Ambient AI Scribe (Voa Health) in Outpatient Clinics: Draft Notes, Documentation Burden, and Well-Being

Official title

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

Overview

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.

Detailed description

This study is a randomized controlled trial designed to assess the impact of an ambient artificial-intelligence (AI) scribe on physician well-being, documentation workload, and patient experience in routine outpatient care.

The intervention consists of using the Voa Health ambient AI scribe during clinical encounters. The system records the audio of the consultation and generates a structured draft clinical note in real time, aligned with specialty-specific templates that reflect the routine workflow of each clinic (for example, different templates for general cardiology, heart failure, dyslipidemia, etc.). At the end of the visit, the physician reviews, edits, and signs the draft in the electronic medical record (EMR), remaining fully responsible for the accuracy and completeness of the documentation. In the control condition, physicians conduct consultations and document encounters using their usual methods without AI support. For study purposes, audio may still be recorded in the control arm, but no AI-generated note is displayed or used by the clinician.

The unit of randomization is the individual consultation. For participating physicians, eligible visits are automatically allocated to one of two parallel arms: (1) usual documentation without AI and (2) documentation assisted by the ambient AI scribe. Randomization is designed to preserve the existing organization of each clinic and to avoid interference with scheduling or patient flow. Clinical care, diagnostic and therapeutic decisions, and follow-up procedures are not dictated by the protocol and follow usual practice; the only experimental element is the use (or non-use) of the AI scribe for documentation and the collection of audio and questionnaires.

Adult patients seen in participating outpatient clinics, and their physicians, are invited to take part. After informed consent, the entire consultation is audio-recorded. Immediately after each visit, both patient and physician are asked to complete brief, structured questionnaires that capture the main outcomes of interest. To keep data collection feasible in a busy ambulatory setting, the instruments were built from subsets of items derived from internationally used scales, while keeping the number of questions per consultation small.

For physicians, items are drawn from the Professional Fulfillment Index (PFI), the Mini-Z 2.0 survey, and the 4-item Physician Task Load / NASA-TLX. These items assess professional fulfillment and burnout (physical and emotional exhaustion), perceived sufficiency of time for documentation, work in the EMR outside direct patient contact, perceived documentation burden, and temporal demand of the visit. Additional study-specific items evaluate the perceived quality and completeness of the final note, time required to edit the AI-generated draft, confidence that key clinical details were captured, occurrence of potential AI "hallucinations" (information not actually stated in the visit), and the perceived impact of documentation on attention to the patient.

For patients, questionnaires use items derived from the Consultation and Relational Empathy (CARE) Measure, the Patient Satisfaction Questionnaire Short-Form (PSQ-18), and the Communication Assessment Tool (CAT). These items cover domains such as active listening, understanding of patient concerns, clarity of explanations, adequacy of time spent with the physician, perceived empathy, overall satisfaction with care, and understanding of diagnosis and treatment. In the AI arm, one additional item specifically asks whether the use of AI during the consultation helped, did not change, or hindered the clarity of communication with the physician.

The primary outcomes are physician-reported well-being and perceived documentation workload when using the ambient AI scribe compared with usual documentation. Key secondary outcomes include patient-reported experience and satisfaction, physician-rated quality and completeness of notes, time required for documentation and for editing AI-generated drafts, and the frequency and clinical relevance of AI-related documentation errors or hallucinations. All outcomes are measured at the level of the individual consultation, immediately after each visit.

The trial is initially conducted in multiple outpatient clinics of Hospital de Clínicas of the Federal University of Paraná (UFPR), Brazil, across different medical specialties. In each service, structured note templates are developed in collaboration with local clinical leaders so that the AI-generated drafts reflect the real-world flow of that specialty without changing the standard of care. Medical students and residents trained in the protocol may support consent and questionnaire administration under supervision of attending physicians, to ensure consistent and feasible data collection.

Data are stored in secure, access-controlled servers, with linkage between audio recordings, questionnaires, and EMR notes managed through coded identifiers. A data monitoring committee, independent from the development team of the AI scribe, periodically reviews aggregated data for protocol adherence, data quality, and any safety concerns related to the use of AI in documentation (for example, systematic documentation errors that could potentially affect patient care). Because the intervention is limited to documentation support and clinicians remain responsible for all clinical decisions and for finalizing the notes, the overall risk of participation is considered minimal.

The protocol allows for future expansion to other outpatient services and collaborating centers that adopt the same randomization, data collection procedures, and outcome definitions. The results are expected to provide pragmatic evidence on how ambient AI scribes can be implemented safely and effectively in real-world clinical practice, particularly regarding their impact on physician well-being, documentation workload, and the patient's experience of the consultation.

