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 three-month intervention period. We evaluated documentation efficiency with both standard and custom Epic metrics to evaluate 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 uncharged throughout the study. Conclusions: Our findings suggest that DAX can improve documentation efficiency, particularly among clinicians that 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.
