Peer-reviewed research
Impact of using an AI scribe on clinical documentation and clinician-patient interactions in allied health private practice: perspectives of clinicians and patients
Kerrie Evans et al., Musculoskeletal Science and Practice, 2025 · DOI 10.1016/j.msksp.2025.103333
Read the originalRead on October 16, 2026
- What it is
- A mixed-methods study of an AI scribe in Australian allied health private practice. 119 allied health clinicians completed surveys at baseline, 6 weeks and 3 months, 157 patients completed a survey after a visit, and a subset was interviewed.
- How much weight it carries
- Peer-reviewed, and the most direct evidence we found for allied health. The study was not randomised, several authors work for the company that supplied the platform, and the 'productivity' measure is self-reported. Physiotherapists and occupational therapists are not reported separately.
Facts taken from this source
- In the 2025 Australian mixed-methods study, 119 allied health clinicians completed the surveys on an AI scribe, along with 157 patients.
“119 AHPs and 157 patients completed the surveys.” (Results)
- In the 2025 Australian study, patients were comfortable consenting to an AI scribe in their own appointments, but some wanted more information about data storage and security before deciding.
“Although patients were comfortable consenting to the AI scribe being used during their own appointments, some acknowledged that other patients might require additional information about data storage and security to make an informed decision.” (Results)
- Allied health clinicians in the 2025 Australian study reported that their productivity increased by an average of 5.8 percent while using an AI scribe.
“Productivity increased by an average of 5.8 %.” (Results)
- In the 2025 Australian study, allied health clinicians spent significantly less time on notes, letters and out-of-hours notes at 6 weeks and 3 months than at baseline.
“There was a significant reduction in time spent doing notes, letters and completing notes out of hours between baseline and 6-weeks and baseline and 3-months” (Results)