Burnout, ProfessionalsSOARNCT07302906
Ambient AI Scribe (Voa Health) in Outpatient Clinics: Draft Notes, Documentation Burden, and Well-Being
A study testing Ambient AI scribe for clinical documentation (Voa Health) in people with Burnout, Professionals and Medical Records Systems, Computerized, run by Pedro Angelo Basei de Paula at 1 site in Brazil.
Trial summary
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. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Burnout, Professionals, Medical Records Systems, Computerized, Physician-Patient Relations
- What is being tested?
- Ambient AI scribe for clinical documentation (Voa Health)
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 300 participants
- Where
- 1 siteBrazil
- Study dates
- 5 Jan 2025to 28 Oct 2026
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- 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:
Show all 12Show fewer
- 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.
Who cannot join
- 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).
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Brazil1 site, 1 recruiting
- Recruiting
Complexo Hospital de Clínicas da UFPR (CHC-UFPR)
Curitiba, Paraná, 80060-900
Pedro Angelo Basei de Paula, +5541996100059, pedroangelo28@gmail.com
About this study
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
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.
Read the 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.
- Conditions
- Burnout, Professionals, Medical Records Systems, Computerized, Physician-Patient Relations, Ambulatory Care
- Being tested
- Ambient AI scribe for clinical documentation (Voa Health), Usual documentation without AI scribe (standard care)
- Keywords
- ambient AI scribe, artificial intelligence, clinical documentation, medical note generation, electronic health record, physician well-being, documentation burden, patient experience, outpatient clinics, randomized controlled trial
- Medical subject headings
- Burnout, Psychological
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Ambient AI scribe for clinical documentation (Voa Health)Other
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 follow routine practice.
Usual documentation without AI scribe (standard care)Other
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 satisfaction.
| Study group | Role | What they receive |
|---|---|---|
| Ambient AI scribe (Voa Health) | Experimental | Outpatient consultations in which the Voa Health ambient AI scribe is active. The system records the audio of the visit and generates a structured draft clinical note based on specialty-specific templates. The physician reviews, edits, and signs the note in the EMR. After the visit, the physician and the patient complete brief questionnaires about workload, well-being, communication, empathy, and satisfaction. Receives: Other: Ambient AI scribe for clinical documentation (Voa Health) |
| Usual documentation without AI scribe | Active comparator | Outpatient consultations in which documentation is performed using usual methods without AI support (standard clinical practice). Audio of the visit may be recorded for study purposes, but no AI-generated note is shown to the clinician. After the visit, the physician and the patient complete the same brief questionnaires about workload, well-being, communication, empathy, and satisfaction. Receives: Other: Usual documentation without AI scribe (standard care) |
What is being measured
The primary outcome is the main question the study is designed to answer.
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.
Measured: Immediately after each outpatient consultation (same day)
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.
Measured: Immediately after each outpatient consultation (same day)
Secondary outcomes (6)
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.
Measured: Immediately after each outpatient consultation (same day)
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.
Measured: Immediately after each outpatient consultation (same day)
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.
Measured: Immediately after finalizing documentation for each consultation (same day)
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.
Measured: Immediately after each outpatient consultation (same day)
Proportion of consultations with AI-related hallucinations in documentation
Among consultations in the ambient AI scribe arm, physicians indicate whether the AI inserted any information in the draft note that was not actually mentioned in the consultation. The outcome is the proportion of AI-assisted consultations with at least one reported hallucination.
Measured: Immediately after each AI-assisted consultation (same day)
Proportion of clinical notes with documentation errors in blinded external review
De-identified clinical notes from both study arms (AI scribe and usual documentation) will be randomly mixed and independently reviewed by at least two clinicians who are blinded to group allocation. Reviewers will classify whether each note contains any clinically relevant documentation error, including fabricated or incorrect information ("hallucinations") that does not match the plausible content of a standard outpatient visit. The primary variable is the proportion of notes with at least one such error in each arm; proportions will be compared between AI-scribe and usual documentation conditions.
Measured: Within 30 days after finalizing each clinical note
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted24 Dec 2025
- Study start5 Jan 2025
- Primary completion28 Oct 2026 (estimated)
- Study completion28 Oct 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (11)Papers the sponsor has linked to this study.
- Other trials for Burnout, ProfessionalsStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Two-arm parallel assignment at the level of individual consultations. Each eligible visit is randomized to either usual documentation (without AI) or documentation assisted by the ambient AI scribe. Each patient contributes only one study consultation to a single arm.
