CClinicalTrials.gg
Not yet recruitingNCT07850700NVC-AI-DOCUpdated Sep 30, 2026

Ambient AI Documentation in Oncology Consultations

An observational study in Neoplasms, Clinical Documentation and Artificial Intelligence in Medicine, sponsored by National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos. Not yet recruiting at 1 site in Lithuania. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-09-30.

Sponsored by National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos · Observational

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
250
Ages
18 Years and older
Sex
All
01

Study summary

This study tests whether an artificial intelligence (AI) system can help doctors write medical notes during cancer consultations.

After a cancer patient is seen by a multidisciplinary team (a group of specialists who decide on the best treatment), they have a consultation with their oncologist to discuss the treatment plan. During this consultation, doctors must write detailed medical notes, which takes significant time and effort.

In this study, an ambient AI system called VOCALI is used during oncology consultations at the National Cancer Center in Vilnius, Lithuania. Before the consultation begins, the doctor loads relevant pseudonymized clinical data from the electronic health record (such as diagnosis and treatment plan) into the system. During the consultation, VOCALI records the conversation (with the patient's consent) and combines it with the loaded clinical data to automatically generate a draft medical note in Lithuanian. Patients may ask the doctor to stop the recording at any time. The doctor then reviews the draft, makes any necessary corrections, and approves the final document. The AI does not make any medical decisions - the doctor is always responsible for the final note.

What the study measures:

The study has three main goals:

  • To assess the quality of the AI-generated notes, rated by two independent reviewers using the PDQI-10, a standardized documentation quality instrument translated into Lithuanian using forward-backward translation
  • To measure the time doctors spend reviewing and approving the AI-generated draft
  • To monitor safety - whether any AI errors could affect patient care

The study also collects information on doctor workload, ease of use of the system, and patient satisfaction with the consultation.

Who can participate:

Adult patients (age 18 or older) attending a primary oncology consultation at the National Cancer Center in Vilnius, Lithuania, after a multidisciplinary team decision, who speak Lithuanian and provide written consent.

Study details:

250 patients will be enrolled over 12 months. Each participant attends one consultation and completes a short satisfaction questionnaire (about 5 minutes). No additional visits are required. There is no comparator group - all participants receive the AI-assisted documentation.

This is the first study to evaluate ambient AI documentation in the Lithuanian language and in the Lithuanian oncology setting.

Read the detailed description

BACKGROUND Electronic health record (EHR) documentation imposes a substantial administrative burden on physicians and is a major contributor to professional burnout. Studies consistently show that clinicians spend up to half their working time on computer-based documentation, leaving less than 30% of the working day for direct patient contact. Ambient AI documentation systems have shown reductions in documentation time and cognitive load across multiple health systems in the United States and Europe, with AI-generated note quality approximating that of physician-authored notes as measured by a modified Physician Documentation Quality Instrument (PDQI-9). No studies have evaluated ambient AI documentation in the Lithuanian language or in the Lithuanian oncology setting.

STUDY DESIGN Prospective, single-group, single-center feasibility study conducted at the National Cancer Center (NVC), Vilnius, Lithuania. No randomization or control arm.

AI DOCUMENTATION SYSTEM The VOCALI ambient AI system is activated at the start of each eligible consultation. Before the consultation, the physician loads pseudonymized clinical data from the EHR (diagnosis, MDT decision, treatment plan) into the system. The system audio-records the consultation in real time, integrates the preloaded clinical data, and generates a structured draft of the E025 outpatient clinical note in Lithuanian. The physician reviews, edits if necessary, and approves the final document in the EHR. The system does not make autonomous clinical decisions.

PROCEDURES

  • Informed consent obtained before consultation, including consent to audio recording.
  • PSQ-18 patient satisfaction questionnaire completed by participants on the same day post-consultation (\~5 min).
  • PDQI-10 documentation quality instrument rated by two independent raters per AI-generated note.
  • NASA-TLX physician workload questionnaire administered at baseline (T0), 1 month (T1), and end of enrollment (T2).
  • SUS system usability scale completed by physicians at T2.
  • Documentation time and draft editing extent (% characters changed) logged automatically by the system.
  • Safety incidents reported by physicians within 3 working days; monthly safety review meeting held; immediate notification of the NVC Deputy Director for Medicine and the ethics committee required for level-5 (critical) incidents.

