The goal of this randomized clinical trial is to learn whether an "ambient AI scribe" (Voa Health) can reduce documentation burden and improve physician well-being and patient experience in outpatient clinics. The AI scribe listens to the audio of the consultation and produces a draft of the clinical note that the physician reviews and edits.
In this study, consultations are randomized to 2 groups: usual documentation (without AI) or documentation assisted by the AI scribe. Adult patients seen in participating clinics, and their physicians, are invited to take part. For both groups, the consultation audio is recorded and, at the end of the visit, physicians and patients complete short questionnaires about well-being, workload, communication, empathy, and satisfaction. The questionnaires are based on internationally used scales (such as PFI, Mini-Z, NASA-TLX, CARE, PSQ-18, and CAT) but adapted to keep them brief and feasible in routine care.
The main questions are whether the AI scribe lowers the time and effort needed to document the visit, improves physician professional fulfillment and reduces burnout, and whether it affects how patients perceive the communication, empathy, and overall quality of the consultation. No drugs or devices are being tested. The results are expected to guide hospitals on the safe and effective use of ambient AI scribes in real-world clinical practice.
Adults (≥18 years) attended at the participating outpatient clinics of the Hospital de Clínicas - Federal University of Paraná during the study period.
Under the care of a physician participating in the trial.
Ability to understand Portuguese and provide informed consent for the audio recording of the consultation and completion of brief questionnaires.
Ability to complete post-consultation questionnaires during interview.
Patients under 18 years of age.
Emergency consultations, urgent care, or inpatient care.
Patients with significant cognitive impairment, acute distress, or clinical instability that, in the opinion of the treating physician, precludes providing consent or completing questionnaires, except when accompanied by a legal guardian capable of providing consent on their behalf.
Patients under legal guardianship or who, for any reason, cannot provide consent on their own, except when the guardian or legal representative is present and can provide informed consent.
Parallel
Ambient AI scribe for clinical documentation (Voa Health)
Other interventionUse of an ambient artificial-intelligence (AI) scribe during outpatient consultations. The Voa Health system records the audio of the visit and generates a structured draft clinical note based on specialty-specific templates that follow the usual flow of each clinic. After the consultation, the physician reviews, edits, and signs the note in the electronic medical record. The AI does not make diagnostic or therapeutic decisions; it only assists documentation. All other aspects of clinical care follow routine practice.
Usual documentation without AI scribe (standard care)
Other interventionClinical documentation performed using usual methods without AI support (standard care). Physicians document the encounter in the electronic medical record as they normally do (typing, dictation, or handwritten notes as applicable). Audio of the visit may be recorded for study purposes, but no AI-generated draft note is shown to the clinician. After the consultation, physicians and patients complete the same brief questionnaires about workload, well-being, communication, empathy, and satisfaction.
Physician documentation workload during the visit
Physician-reported documentation burden, measured immediately after each consultation using brief 5-point Likert-type items adapted from internationally used instruments (NASA-TLX, Mini-Z) and study-specific items. Items assess: (1) administrative burden of the consultation, (2) time available to focus on the patient, (3) mental demand of the consultation (adapted NASA-TLX), (4) interference of the documentation process with patient interaction, and (5) disruption of workflow due to documentation adjustments. Individual item scores and a composite burden score (mean of items; higher values = greater burden) will be compared between consultations with the ambient AI scribe and consultations with usual documentation without AI.
Physician well-being / exhaustion during the visit
Physician physical exhaustion immediately after the consultation, assessed with a single item derived from the Professional Fulfillment Index (PFI): "I feel physically exhausted after this consultation," rated on a 5-point agreement scale (strongly disagree to strongly agree; higher values = greater exhaustion). Scores will be compared between consultations with the ambient AI scribe and consultations with usual documentation without AI.
Patient experience of communication and empathy
Patient-reported experience of the consultation, including active listening, understanding of concerns, clarity of explanations, perceived empathy, time spent with the physician, and overall satisfaction. Items are derived from the CARE Measure, PSQ-18, and Communication Assessment Tool (CAT), rated on 5-point Likert scales. A composite score (mean of item scores; higher values = better experience) will be compared between consultations with the ambient AI scribe and consultations with usual documentation without AI.
Patient understanding of diagnosis and treatment
Single item asking patients how much they understood about their diagnosis and treatment after the consultation, rated on a 5-point scale from 1 (nothing) to 5 (completely). Scores will be compared between consultations with the ambient AI scribe and consultations with usual documentation without AI.
Physician-rated quality and completeness of clinical notes
Physician global rating of the final clinical note for the consultation (clarity, organization, and completeness), using a 5-point scale adapted from Mini-Z (poor, marginal, satisfactory, good, excellent). Scores will be compared between consultations with the ambient AI scribe and consultations with usual documentation without AI.
Time required for documentation outside direct patient contact
Physician self-reported time spent working on the electronic medical record outside direct patient contact for that consultation (for example, after the patient leaves the room), including review and editing of AI-generated notes when applicable. Time is rated in ordered categories (almost none; minor edits; moderate edits; extensive edits). Distributions of categories will be compared between the ambient AI scribe and usual documentation conditions.
Click on the lead sponsor to view all of their trials.
Pedro Angelo Basei de Paula
Lead sponsor
Universidade Federal do Paraná
Sponsor institution
Universidade Federal do Paraná
Collaborator
