Ambient AI Clinical Trial

Evaluation of Abridge Ambient AI Technology Regarding Provider Burnout and Patient Satisfaction With the Clinical Encounter

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 Overview

• Status: Completed
• Conditions: Physician Work Environment; Physician Burnout; Artificial Intelligence (AI)
• Intervention / Treatment: Other: Use of Ambient AI scribe tool on participant's mobile device

• Study Type: Interventional
• Enrollment (Actual): 139
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • Washington
    • Seattle, Washington, United States, 98195
      • University of Washington Medical Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Provider is an employee of the University of Washington Medicine.
• Clinical specialty of primary care, oncology, or urology.
• Clinical full-time equivalent (FTE) of 0.2 or greater (provider must have an outpatient clinic of at least 20% of an FTE).
• Provider is a physician or an advanced practice provider.

Exclusion Criteria:

• Trainees (e.g., medical students, residents, or fellows)
• Provider does not have access to a mobile device that is compatible with the ambient AI scribe service (e.g., Android mobile phone).

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Ambient AI scribe users; Participants in this arm will utilize the ambient AI scribe tools from Abridge. They will otherwise continue their usual clinical activities, including providing care with trainees (e.g., medical students, residents) and multiple family members in the room. The tool will be used exclusively in the outpatient clinical setting and only when the participant is present. The ambient AI scribe tool integrates into the electronic health record (EHR), and the EHR's mobile app is used to collect the recording on a mobile device. The ambient AI scribe tool is transcriptional and does not provide clinical decision support.	Other: Use of Ambient AI scribe tool on participant's mobile device; 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.; Other Names: Abridge
No Intervention: Routine patient care (no AI scribe); These participants were not provided with the ambient AI scribe application on their mobile device. They still had access to documentation with dictation or existing scribe services (non-AI).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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).	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.	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.	Through study completion, up to 150 days after the start of the pilot.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	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.	Through study completion, up to 150 days after the start of the pilot.

Collaborators and Investigators

• Sponsor: University of Washington
• Investigators: Principal Investigator: Christopher W Lewis, MD, MS, University of Washington

Study record dates

Study Major Dates

• Study Start (Actual): December 19, 2024
• Primary Completion (Actual): July 4, 2025
• Study Completion (Actual): July 4, 2025

Study Registration Dates

• First Submitted: April 27, 2026
• First Submitted That Met QC Criteria: May 13, 2026
• First Posted (Actual): May 20, 2026

Study Record Updates

• Last Update Posted (Actual): May 28, 2026
• Last Update Submitted That Met QC Criteria: May 22, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: Primary care; Oncology; Clinical trial; Artificial intelligence; Burnout; Urology; Ambient scribe
• Additional Relevant MeSH Terms: Behavioral Symptoms; Stress, Psychological; Behavior; Burnout, Psychological; Neoplasms
• Other Study ID Numbers: STUDY00022081

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: All participant data will be deidentified (limited dataset), aggregated, or normalized. Data will be managed and stored on Dryad (https://datadryad.org/), a nonprofit membership organization that is committed to making data available for research and educational reuse.
• IPD Sharing Time Frame: Data will be available for at least 10 years.
• IPD Sharing Access Criteria: Data will be shared with qualified researchers whose proposed use has been approved by an institutional review board. Request for deidentified data will be available through Dryad. Requests for additional data can be made to the study's PI.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No