- Masking
- None (open label)
- Enrolment
- 300 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Pedro Angelo Basei de Paula
- Sponsor type
- University, hospital or other
- Collaborators
- Universidade Federal do Paraná
- Responsible party
- Sponsor-investigator, Pedro Angelo Basei de Paula, Universidade Federal do Paraná
- Investigators
- Gustavo Lenci Marques, MD, PhD, Principal investigator, Universidade Federal do ParanáPedro Angelo Basei de Paula, Medical Student, Study director, Universidade Federal do Paraná
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07302906
- Sponsor's protocol ID
- SOAR-UFPR-VOA-001
- Other IDs
- 81736024.4.0000.0096, 51.562.244/0001-07
- Acronym
- SOAR
- Status last verified
- Feb 2026
- First submitted
- 11 Dec 2025
- Last updated
- 30 Sep 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: De-identified individual participant data (IPD) underlying the main published results may be shared with other researchers upon reasonable request to the principal investigator and after approval by the Hospital de Clínicas/UFPR data governance. The study protocol and statistical analysis plan will be made available as supplementary material. The analytic code (e.g., R/Python scripts) used for data cleaning and analysis will be deposited in a public Git repository (such as GitHub) after publication of the primary results.
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/aioa2500945. doi: 10.1056/aioa2500945. Epub 2025 Nov 26.
PubMed 41625485Grace 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.
PubMed 31363513Quiroz 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.
PubMed 31799422Cheng 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.
PubMed 35089204Olson 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.
PubMed 41037268Yixing 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 Practice. NEJM AI. 2025 Sep;2(9):10.1056/aidbp2401267. doi: 10.1056/aidbp2401267. Epub 2025 Aug 28.
PubMed 40959192BASEI DE PAULA, P., BRUNETI SEVERINO, J., BERGER, M., VEIGA, M., PARENTE RIBEIRO, K., LOURES, F., TODESCHINI, S., ROEDER, E., MARQUES, G.. Improving documentation quality and patient interaction with AI: a tool for transforming medical records-an experience report. Journal of Medical Artificial Intelligence, North America, 8, jan. 2025. Available at: <https://jmai.amegroups.org/article/view/9651>
Lukac PJ, Turner W, Vangala S, Chin AT, Khalili J, Shih YT, Sarkisian C, Cheng EM, Mafi JN. Ambient AI Scribes in Clinical Practice: A Randomized Trial. NEJM AI. 2025 Dec;2(12):10.1056/aioa2501000. doi: 10.1056/aioa2501000. Epub 2025 Nov 26.
PubMed 41497288Eileen Kim, M.D., Vincent X. Liu, M.D., M.Sc., and Karandeep Singh, M.D., M.M.Sc. AI Scribes Are Not Productivity Tools (Yet). NEJM AI. November 26, 2025;2(12)
Study at a glance
From the registry record, last updated by the sponsor on 30 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- 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
- ClinicalTrials.gov ID
- NCT07302906
- Acronym / sponsor ID
- SOAR / SOAR-UFPR-VOA-001
- Conditions
- Burnout, Professionals, Medical Records Systems, Computerized, Physician-Patient Relations, Ambulatory Care
- Keywords
- ambient AI scribe, artificial intelligence, clinical documentation, medical note generation, electronic health record, physician well-being, documentation burden, patient experience
- Study type
- Interventional
- Recruitment status
- Recruiting
- Enrolment
- 300 participants (estimated)
- Lead sponsor
- Pedro Angelo Basei de PaulaUniversity, hospital or other
- Collaborators
- Universidade Federal do Paraná
- Study start
- 5 Jan 2025 (actual)
- Primary completion
- 28 Oct 2026 (estimated)
- Study completion
- 28 Oct 2026 (estimated)
- First posted
- 24 Dec 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Study design
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- Two-arm parallel assignment at the level of individual consultations. Each eligible visit is randomized to either usual documentation (without AI) or documentation assisted by the ambient AI scribe. Each patient contributes only one study consultation to a single arm.
| Arm | Type | Receives |
|---|---|---|
| Ambient AI scribe (Voa Health) | Experimental | Other: Ambient AI scribe for clinical documentation (Voa Health)Outpatient consultations in which the Voa Health ambient AI scribe is active. The system records the audio of the visit and generates a structured draft clinical note based on specialty-specific templates. The physician reviews, edits, and signs the note in the EMR. After the visit, the physician and the patient complete brief questionnaires about workload, well-being, communication, empathy, and satisfaction. |
| Usual documentation without AI scribe | Active comparator | Other: Usual documentation without AI scribe (standard care)Outpatient consultations in which documentation is performed using usual methods without AI support (standard clinical practice). Audio of the visit may be recorded for study purposes, but no AI-generated note is shown to the clinician. After the visit, the physician and the patient complete the same brief questionnaires about workload, well-being, communication, empathy, and satisfaction. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (12 listed)
- 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.
