Comparison of Two Artificial Intelligence Scribe Products on Pediatric Subspecialty Provider Wellness and Experience, Patient Satisfaction, and Efficiency.

NCT07157943 | Active Not Recruiting

• 1 other identifier: STUDY00001962_MOD
• Study Type: interventional
• Target: 105
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this rapid, randomized quality improvement trial is to learn if implementing generative AI scribe software can enhance physician documentation efficiency and reduce burnout in outpatient providers at Children's Healthcare of Atlanta facilities. The main questions it aims to answer are:

• Do AI scribes have significant benefits in terms of physician burnout, clinical efficiency, patient experience, and business efficiency?
• Does one vendor outperform another in these measures? The investigators will compare providers using DAX Copilot and Abridge AI scribe software to a control group using traditional documentation methods to see if AI scribes improve documentation efficiency and reduce burnout. Participants will:
• Be randomized to one of two AI scribe vendors or control
• Intervention participants may be crossed over to the other vendor mid-trial.
• Collect patient experience scores pre- and post-intervention
• Complete surveys on burnout, efficiency, and fulfillment.

Conditions

Burnout

Keywords

artificial intelligence; AI scribe; ambient documentation; pediatrics; documentation burden

Outcome Measures

Primary Outcomes (2)

• Pajama Time

  The average number of minutes per scheduled day spent in charting activities outside 7 AM to 5:30 PM on weekdays, time outside scheduled hours on weekends, and time on unscheduled holidays

  12 months prior to study start through study completion (total 16 months)

• Time in Notes per Appointment in Minutes

  The Epic Signal Metric "Time in Notes per Appointment" in minutes.

  12 months prior to study start through study completion (total 16 months)

Secondary Outcomes (6)

• Professional Fulfillment

  At baseline, prior to crossover at 2 months (for those who do crossover) and at study completion (4 months).

• Burnout

  At baseline, prior to crossover at 2 months (for those who do crossover) and at study completion (4 months).

• Manual Note Contribution

  12 months prior to study start through study completion (total 16 months)

• AI Scribe Adoption

  Study enrollment through study completion (4 months) for intervention groups

• Patient/Family Satsifaction

  5 visits actively solicited at baseline and 5 visits actively solicited at study completion (4 months)

Study Arms (3)

Intervention - Abridge

EXPERIMENTAL

Gains access to Abridge AI scribe

Other: Abridge AI Scribe

Intervention - DAX Copilot

ACTIVE COMPARATOR

Gains access to DAX Copilot AI scribe

Other: DAX Copilot

Control

NO INTERVENTION

No access to AI scribe

Interventions

Abridge AI Scribe OTHER

Users will have access to the Abridge AI scribe software, either integrated into Epic Haiku ("Abridge Inside") or via standalone app that send information back to Epic ("Abridge Integrated").

Intervention - Abridge

DAX Copilot OTHER

Users will have access to DAX Copilot integrated into Epic Haiku or via standalone app.

Intervention - DAX Copilot

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• \. Provider (MD, DO, APP) in an outpatient practice at Children's Healthcare of Atlanta in a specialty supported by integrated ambient AI scribe software
• Includes Urgent Care and Emergency Department
• Excludes providers working in hospital-based clinics due to lack of availability of workflow integration into the EHR 2. Does not currently utilize an in-person human scribe 3. High clinical workload during pilot period 4. Agrees to use the Children's EHR mobile application (Haiku) on their personal device.
• \. Agrees to offer use of the ambient AI scribe software for at least 75% of patient visit encounters for the duration of the project period

You may not qualify if:

• None

Sponsors & Collaborators

• Children's Healthcare of Atlanta: lead

Study Sites (1)

Children's Healthcare of Atlanta

Atlanta, Georgia, 30329, United States

Location

MeSH Terms

Conditions

Burnout, Psychological

Condition Hierarchy (Ancestors)

Stress, Psychological; Behavioral Symptoms; Behavior

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The project will recruit 105 providers on a voluntary basis to use ambient AI scribe software: Twenty providers will be randomized to DAX Copilot (total of 40 including those in the phase 1 pilot) and 50 providers to Abridge software in an equal distribution of specialties, with the remaining 35 randomized to a control group (no AI scribe software; continue usual documentation practices). After 1-2 months, 40 of the providers in each cohort will be asked to switch to using the other product for another 1-2 months and provide qualitative comparative feedback on the two products.

Study Record Dates

• First Submitted: May 19, 2025
• First Posted: September 5, 2025
• Study Start: April 14, 2025
• Primary Completion: September 9, 2025
• Study Completion: September 12, 2025
• Last Updated: September 5, 2025

Record last verified: 2025-08

Locations

US (1)