Ambient AI scribe (Voa Health) to help write outpatient clinic notes and reduce documentation burden

The SOAR Trial (Scribe Optimization for Ambulatory Records): Ambient Artificial Intelligence Scribe With Voa Health for Generating Medical Documentation From Outpatient Visit Audio - A Randomized Controlled Trial

This project tests whether an ambient AI scribe (Voa Health) that drafts clinical notes during adult outpatient visits can reduce doctors' documentation workload and improve physician well‑being and patient experience.

Quick facts

• Phase: Not applicable
• Study type: Interventional
• Enrollment: 300 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Universidade Federal do Paraná (Academic / other)
• Locations: 1 site (Curitiba, Paraná)
• Trial ID: NCT07302906 on ClinicalTrials.gov

What this trial studies

This is a randomized, parallel-group trial where individual outpatient visits are allocated to either usual documentation or documentation assisted by the Voa Health ambient AI scribe. The AI system records the consultation audio and generates a structured draft note using clinic-specific templates, which the physician reviews, edits, and signs in the electronic medical record; clinicians remain responsible for final content. In the control arm, audio may be recorded for study purposes but no AI-generated draft is presented to the clinician. Brief post-visit questionnaires for physicians and patients capture measures of documentation burden, clinician well-being, communication, empathy, and satisfaction using adapted international scales.

Who should consider this trial

Good fit: Adults (age ≥18) seen by participating resident physicians at the outpatient clinics of Complexo Hospital de Clínicas da UFPR who can understand Portuguese, provide informed consent for audio recording, and complete brief post-visit questionnaires are eligible.

Not a fit: Patients who are under 18, cannot consent, do not speak Portuguese, receive care outside the participating clinics, or have visits unsuitable for audio capture are unlikely to benefit from participation.

Why it matters

Potential benefit: If successful, patients may experience clearer and more complete medical notes, more attentive face-to-face time with clinicians, and higher satisfaction with their visits.

How similar studies have performed: Early pilot studies and commercial implementations of AI scribes have reported reduced documentation time and improved clinician satisfaction, but randomized evidence is still limited.

Eligibility criteria

Inclusion Criteria:

Patients:

1. Adults (≥18 years) attended at the participating outpatient clinics of the Hospital de Clínicas - Federal University of Paraná during the study period.
2. Under the care of a physician participating in the trial.
3. Ability to understand Portuguese and provide informed consent for the audio recording of the consultation and completion of brief questionnaires.
4. Ability to complete post-consultation questionnaires during interview.

Physicians:

1. Resident physicians working in the participating outpatient clinics.
2. Use of the hospital's electronic medical record in routine care practice.
3. Agreement to the audio recording of consultations and to the completion of brief questionnaires after each included encounter.

Student Researchers:

1. Medical students or undergraduate health science students linked to the research project.
2. Trained in patient registration, collection of Informed Consent (ICF), and administration of questionnaires to the patient on the Infinity Research platform.

Exclusion Criteria:

1. Patients under 18 years of age.
2. Emergency consultations, urgent care, or inpatient care.
3. 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.
4. 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.
5. Consultations where either the patient or the physician refuses audio recording or participation in the study.
6. Consultations where the AI system is unavailable or malfunctioning (applicable only for protocol adherence analyses).

Where this trial is running

Curitiba, Paraná

• Complexo Hospital de Clínicas da UFPR (CHC-UFPR) — Curitiba, Paraná, Brazil (Recruiting)

Study contacts

• Principal investigator: Gustavo Lenci Marques, MD, PhD — Universidade Federal do Paraná
• Study coordinator: Gustavo Lenci Marques, MD, PhD

Conditions Burnout, Professionals; Medical Records Systems, Computerized; Physician-Patient Relations; Ambulatory Care; ambient AI scribe; artificial intelligence; clinical documentation; medical note generation