- Resident physicians working in the participating outpatient clinics.
Key exclusion criteria (6 listed)
- 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.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| 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 follow routine practice. | Other | Ambient AI scribe (Voa Health) |
| 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 satisfaction. | Other | Usual documentation without AI scribe |
Primary outcome
Physician documentation workload during the visit
Time frame: Immediately after each outpatient consultation (same day)
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
Time frame: Immediately after each outpatient consultation (same day)
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.
6 secondary outcomes
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
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 30 Sep 2026.
- Background: PubMed 41625485Afshar 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/aioa2500945. doi: 10.1056/aioa2500945. Epub 2025 Nov 26.
- BackgroundGrace 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.
- Background: PubMed 31363513Davenport 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.
- Background: PubMed 31799422Quiroz 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.
- Background: PubMed 35089204Cheng 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.
- Background: PubMed 41037268Olson 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.
- BackgroundYixing 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)
- Background: PubMed 40959192Afshar 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 Practice. NEJM AI. 2025 Sep;2(9):10.1056/aidbp2401267. doi: 10.1056/aidbp2401267. Epub 2025 Aug 28.
- BackgroundBASEI DE PAULA, P., BRUNETI SEVERINO, J., BERGER, M., VEIGA, M., PARENTE RIBEIRO, K., LOURES, F., TODESCHINI, S., ROEDER, E., MARQUES, G.. Improving documentation quality and patient interaction with AI: a tool for transforming medical records-an experience report. Journal of Medical Artificial Intelligence, North America, 8, jan. 2025. Available at: <https://jmai.amegroups.org/article/view/9651>
- Background: PubMed 41497288Lukac PJ, Turner W, Vangala S, Chin AT, Khalili J, Shih YT, Sarkisian C, Cheng EM, Mafi JN. Ambient AI Scribes in Clinical Practice: A Randomized Trial. NEJM AI. 2025 Dec;2(12):10.1056/aioa2501000. doi: 10.1056/aioa2501000. Epub 2025 Nov 26.
- BackgroundEileen Kim, M.D., Vincent X. Liu, M.D., M.Sc., and Karandeep Singh, M.D., M.M.Sc. AI Scribes Are Not Productivity Tools (Yet). NEJM AI. November 26, 2025;2(12)
- Individual participant dataSharing planned: Yes. De-identified individual participant data (IPD) underlying the main published results may be shared with other researchers upon reasonable request to the principal investigator and after approval by the Hospital de Clínicas/UFPR data governance. The study protocol and statistical analysis plan will be made available as supplementary material. The analytic code (e.g., R/Python scripts) used for data cleaning and analysis will be deposited in a public Git repository (such as GitHub) after publication of the primary results.
Related trials for Burnout, Professionals
Active, not recruiting
Online Mindfulness-Based Stress Reduction for the Mental Health of Healthcare Professionals
Occupational Stress or Workplace Stress, Burnout, Professionals
Active, not recruiting
Self-Help Plus (SH+) for Stress Reduction in Social Service Workers: A Pilot RCT
Stress, Psychological, Occupational, Stress, Psychological
Recruiting
A Study Of Resilience And Mental Well-Being Through Breathing Practice For Clinical Care Professionals
Burnout, Healthcare Workers, Breathing Exercises
Recruiting
Professional Readiness Through Emotional Preparedness (PREP)
Burnout
Enrolling by invitationObservational study
Floatation Experience in Nurses and Physicians
Burnout, Professional, Negative Affect
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Gustavo Lenci Marques, MD, PhD principal investigator
Universidade Federal do Paraná
Pedro Angelo Basei de Paula, Medical Student study director
Universidade Federal do Paraná
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Ambient AI scribe for clinical documentation (Voa Health) in people with Burnout, Professionals and Medical Records Systems, Computerized, run by Pedro Angelo Basei de Paula at 1 site in Brazil.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 12 inclusion and 6 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: looking for participants now, as of the sponsor's last update on 30 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Brazil. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Gustavo Lenci Marques, MD, PhD (+5541991491428, gustavolencimarques@gmail.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Physician documentation workload during the visit (time frame: Immediately after each outpatient consultation (same day)). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07302906, which also lists 11 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 30 Sep 2026.