Using Artificial Intelligence to Improve Radiologists' Performance in Radiology Report Writing: a Randomised Controlled Trial

This is a randomised controlled trial to assess whether artificial intelligence software can improve radiologists' performance in radiology report writing and improve the quality of radiology reports.

Study Overview

• Status: Recruiting
• Conditions: Healthy
• Intervention / Treatment: Behavioral: Control group; Behavioral: Experimental group

• Study Type: Interventional
• Enrollment (Estimated): 100
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Lian Yang; Phone Number: 18986273791; Email: yanglian@hust.edu

Study Locations

• China
  • Hubei
    • Wuhan, Hubei, China, 430000
      • Recruiting
      • Union Hospital，Tongji Medical College，Huazhong University of Science and Technology
      • Contact: Lian Yang; Phone Number: 18986273791; Email: yanglian@hust.edu

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

1. Radiologists who submit reports;
2. Clinical experience of less than 10 years and more than six months;
3. An average of more than 10 radiology reports are submitted per day;
4. Participants provided signed informed consent.

Exclusion criteria：

1. Radiologists who review reports;
2. Clinical experience of less than 6 months or more than 10 years;
3. An average of less than 10 radiology reports are submitted per day.）

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Experimental group	Behavioral: Experimental group; the radiologists enrolled in the study will be randomly divided into two groups: the experimental group used AI(Artificial Intelligence) software to assist in the submission of radiology reports and the control group did not use any AI software to submit their reports
Placebo Comparator: Control group	Behavioral: Control group; the radiologists enrolled in the study will be randomly divided into two groups: the experimental group used AI(Artificial Intelligence) software to assist in the submission of radiology reports and the control group did not use any AI software to submit their reports

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Error rates in radiology reports	Statistical analysis of errors in radiology reports submitted by study and control group physicians	1 month

Collaborators and Investigators

• Sponsor: Wuhan Union Hospital, China

Study record dates

Study Major Dates

• Study Start (Estimated): April 1, 2025
• Primary Completion (Estimated): April 30, 2025
• Study Completion (Estimated): April 30, 2025

Study Registration Dates

• First Submitted: March 26, 2025
• First Submitted That Met QC Criteria: March 26, 2025
• First Posted (Actual): April 2, 2025

Study Record Updates

• Last Update Posted (Actual): April 2, 2025
• Last Update Submitted That Met QC Criteria: March 26, 2025
• Last Verified: March 1, 2025

More Information

Terms related to this study

• Other Study ID Numbers: 2025-0033

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No