Ambient AI Scribes in Clinical Practice: A Randomized Trial
Nabla reduced time-in-note versus the control. Both DAX and Nabla resulted in potential improvements in burnout, task load, and work exhaustion, but these secondary end point findings need confirmation in larger, multicenter trials. Clinicians reported that performance was similar across the two distinct platforms, and occasional inaccuracies observed in either scribe require ongoing vigilance. (Funded by the University of California, Los Angeles, Department of Medicine and others; ClinicalTrials.gov number, NCT06792890.).
Authors
- John N. Mafi (ORCID: https://orcid.org/0000-0002-0322-7636)
- Catherine A. Sarkisian (ORCID: https://orcid.org/0000-0003-2768-2323)
- Paul J. Lukac (ORCID: https://orcid.org/0000-0002-3315-6613)
- Aaron Chin (ORCID: https://orcid.org/0000-0001-9490-6580)
- Sitaram Vangala
- Ya‐Chen Tina Shih (ORCID: https://orcid.org/0000-0001-7290-3864)
- Joshua Khalili (ORCID: https://orcid.org/0009-0009-3559-4332)
- Eric M. Cheng (ORCID: https://orcid.org/0000-0002-2568-5603)
- William J. Turner (ORCID: https://orcid.org/0009-0002-9773-1290)
Institutions
- West Los Angeles College (US)
- RAND Corporation (US)
- University of California, Los Angeles (US)
- UCLA Health (US)
- USC Norris Comprehensive Cancer Center (US)
- VA Greater Los Angeles Healthcare System (US)
Publication Details
- Journal
- NEJM AI
- Published
- 2025-11-26
- DOI
- https://doi.org/10.1056/aioa2501000
- Citations
- 17
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 11.12