Interventions

• Other Ambient AI scribe for clinical documentation (Voa Health)
  Use 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 f
• Other Usual documentation without AI scribe (standard care)
  Clinical 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 satisfactio

Primary outcome measures

• Physician documentation workload during the visit [Time frame: Immediately after each outpatient consultation (same day)]
• Physician well-being / exhaustion during the visit [Time frame: Immediately after each outpatient consultation (same day)]

Secondary outcome measures (6)

• Patient experience of communication and empathy [Time frame: Immediately after each outpatient consultation (same day)]
• Patient understanding of diagnosis and treatment [Time frame: Immediately after each outpatient consultation (same day)]
• Physician-rated quality and completeness of clinical notes [Time frame: Immediately after finalizing documentation for each consultation (same day)]
• Time required for documentation outside direct patient contact [Time frame: Immediately after each outpatient consultation (same day)]
• Proportion of consultations with AI-related hallucinations in documentation [Time frame: Immediately after each AI-assisted consultation (same day)]
• Proportion of clinical notes with documentation errors in blinded external review [Time frame: Within 30 days after finalizing each clinical note]

Eligibility criteria

Inclusion criteria

Patients:

• 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.

Physicians:

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

Student Researchers:

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

Exclusion criteria

• 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.
• Consultations where either the patient or the physician refuses audio recording or participation in the study.
• Consultations where the AI system is unavailable or malfunctioning (applicable only for protocol adherence analyses).

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Health services research

Study locations

Brazil · 1 center

• Complexo Hospital de Clínicas da UFPR (CHC-UFPR) — Curitiba

Publications

• Afshar M, Baumann MR, Resnik F, Hintzke J, Sullivan AG, Wills G, Lemmon K, Dambach J, Ann Mrotek L, Quinn M, Abramson K, Kleinschmidt P, Brazelton TB, Leaf MA, Twedt H, Kunstman D, Patterson B, Liao F, Rasmussen S, Burnside ES, Goswami C, Gordon J. A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being. NEJM AI. 2025 Dec;2(12):10.1056/a PMID 41625485
• Grace Hong, B.A., Lauren Wilcox, Ph.D., Amelia Sattler, M.D., Samuel Thomas, M.D., Nina Gonzalez, M.D., Marissa Smith, Ph.D., John Hernandez, Ph.D., Margaret Smith, M.B.A., Steven Lin, M.D., and Robert Harrington, M.D. Clinicians' Experiences with EHR Documentation and Attitudes Toward AI-Assisted Documentation. Stanford University School of Medicine and Google Health. 2020.
• Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019 Jun;6(2):94-98. doi: 10.7861/futurehosp.6-2-94. PMID 31363513
• Quiroz JC, Laranjo L, Kocaballi AB, Berkovsky S, Rezazadegan D, Coiera E. Challenges of developing a digital scribe to reduce clinical documentation burden. NPJ Digit Med. 2019 Nov 22;2:114. doi: 10.1038/s41746-019-0190-1. eCollection 2019. PMID 31799422
• Cheng CG, Wu DC, Lu JC, Yu CP, Lin HL, Wang MC, Cheng CA. Restricted use of copy and paste in electronic health records potentially improves healthcare quality. Medicine (Baltimore). 2022 Jan 28;101(4):e28644. doi: 10.1097/MD.0000000000028644. PMID 35089204
• Olson KD, Meeker D, Troup M, Barker TD, Nguyen VH, Manders JB, Stults CD, Jones VG, Shah SD, Shah T, Schwamm LH. Use of Ambient AI Scribes to Reduce Administrative Burden and Professional Burnout. JAMA Netw Open. 2025 Oct 1;8(10):e2534976. doi: 10.1001/jamanetworkopen.2025.34976. PMID 41037268
• Yixing Jiang, Kameron C. Black, D.O., M.P.H., Gloria Geng, Danny Park, James Zou, Ph.D., Andrew Y. Ng, Ph.D., and Jonathan H. Chen, M.D., Ph.D. MedAgentBench: A Virtual EHR Environment to Benchmark Medical LLM Agents. NEJM AI. August 14, 2025;2(9)
• Afshar M, Resnik F, Baumann MR, Hintzke J, Lemmon K, Sullivan AG, Shah T, Stordalen A, Oberst M, Dambach J, Mrotek LA, Quinn M, Abramson K, Kleinschmidt P, Brazelton T, Twedt H, Kunstman D, Wills G, Long J, Patterson BW, Liao FJ, Rasmussen S, Burnside E, Goswami C, Gordon JE. A Novel Playbook for Pragmatic Trial Operations to Monitor and Evaluate Ambient Artificial Intelligence in Clinical Practic PMID 40959192

Identifiers

NCT: NCT07302906 · SOAR-UFPR-VOA-001 · 81736024.4.0000.0096 · 51.562.244/0001-07

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