Assessing the Efficacy and Impact of Ambient AI Scribes in Healthcare

Assessing the Efficacy and Impact of Ambient AI Scribes in Healthcare: A Randomized Controlled Trial

The goal of this clinical trial is to assess the impacts of ambient AI scribes on the workload and burnout in physicians who see patients in a clinic setting at least twice in a week, as well as the impacts on patient-physician interaction.

The main questions it aims to answer are:

• What is the impact of ambient AI scribe use on physician workload and burnout?
• What is the impact of ambient AI scribe use on quality of patient-physician interaction?

Researchers will compare the group of physicians using the ambient AI scribes to the group not using ambient AI scribes to see if there are any significant differences.

Participants randomly assigned to Group A will make use of the AI scribe and participants randomly assigned to Group B will not use any AI scribe for the 10 working day duration of the study. They will be asked to complete a survey assessing workload and burnout immediately prior to the commencement of the study and at the end of each week of the study or 5 full working days for part time physicians. They will also invite their patients to complete a survey assessing their experience after each clinical interaction.

Study Overview

• Status: Not yet recruiting
• Conditions: Physician Burnout; Use of Ambient AI Scribes; Patient-Phyisican Interaction; Physician Workload
• Intervention / Treatment: Device: Ambient AI Scribe

• Study Type: Interventional
• Enrollment (Estimated): 64
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Scott Adams, MD, PhD, MEd, FRCPC; Phone Number: 306-655-2402; Email: scott.adams@usask.ca
• Study Contact Backup: Name: Sundus Zia; Email: sundus.zia@usask.ca

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Physicians from family medicine or any specialty
• Physicians who regularly see patients in a clinic setting at least 2 days per week

Exclusion Criteria:

• Physicians who are planning to leave their practice during the study period

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; This group will make use of the ambient AI scribe in their clinical visits to generate clinical notes for them over the duration of the study.	Device: Ambient AI Scribe; Software that records audio of a clinical interaction and generates a clinical note.
No Intervention: Non-Ambient AI Users; This group will continue to generate their own clinical notes without the use of ambient AI scribes over the duration of the study.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Physician Workload as Measured Using the NASA Task Load Index	The NASA-TLX is separated into six 100-point scales with 5-point steps that assess mental demand, physical demand, temporal demand, performance, effort, and frustration. A higher score indicates that they feel a greater degree of each of the domains.	From enrolment to the end of the study at 10 working days.
Physician Burnout as Measured Using the MBI - HSS (MP)	The MBI-HSS (MP) is created specifically for medical personnel and assesses emotional exhaustion (9 items), depersonalization (5 items), and personal accomplishment (8 items).	From enrolment to the end of the study at 10 working days.
Quality of Patient-Physician Interaction As Measured Using the CARE Patient Feedback Measure Domain of "Really Listening"	The CARE measure consists of a series of 10 questions asked of patients with our focus on the domain of whether the physician was "really listening (paying close attention to what you were saying; not looking at the notes or computer as you were talking)" scored on a 5 point Likert scale.	Throughout study completion at 10 working days.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Documentation Quality as Measured by the PDQI-9	Documentation is scored by two blinded reviewers on a scale from 1-5 (with 5 indicating a higher quality) across 9 domains: up-to-date, accurate, thorough, useful, organized, comprehensible, succinct, synthesized, and internally consistent.	From enrollment to the completion of the study at 10 working days.
Time Spent Within the EMR for Each Clinical Note	The amount of time spent within the EMR for each clinical note and the amount of time spent editing the note on the ambient AI platform will be tracked using EMR logs and time-tracking tools.	From enrollment to the completion of the study at 10 working days.
Time Spent in the EMR After Hours	The amount of time spent using the EMR after regular working hours will be measured using EMR logs and time-tracking tools.	From enrollment to the completion of the study at 10 working days.

Collaborators and Investigators

• Sponsor: University of Saskatchewan
• Investigators: Principal Investigator: Scott Adams, MD, PhD, MEd, FRCPC, University of Saskatchewan College of Medicine

Publications and helpful links

General Publications

• Shanafelt TD, Dyrbye LN, West CP, Sinsky CA. Potential Impact of Burnout on the US Physician Workforce. Mayo Clin Proc. 2016 Nov;91(11):1667-1668. doi: 10.1016/j.mayocp.2016.08.016. No abstract available.
• Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019 Jun;6(2):94-98. doi: 10.7861/futurehosp.6-2-94.
• Li B, Crampton N, Yeates T, Xia Y, Tian X, Truong KN. Automating Clinical Documentation with Digital Scribes: Understanding the Impact on Physicians. In: CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery; 2021. Accessed July 1, 2024. https://doi.org/10.1145/3411764.3445172
• Saag HS, Shah K, Jones SA, Testa PA, Horwitz LI. Pajama Time: Working After Work in the Electronic Health Record. J Gen Intern Med. 2019 Sep;34(9):1695-1696. doi: 10.1007/s11606-019-05055-x. No abstract available.
• Tierney AA, Gayre G, Hoberman B, et al. Ambient Artificial Intelligence Scribes to Alleviate the Burden of Clinical Documentation. NEJM Catal. 2024;5(3). doi:10.1056/cat.23.0404

Study record dates

Study Major Dates

• Study Start (Estimated): August 1, 2025
• Primary Completion (Estimated): August 1, 2025
• Study Completion (Estimated): August 1, 2025

Study Registration Dates

• First Submitted: July 21, 2025
• First Submitted That Met QC Criteria: August 2, 2025
• First Posted (Actual): August 11, 2025

Study Record Updates

• Last Update Posted (Actual): August 11, 2025
• Last Update Submitted That Met QC Criteria: August 2, 2025
• Last Verified: August 1, 2025

More Information

Terms related to this study

• Keywords: artificial intelligence; physician burnout; physician workload; documentation quality
• Additional Relevant MeSH Terms: Behavioral Symptoms; Stress, Psychological; Burnout, Psychological
• Other Study ID Numbers: 5336

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

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