorize the AI-generated text before finalizing the chart, ensuring necessary human oversight and medical accuracy. In this study, participants used Ambient AI scribes on mobile devices for the recordings. The ambient AI scribe will be available for the provider to use in the outpatient setting. They were not required to use the Ambient AI scribe, but could choose whether to use it and with which patients. Consent to use the device was documented for all patient encounters.
University of Washington Medical Center
Seattle, Washington, United States
Professional Fulfillment Index (PFI)
Change in professional fulfillment and burnout, measured using the Professional Fulfillment Index (PFI), a validated 16-item self-report questionnaire. The instrument comprises three subscales: Professional Fulfillment (6 items), Work Exhaustion (4 items), and Interpersonal Disengagement (6 items). Items are rated on a 5-point Likert scale (0 = "Not at all true" / "Not at all" to 4 = "Completely true" / "Extremely"). Subscale scores are calculated as the mean of constituent items. Unit of measure: mean subscale score (range 0-4) and overall burnout score (mean of Work Exhaustion and Interpersonal Disengagement subscales, range 0-4).
Time frame: Surveyed at enrollment (day 0 of pilot), midpoint (day 75), and end of pilot (day 150)
Mean Score on NASA Task Load Index (NASA-TLX)
Change in perceived workload, measured using the NASA Task Load Index (NASA-TLX), a validated multidimensional self-report questionnaire. The instrument comprises six subscales: Mental Demand, Physical Demand, Temporal Demand, Performance, Effort, and Frustration. Each subscale is rated on a 0-100 scale in 5-point increments. Unit of measure: subscale score (range 0-100) and overall workload score, calculated as the unweighted mean of the six subscales (range 0-100). Higher scores indicate greater perceived task workload associated with clinical documentation.
Time frame: Surveyed at enrollment (day 0 of pilot), midpoint (day 75), and end of pilot (day 150)
Ambient AI scribe utilization rate (%)
Percentage of clinical encounters in which the provider used the Abridge ambient AI scribe, measured using Abridge platform usage logs cross-referenced with electronic health record (EHR) encounter data. Unit of measure: utilization rate, calculated as (number of encounters in which Abridge was used divided by the total number of clinical encounters during the same period). This fraction is then represented as a percentage (range 0-100%) and aggregated monthly by provider.
Time frame: Through study completion, up to 150 days after the start of the pilot.
Time Spent in the Electronic Health Record on Clinical Note Documentation (Minutes)
Time spent by the provider in the electronic health record on clinical note documentation activities, measured using EHR audit log data (e.g., Epic Signal Provider Efficiency Profile). Unit of measure: minutes per scheduled clinic day on note documentation, normalized to clinical workload (clinical Full-Time Equivalent), and aggregated in 4-week windows per provider. No patient information will be collected for this outcome measure.
Time frame: Through study completion, up to 150 days after the start of the pilot.
Time spent in the electronic health record outside of working hours
Time spent by the provider in the electronic health record outside of scheduled clinic/working hours (commonly referred to as "work outside of work" or "pajama time"), measured using EHR audit log data (e.g., Epic Signal Provider Efficiency Profile). Unit of measure: minutes per scheduled clinic day spent in the EHR outside of working hours, normalized to clinical workload and aggregated in 4-week windows per provider. No patient information will be collected for this outcome measure.
Time frame: Through study completion, up to 150 days after the start of the pilot.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.