Generative AI Radiologist's Workstation

NCT07057830 | Not Yet Recruiting

• 1 other identifier: 2025-2
• Study Type: observational
• Target: 27
• Locations: 1 country
• Sites: 2

Brief Summary

This study aims to develop a generative AI assistant for radiologists to automate the processing of electronic medical records (EMRs) and provide relevant clinical information, optimizing diagnostic interpretation workflows.

Conditions

Study Aims to Develop and Validate a Generative AI-assistant Designed to Optimize Radiologists' Workflows and to Evaluate Its Performance

Keywords

LLM, generative AI, radiologist workstation, Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• Radiologist satisfaction levels

  Radiologists' satisfaction levels with the AI-powered workstation will be measured using a specially developed questionnaire.

  6 months

Secondary Outcomes (3)

• Change in time required for medical record analysis

  6 months

• Change in study interpretation time

  6 months

• Change in the number of reporting errors

  6 months

Study Arms (3)

Group A: Reviews full electronic medical record without AI summaries

Group A will review full electronic medical records without AI-generated summaries. Participants will be required to determine the purpose of the radiological examination and prepare a full radiology report (including protocol and conclusion).

Group B: Evaluates AI summaries via validated questionnaire

Group B will receive access to full electronic medical records and to AI-generated summaries, which they will have to evaluate via specially developed and validated questionnaire. Participants will have to determine the purpose of the radiological examination, generate a complete radiology report (protocol + conclusion) and evaluate the AI summaries using a validated questionnaire.

Group C: Receives AI summaries only

Group C participants will receive only AI-generated clinical summaries without access to full electronic medical records. Each radiologist in this group will be required to determine the purpose of the radiological examination and generate a complete radiology report consisting of both protocol documentation and diagnostic conclusion. Comparative analysis will be performed against Groups A and B for all measured outcome parameters.

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

The study population comprises 27 board-certified radiologists from tertiary hospitals, who have more than three years of working experience, proficiency in using UMIAS and no competing research involvement.

You may qualify if:

• Board-certified practicing radiologist;
• ≥3 years of experience in diagnostic imaging;
• Proficiency in using UMIAS systems;
• Signed informed consent form.

You may not qualify if:

• Participation in other studies;
• Unwillingness to adopt new technologies in daily practice;
• Conflict of interest.

Sponsors & Collaborators

• Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department: lead

Study Sites (2)

MIREA - Russian Technological University

Moscow, 119454, Russia

Location

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department

Moscow, 127051, Russia

Location

Study Officials

• Yuriy A. Vasilev, PhD, MD

  Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department

  STUDY DIRECTOR

Central Study Contacts

Anton V. Vladzymyrskyy, PhD, MD

CONTACT

+7 (495) 276-04-36; VladzimirskijAV@zdrav.mos.ru

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Deputy Director for Research

Study Record Dates

• First Submitted: June 30, 2025
• First Posted: July 10, 2025
• Study Start: July 1, 2025
• Primary Completion: December 31, 2025
• Study Completion: February 1, 2026
• Last Updated: July 10, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will not share

Locations

RU (2)