Ambient AI Documentation in Oncology Consultations

NCT07850700 | Not Yet Recruiting

• 2 other identifiers: NVC-2026-0012026/5-1769-1212
• Study Type: observational
• Target: 250
• Locations: 1 country
• Sites: 1

Brief 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.

Conditions

Neoplasms; Clinical Documentation; Artificial Intelligence in Medicine

Keywords

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

Outcome Measures

Primary Outcomes (3)

• 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.

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

• 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.

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

• 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.

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

Secondary Outcomes (4)

• Physician Subjective Workload (NASA-TLX)

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

• System Usability (SUS)

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

• AI Draft Editing Extent

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

• Patient Satisfaction with Consultation (PSQ-18)

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

Study Arms (1)

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

Ambient AI documentation system DEVICE

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

Oncology patients undergoing AI-assisted consultation

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• 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.

You may qualify if:

• 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

You may not qualify if:

• 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

Sponsors & Collaborators

• National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos: lead
• UAB Vocali: collaborator

Study Sites (1)

National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos

Vilnius, Vilnius City, LT-08660, Lithuania

Location

Related Publications (5)

• 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 BACKGROUND

• 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.

  PMID: 40565474 BACKGROUND

• 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.

  PMID: 42712320 BACKGROUND

• 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.

  PMID: 40314951 BACKGROUND

• 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.

  PMID: 41199808 BACKGROUND

MeSH Terms

Conditions

Neoplasms

Study Officials

• Ernestas Šileika

  National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Ernestas Sileika, MD

CONTACT

+37060950402; ernestas.sileika@nvc.santa.lt

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Radiation Oncologist

Study Record Dates

• First Submitted: September 23, 2026
• First Posted: September 30, 2026
• Study Start (Estimated): November 1, 2026
• Primary Completion (Estimated): November 1, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: September 30, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will not share

Locations

LI (1)