SAMPLE SIZE 250 participants will be enrolled over a 12-month period. As a feasibility study, sample size was determined by practical feasibility and literature precedent rather than formal power calculation. With n = 250, proportions can be estimated with a 95% CI of approximately ±3-4%; if no critical incident is observed, the upper 95% confidence limit is 1.2% (rule of three). Approximately 20% data loss is anticipated.

STATISTICAL ANALYSIS R ≥4.0 or SAS ≥9.4. Descriptive statistics for all outcomes. PDQI-10 mean score with 95% CI and domain-level analysis; documentation time as mean with 95% CI and median with IQR; SUS mean with 95% CI; PSQ-18 subscale means. Inter-rater reliability assessed by rWG coefficient (target ≥0.7). Critical incident rate reported with 95% CI using the Clopper-Pearson method. NASA-TLX change (T2-T0) analyzed by paired t-test or Wilcoxon signed-rank test depending on distribution. All inferential tests are descriptive in intent; results interpreted via confidence intervals.

DATA PROTECTION All participant data are pseudonymized immediately upon enrollment. Audio recordings and transcripts are stored in the VOCALI provider's secure infrastructure under a data processing agreement per GDPR Article 28; the provider has no access to identifiable participant data. Data retained for 5 years after study completion.

02

Conditions studied

  • Neoplasms
  • Clinical Documentation
  • Artificial Intelligence in Medicine

Browse trials for

Keywords

  • Clinical documentation
  • Ambient artificial intelligence
  • AI scribe
  • Oncology consultation
  • Feasibility study
  • Physician burnout
  • Natural language processing
  • Electronic health records
  • Lithuanian language
03

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

Adult oncology patients attending a primary oncologist consultation at the National Cancer Center (Vilnius, Lithuania) following a multidisciplinary team (MDT) decision, with diagnosis and treatment plan established.

Inclusion criteria

  • Age 18 years or older at the time of signing the informed consent form
  • Primary oncologist consultation at the National Cancer Center following a multidisciplinary team (MDT) decision, with diagnosis and treatment plan established at the MDT meeting
  • MDT protocol available in the electronic health record (EHR)
  • Signed informed consent form, including consent to audio recording of the consultation

Exclusion criteria

Exclusion Criteria:

  • Absence of MDT protocol in the EHR
  • Diagnosis or treatment plan not yet established
  • MDT recommended additional diagnostic workup (treatment plan not yet defined)
  • Palliative care consultation (not active oncological treatment planning)
  • Non-Lithuanian speaking patients
  • Cognitive impairment affecting ability to understand study information
  • Hearing impairment affecting participation in verbal consultation
04

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
250 participants (estimated)
Patient registry
No

Groups and cohorts

  • Oncology patients undergoing AI-assisted consultation

    Adult oncology patients attending a primary oncologist consultation at the National Cancer Center following a multidisciplinary team (MDT) decision, during which the VOCALI ambient AI documentation system is used to generate a draft clinical note (E025 form).

    Device: Ambient AI documentation system

Interventions

  • DeviceAmbient AI documentation system

    An ambient artificial intelligence documentation system that records the consultation audio, integrates relevant pseudonymized clinical data from the electronic health record (EHR), generates a speech transcript, and produces a draft clinical note (E025 form) for physician review and approval. The system does not make autonomous clinical decisions. The physician reviews, edits if necessary, and approves all AI-generated content before it is saved to the EHR.

    Also known as: VOCALI

05

What researchers measure

Primary outcomes

  1. Documentation Quality - AI-Generated Clinical Documentation Quality (PDQI-10)

    Mean score assessed by two independent raters using the Physician Documentation Quality Instrument (PDQI-10), covering 10 domains (accuracy, completeness, usefulness, organization, clarity, conciseness, synthesis, consistency, data accuracy, and bias) on a 1-5 Likert scale.

    Time frame: Per consultation, throughout the enrollment period (up to 12 months)

  2. Documentation Efficiency - Documentation Completion Time

    Time (in minutes) from opening the AI-generated draft to final approval in the electronic health record (EHR), automatically recorded by the system.

    Time frame: Per consultation, throughout the enrollment period (up to 12 months)

  3. Safety - AI System Incident Rate

    Frequency of AI documentation incidents classified by a 5-level severity scale (1 = insignificant, 2 = minor, 3 = moderate, 4 = major, 5 = critical). Incidents reported by physicians within 3 working days. Critical incident (level 5) rate reported with 95% confidence interval using the Clopper-Pearson method.

