EUVIMEDEUVIMED entdecken
StudienprotokollOpen Access · CC BY 4.0

Perceived Impact of a Simulated AI-Enabled EMR Autofill System on Resident Physician Burnout and Workflow Efficiency: A Research Protocol

Muhammad Ahmed, Abdullah Al Azzawi

Undergraduate Research in Natural and Clinical Science and Technology Journal · 08.07.2026 · 1-7

DOI: 10.26685/urncst.1041 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift Undergraduate Research in Natural and Clinical Science and Technology Journal, online erschienen am 08.07.2026. Verfasst von Muhammad Ahmed und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Burnout remains a pervasive challenge among resident physicians, driven in part by excessive documentation burden and inefficient electronic medical record (EMR) workflows. While artificial intelligence (AI)–enabled documentation tools have demonstrated potential to reduce administrative workload among practicing clinicians, little is known about their perceived feasibility or impact within residency training environments. This protocol outlines a mixed-methods study designed to examine whether exposure to a simulated AI-supported EMR autofill interface can influence resident physicians’ perceptions of documentation burden, workflow efficiency, and burnout.

Methods

A prospective pre-post design will recruit 40 resident physicians from Ontario training programs across multiple specialties. Participants will complete a baseline survey including demographic measures and the Mini Z Resident Psychometric Assessment of Worklife and Wellness (Mini ReZ). Residents will then interact with a simulated AI-enabled EMR interface demonstrating automated data entry for non-clinical forms. Thirty days later, participants will repeat the Mini ReZ and respond to open-ended questions regarding feasibility, acceptability, and anticipated workflow impact. Quantitative data will be analyzed using paired-sample t-tests in R (version 4.3.2), and qualitative responses will undergo thematic analysis.Expected Results: It is anticipated that exposure to the AI-simulation will lead to improvements in Mini ReZ items related to EMR stress, documentation workload, and perceived efficiency. Qualitative themes are expected to reflect increased interest in AI-enabled documentation support, perceived reductions in cognitive burden, and concerns regarding accuracy, privacy, and clinical feasibility. Changes in global burnout scores are expected to be more limited, reflecting the multifactorial nature of resident wellness.

Conclusion

Findings from this study will provide initial evidence regarding the feasibility and perceived value of AI-assisted documentation tools within residency training environments. By identifying early indicators of acceptability and areas requiring refinement, this protocol establishes a foundation for future trials involving live AI integration, objective workload metrics, and longer-term evaluation. The insights generated may contribute to system-level strategies aimed at reducing documentation burden and supporting resident physician well-being across Canadian training programs.

Zitieren

APA

Ahmed, M., & Azzawi, A. A. (2026). Perceived Impact of a Simulated AI-Enabled EMR Autofill System on Resident Physician Burnout and Workflow Efficiency: A Research Protocol. Undergraduate Research in Natural and Clinical Science and Technology Journal, 1-7. https://doi.org/10.26685/urncst.1041

Vancouver

Ahmed M, Azzawi AA. Perceived Impact of a Simulated AI-Enabled EMR Autofill System on Resident Physician Burnout and Workflow Efficiency: A Research Protocol. Undergraduate Research in Natural and Clinical Science and Technology Journal. 2026:1-7. doi:10.26685/urncst.1041

BibTeX
@article{Ahmed2026,
  author = {Ahmed, Muhammad and Azzawi, Abdullah Al},
  title = {Perceived Impact of a Simulated AI-Enabled EMR Autofill System on Resident Physician Burnout and Workflow Efficiency: A Research Protocol},
  journal = {Undergraduate Research in Natural and Clinical Science and Technology Journal},
  year = {2026},
  pages = {1--7},
  doi = {10.26685/urncst.1041}
}
Kostenlos starten →