While AI scribes promise to ease the burden of document production, new real-world data reveals a more complex reality. Efficiency has increased slightly and overtime has remained the same, raising important questions about how clinicians will actually use the time they save.
Research: Changes in clinician time expenditure and number of visits with the introduction of artificial intelligence-powered scribes. Image credit: Andrey_Popov/Shutterstock.com
Artificial intelligence (AI)-powered scribes may offer some benefit to clinicians by reducing the time it takes to record and document electronic medical records and increasing the volume of weekly visits, a new study published in October 2006 reports. Japan Automobile Manufacturers Association.
AI scribes rise to tackle the growing burden of document production
Electronic health record (EHR) documentation is a time-consuming task for clinicians, taking an average of 2.3 hours per 8 hours of patient care. This documentation time leads to clinician burnout and often limits clinical competency, patient access, and quality of care.
Artificial intelligence (AI)-powered documentation tools, also known as AI scribes, were developed to reduce the burden of EHR documentation and improve clinician satisfaction. However, studies examining the effectiveness of AI scribes have yielded mixed results, and evidence regarding their impact on productivity remains limited.
Given this gap in the literature, the current study investigated whether the introduction of AI scribes into health systems results in any changes in EHR time expenditures and weekly visit volume, and whether these changes vary by clinician characteristics.
Want to see how AI works in a real clinic? Read this expert interview
US multi-site study explores real-world AI scribe adoption
The study includes five academic medical institutions in multiple regions of the United States that have introduced AI scribes to their clinicians. The study population included ambulatory clinicians, advanced practice clinicians, and residents with the option of using AI scribes.
Across the study population, clinicians who were given access to AI Scribe were considered AI Scribe adopters, regardless of whether they actively used the tool (intention-to-treat definition). Conversely, clinicians who are not given access to an AI scribe are considered non-recruiters.
The main parameters analyzed in this study were time spent on documentation, time spent on the EHR outside of scheduled working hours, and weekly visit volume.
AI scribe dramatically reduces EHR and document creation time
The study enrolled 8,581 clinicians, including 1,809 AI scribe recruits. Participants were from primary care, medical, and surgical specialties, with the majority being attending physicians, followed by advanced practice clinicians and residents.
Analysis of pre- and post-implementation trends showed that AI scribe implementation reduced EHR time by 13 minutes and documentation time by 16 minutes per 8 hours of scheduled patient care, resulting in relative time spent reductions of 3.0% and 10.0%, respectively.
In addition, the introduction of AI scribes resulted in an increase of 0.49 visits per week, which translates to a 1.7% increase in weekly visit volume. However, we did not observe any significant changes in after-hours EHR time after hiring the AI scribe.
Among clinician groups, significant improvements following AI scribe implementation were observed among primary care specialists, advanced specialty clinicians, female clinicians, residents, and clinicians who used AI scribes on 50% or more of their visits.
Revenue analysis estimated an additional $167.37 in monthly evaluation and management (E/M) revenue per clinician associated with implementing AI scribe.
Time savings can be transferred to other clinical responsibilities
This study reveals that adoption of AI scribing by clinicians at academic healthcare institutions is associated with a small decrease in total EHR and documentation time and a small increase in weekly visit volume.
Notably, the study found that despite some reductions in total EHR time and document preparation time, the introduction of AI scribes did not result in significant changes in after-hours work. These findings suggest that although the implementation of AI scribes saved clinicians time on documentation, some of that time could be reallocated to other patient care activities, such as verifying document accuracy, monitoring incoming electronic messages from patients, addressing test results, and conducting medical record reviews.
As observed in the study, time saved by implementing AI scribes was highest among primary care specialists, advanced practice clinicians, female clinicians, residents, and clinicians who used AI scribes on 50% or more of their visits. Among these clinician groups, residents are an important population in evaluating the usefulness of implementing AI scribes, given how important documentation is to learning and the unknown impact on resident learning.
Because the number of residents using AI scribes was limited in this study, the researchers emphasize the need for future research to assess the impact of AI scribes on time expenditure and the impact on residents’ learning.
Even though the highest benefits were observed for clinicians who used AI scribes on more than 50% of their visits, only 32% of adopters used AI scribes that often. This finding highlights the need for strong training and support for adopters.
Due to the non-randomized study design, the observed changes may not be solely related to the introduction of AI scribes. Unmeasured differences between adopters and non-adopters may also influence our findings. Future research should investigate the reproducibility of these findings and identify factors that can enhance the benefits of this technology.
Additionally, this study included only academic medical facilities, with an average weekly visit count of approximately 20 patients. The observed benefits may be different in non-academic settings where the number of clinician visits is much higher.
Click here to download your PDF copy.