    Time frame: Per consultation, throughout the enrollment period (up to 12 months)

Secondary outcomes

  1. Physician Subjective Workload (NASA-TLX)

    Physician-reported workload assessed using the NASA Task Load Index (NASA-TLX), covering 6 dimensions (mental demand, physical demand, temporal demand, performance, effort, frustration). Change from baseline (T0) to end of enrollment (T2) analyzed by paired t-test or Wilcoxon signed-rank test.

    Time frame: Baseline (T0), 1 month (T1), and end of enrollment period (T2, up to 12 months)

  2. System Usability (SUS)

    Physician-rated system usability assessed using the System Usability Scale (SUS), a 10-item questionnaire scored 0-100.

    Time frame: End of enrollment period (T2, up to 12 months)

  3. AI Draft Editing Extent

    Proportion of characters modified between the AI-generated draft and the final approved document, expressed as percentage. Automatically calculated per consultation.

    Time frame: Per consultation, throughout the enrollment period (up to 12 months)

  4. Patient Satisfaction with Consultation (PSQ-18)

    Patient-reported satisfaction assessed using the Patient Satisfaction Questionnaire (PSQ-18), an 18-item instrument. Results reported as subscale means.

    Time frame: After each consultation, throughout the enrollment period (up to 12 months)

06

Study locations

1 site
  • National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos
    Vilnius, Vilnius City LT-08660, Lithuania
07

References and documents

Publications

  • 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. PubMed 41037268 ↗
  • Sasseville M, Yousefi F, Ouellet S, Naye F, Stefan T, Carnovale V, Bergeron F, Ling L, Gheorghiu B, Hagens S, Gareau-Lajoie S, LeBlanc A. The Impact of AI Scribes on Streamlining Clinical Documentation: A Systematic Review. Healthcare (Basel). 2025 Jun 16;13(12):1447. doi: 10.3390/healthcare13121447. PubMed 40565474 ↗
  • Draper TC, Cox T, Lamb-Riddell K, Moretti LA, McCormick J, Trowell S, Kiely J, Luxton R. Clinical AI Scribes in primary care: accuracy, error severity and implications for clinical practice. BMJ Digit Health Ai. 2025 Sep 28;1(1):e000092. doi: 10.1136/bmjdhai-2025-000092. eCollection 2025. PubMed 42712320 ↗
  • Stults CD, Deng S, Martinez MC, Wilcox J, Szwerinski N, Chen KH, Driscoll S, Washburn J, Jones VG. Evaluation of an Ambient Artificial Intelligence Documentation Platform for Clinicians. JAMA Netw Open. 2025 May 1;8(5):e258614. doi: 10.1001/jamanetworkopen.2025.8614. PubMed 40314951 ↗
  • Palm E, Manikantan A, Mahal H, Belwadi SS, Pepin ME. Assessing the quality of AI-generated clinical notes: validated evaluation of a large language model ambient scribe. Front Artif Intell. 2025 Oct 22;8:1691499. doi: 10.3389/frai.2025.1691499. eCollection 2025. PubMed 41199808 ↗

Individual participant data

Plan to share: No — Individual participant data will not be shared. The ethics-approved protocol and the informed consent do not provide for transfer of individual data to third parties, in accordance with the EU General Data Protection Regulation (GDPR) 2016/679 and Lithuanian data protection legislation. The data include consultation audio recordings and clinical documentation. Only aggregated results will be published in scientific journals and presented at conferences.

08

Registry details

Key details

Study ID
NCT07850700
Lead sponsor
National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos
Collaborators
UAB Vocali
Responsible party
Ernestas Sileika (Radiation Oncologist, National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos) — Principal investigator
First posted
Sep 30, 2026
Start date
Nov 1, 2026 (estimated)
Primary completion
Nov 1, 2027 (estimated)
Completion
Dec 31, 2027 (estimated)
Last update
Sep 30, 2026

Study contacts

Ernestas Sileika, MD
Contact
ernestas.sileika@nvc.santa.lt
+37060950402
Ernestas Šileika
principal investigator · National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Not currently enrolling

This study is not yet recruiting, as verified in Sep 2026. You cannot join it, but the record below documents what was studied.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion