The STREAMLINE Pilot Study on Time Reduction and Efficiency in AI-Mediated Logging for Improved Note-Taking Experience

Abstract

Objectives

This pilot study aimed to evaluate the impact of an ambient listening AI tool, DAX CoPilot (DAX), on clinical documentation efficiency among primary care providers in a community-based setting.

Methods

We conducted a randomized controlled trial among volunteer clinicians (physicians, nurse practitioners, and physician assistants in family medicine, internal medicine, pediatrics, and urgent care), who were asked to use DAX with a standardized note template (n = 25) or to continue with traditional documentation methods (n = 20) over a 3-month intervention period. We evaluated documentation efficiency with both standard and custom Epic metrics to evaluate the impact on all visit types as well as specifically problem-focused visits.

Results

Because of heterogeneity in DAX usage, we created post hoc categories of low (<45% of all visits, n = 12), moderate (45–69.9% of all visits, n = 6), and high-frequency (≥ 70% of all visits, n = 7) DAX users. We observed the largest differences among high-frequency DAX users. For problem-focused visits with clinicians in this group, a median of 50% of note characters were written by DAX, and we observed a 1.4-minute decrease in time spent on notes per visit (p-value: 0.38) and a 35% decrease in the median number of characters per note (p-value: 0.38) from baseline to the end of the study period. The control group metrics were largely unchanged throughout the study.

Conclusion

Our findings suggest that DAX can improve documentation efficiency, particularly among clinicians who use it frequently. Healthcare systems might benefit by using AL-AI tools like DAX but should consider implementation scope and note template features. Future investigations are needed to further explore these trends and their additional implications for outcomes such as burnout.

Keywords

artificial intelligence - ambient assistive technologies - electronic health records and systems

Protection of Human and Animal Subjects

This study was performed in compliance with the World Medical Association Declaration of Helsinki on Ethical Principles for Medical Research Involving Human Subjects and was reviewed by the Samaritan Health Services Institutional Review Board.

Publikationsverlauf

Eingereicht: 29. Oktober 2024

Angenommen: 14. März 2025

Accepted Manuscript online:
17. März 2025

Artikel online veröffentlicht:
09. Juli 2025

• References

• 1 Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019; 25 (01) 44-56
• 2 Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng 2018; 2 (10) 719-731
• 3 Jiang F, Jiang Y, Zhi H. et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017; 2 (04) 230-243
• 4 Chintagunta B, Katariya N, Amatriain X, Kannan A. Medically aware GPT-3 as a data generator for medical dialogue summarization. In: Shivade C, Gangadharaiah R, Gella S, et al., eds. Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations. Association for Computational Linguistics; 2021: 66-76
• 5 Van Veen D, Van Uden C, Blankemeier L. et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat Med 2024; 30 (04) 1134-1142
• 6 West CP, Dyrbye LN, Shanafelt TD. Physician burnout: contributors, consequences and solutions. J Intern Med 2018; 283 (06) 516-529
• 7 Tajirian T, Stergiopoulos V, Strudwick G. et al. The influence of electronic health record use on physician burnout: cross-sectional survey. J Med Internet Res 2020; 22 (07) e19274
• 8 Cascella M, Semeraro F, Montomoli J, Bellini V, Piazza O, Bignami E. The breakthrough of large language models release for medical applications: 1-year timeline and perspectives. J Med Syst 2024; 48 (01) 22
• 9 Tierney AA, Gayre G, Hoberman B. et al. Ambient artificial intelligence scribes to alleviate the burden of clinical documentation. NEJM Catal 2024; 5 (03)
• 10 Cao DY, Silkey JR, Decker MC, Wanat KA. Artificial intelligence-driven digital scribes in clinical documentation: Pilot study assessing the impact on dermatologist workflow and patient encounters. JAAD Int 2024; 15: 149-151
• 11 Ma SP, Liang AS, Shah SJ. et al. Ambient artificial intelligence scribes: utilization and impact on documentation time. J Am Med Inform Assoc 2025; 32 (02) 381-385
• 12 Liu T, Hetherington TC, Dharod A. et al. Does AI-powered clinical documentation enhance clinician efficiency? A longitudinal study. NEJM AI 2024; 1 (12)
• 13 Jeppson J. What can Epic's signal data tell us about EHR satisfaction and burnout?. KLAS Research. Accessed 2020 at: https://klasresearch.com/archcollaborative/report/what-can-epics-signal-data-tell-us-about-ehr-satisfaction-and-burnout/324
• 14 Jeppson J, Anderson J. Epic Signal data 2023: examining its implication for EHR satisfaction, burnout, and turnover. KLAS Research. Accessed 2023 at: https://klasresearch.com/archcollaborative/report/epic-signal-data-2023/548
• 15 Rule A, Melnick ER, Apathy NC. Using event logs to observe interactions with electronic health records: an updated scoping review shows increasing use of vendor-derived measures. J Am Med Inform Assoc 2022; 30 (01) 144-154
• 16 Kannampallil T, Adler-Milstein J. Using electronic health record audit log data for research: insights from early efforts. J Am Med Inform Assoc 2022; 30 (01) 167-171
• 17 Nguyen OT, Turner K, Charles D. et al. Implementing digital scribes to reduce electronic health record documentation burden among cancer care clinicians: a mixed-methods pilot study. JCO Clin Cancer Inform 2023; 7 (07) e2200166