Ambient Audio-Visual Capture for Clinical Documentation, Assessment and Feedback in Medical Education
Trial Snapshot
- Phase
- Not Applicable
- Status
- Not yet recruiting
- Sponsor
- Enrollment
- 60
- Primary Endpoint
- Mean documentation time per encounter with versus without AI scribe assistance
Study Overview
Brief Summary
AI-powered tools that automatically document clinical conversations are being adopted rapidly in outpatient settings but have not been evaluated in hospital wards. Existing tools use audio recording only, which cannot capture physical examination findings, procedural observations, or clinical safety behaviours - elements of a ward round that are visible but not audible.
This study evaluates an ambient audio-visual (AV) capture system - BlackFrame - that uses both microphone and camera to generate accurate clinical documentation and structured educational feedback in a real inpatient surgical ward setting.
Medical students and doctors in training participate in supervised ward round encounters with consenting adult inpatients. The BlackFrame AI platform generates: (a) a structured draft clinical note for the supervising clinician to review and countersign before any use in the patient record; and (b) formative feedback for the trainee, delivered within 30 minutes, covering clinical communication, examination technique, and documentation quality.
The study measures whether AI-generated feedback improves trainee clinical performance over a placement, how much documentation time is saved, and whether the system is acceptable to patients and clinicians. No AI-generated text enters the patient record without explicit clinician review and sign-off. All participation is voluntary.
Detailed Description
BACKGROUND
Ambient AI scribes have achieved rapid uptake in outpatient and community settings but all published evaluations use audio-only capture. The inpatient ward round is a multimodal clinical event comprising verbal exchange, physical examination, procedural assessment, and non-verbal observation. Audio-only systems are structurally incapable of capturing observable clinical elements, representing construct under-representation under the Messick validity framework.
No published study has evaluated ambient audio-visual capture in a real inpatient setting, nor measured the educational impact of AI-generated formative feedback on ward rounds.
STUDY DESIGN
Mixed-methods feasibility and educational impact study. Surgical ward round at Yeovil District Hospital as the primary study context. Up to three ambient AV capture devices deployed simultaneously in separate side rooms on each study day. Ward rounds proceed sequentially through each room, allowing up to three consented encounters per study day.
Study Design
- Study Type
- Interventional
- Allocation
- Non Randomized
- Intervention Model
- Single Group
- Primary Purpose
- Other
- Masking
- None
Eligibility Criteria
- Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- •Trainee participants:
- •Doctor in training (FY1 through registrar/ST grade) undertaking a supervised clinical activity at a participating NHS study site
- •Able to provide written informed consent in English
- •Patient participants:
- •Adult inpatient aged 18 years or over
- •Able to provide written informed consent in English
- •Admitted under a surgical team at a participating study site
- •Clinically stable at the time of approach
- •Trainee participants:
- •Unwilling to be audio-visually recorded
- •Unable to provide written informed consent
- •Any trainee where participation could create a direct conflict with a concurrent formal assessment or appraisal process at that session
- •Patient participants:
- •Age under 18 years
- •Unable to provide informed consent (including temporary incapacity due to acute illness, sedation, or delirium)
- •Acute clinical deterioration at the time of approach
- •Encounter involves sensitive disclosures in mental health, sexual health, or safeguarding unless a specific sub-protocol with additional consent measures is in place
- •Patient has previously declined participation and does not wish to be re-approached
- •Non-English speaking patients where no appropriate interpreter is available to support the consent process
Exclusion Criteria
- Not provided
Arms & Interventions
Trainee participants
Medical students (Year 3-5) and doctors in training (FY1 through registrar/ST grade) undertaking supervised clinical activities on the surgical ward at the study site. Participants receive AI-generated formative feedback within 30 minutes of each ward round encounter and complete baseline and follow-up clinical assessments.
Intervention: BlackFrame ambient audio-visual capture platform (Device)
Patient participants
Adult inpatients aged 18 or over admitted under the surgical team at the study site, able to provide informed consent and clinically stable at the time of approach. Patients consent to ambient AV recording of their ward round encounter. Their care is unaffected by participation.
Intervention: BlackFrame ambient audio-visual capture platform (Device)
Outcomes
Primary Outcomes
Mean documentation time per encounter with versus without AI scribe assistance
Time Frame: Through study completion, approximately 12 weeks
mean difference in time (minutes) to produce a clinical ward round note with versus without AI scribe assistance. Analysed using paired comparison with 95% confidence interval.
Secondary Outcomes
- Cohen's kappa between AI-generated and expert human assessment scores per checklist domain(Through study completion, approximately 12 weeks)
- Trainee-rated feedback quality score on 5-item Likert survey(After first study encounter, approximately within 1 week of study enrolment)
- Blinded expert rating of AI-assisted clinical note completeness and accuracy(Through study completion, approximately 12 weeks)