AI-Assisted Chest-CT Reporting for Enhanced Speed and Quality (The DOUBLE-ACE Study)

NCT07640906 | Not Yet Recruiting DMC

• 1 other identifier: B2025-151(2)
• Study Type: observational
• Target: 75
• Locations: 1 country
• Sites: 2

Brief Summary

The goal of this observational study is to learn if an AI assistant tool can help doctors who read chest CT scans (called radiologists) write their reports faster and just as well or better. Chest CT scans are common pictures taken of the inside of the chest to help with diagnosis. The main questions the study aims to answer are: (1) Does using the AI tool save radiologists time when writing their reports? (2) Are the final reports written with the AI tool's help as good as or better than reports written without it? To answer these questions, researchers will compare two time periods at several hospitals. They will look at how long it took to write reports and how good the reports were, both from a time before the AI tool was available and from a time after it was in regular use. In this study, radiologists will use the AI tool as part of their normal daily work. The tool is built into the computer system they already use to look at scans. Researchers will then measure the time and quality of the reports produced during their regular shifts.

Conditions

Thoracic Diseases; Chest CT Scan; Artificial Intelligence (AI) in Diagnosis

Keywords

Chest CT scan; artificial intelligence

Outcome Measures

Primary Outcomes (2)

• Change in Average Image Interpretation Time

  Comparison of the average time taken by participating radiologists to complete standard chest CT interpretation tasks, measured both with and without use of the automated interpretation tool. The time will be recorded from the start to the completion of each individual reading case.

  Time of interpretation will be collected once the data become fully available (generally within 2 weeks after the planned primary completion date). Final aggregated analysis will be completed within 3 months after the collection of potential confounders.

• Change in Chest CT Report Quality Score

  Comparison of the subjective quality of chest CT reports written with and without automated tool support. Blinded external experts will evaluate the subjective quality of all sampled reports using a 10-point rating scale, with scores ranging from 1 (poorest quality) to 10 (highest quality).

  Reports will be distributed to external experts for scoring once the data become available, with scoring results returned within 7 days. Final aggregated analysis will be completed within 3 months after the collection of potential confounders.

Other Outcomes (1)

• Radiologist Editing Intensity on AI-Generated Report Drafts

  Report texts will be collected once the data become fully available (generally within 2 weeks after the planned primary completion date). Final aggregated analysis will be completed within 3 months after the collection of potential confounders.

Study Arms (1)

Radiologists with/without chest CT interpretation AI assistant

This study employs a single-arm, within-subjects design. A cohort of radiologists will be followed through two sequential practice phases: (1) Baseline (Control) Phase: Participants interpret and report on chest CT scans using their standard clinical workflow without AI assistance. (2) AI-available phase: The same participants interpret and report on a different set of chest CT scans with the integrated AI-assisted reporting system activated in their workflow.

Device: An AI-assisted reporting system integrated into the clinical workflow, providing automated draft generation to assist with chest CT interpretation

Interventions

An AI-assisted reporting system integrated into the clinical workflow, providing automated draft generation to assist with chest CT interpretation DEVICE

The intervention under evaluation is an AI-assisted diagnostic reporting system, integrated directly into the radiologists' workflow. The system analyzes the CT images in real time using an AI model and automatically generates a structured, preliminary radiology report draft. The interpreting radiologist reviews this AI-generated draft, which is presented within their familiar reporting interface. The radiologist then actively edits, confirms, supplements, or overrides the draft content as necessary before finalizing and signing the report. This intervention is distinguished from other AI tools by its focus on end-to-end reporting efficiency via integrated draft generation within the radiologist's classic workflow. It moves beyond simple abnormality detection or highlighting by generating a complete, structured narrative report draft, aiming to reduce dictation/typing time and minimize oversight of findings.

Radiologists with/without chest CT interpretation AI assistant

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population is defined as follows: 1. Radiologists: Attending radiologists who routinely interpret chest CT scans as part of their clinical duties at the participating medical centers. 2. Chest CT Scans: Clinically indicated, non-contrast chest CT examinations acquired from the patient populations served by the participating centers. The scans are stratified into two groups based on the date of acquisition: before and after the implementation of the AI reporting system.

You may qualify if:

• For Radiologists
• Board-certified radiologists specializing in or routinely performing thoracic imaging.
• Employed at one of the participating study centers for the entire duration of both the without-AI and with-AI study periods.
• Interpreted a minimum of eligible chest CT scans (e.g., \> 50 scans) during both the without-AI and with-AI data collection periods.
• For Chest CT Scans
• Non-contrast chest CT examinations performed for any clinical indication.
• Scans completed and finalized during the defined with-AI or without-AI study periods.
• Patient age 18 years or older at the time of the scan.

You may not qualify if:

• For Radiologists:
• Radiologists who joined, left, or were on extended leave (e.g., \>4 weeks) from the participating center between the with-AI and without-AI study periods.
• Radiologists who interpreted fewer than the minimum required number of eligible scans in either study period.
• Radiologists who voluntarily decline to have their de-identified performance data included in the study analysis.
• Radiologists who decline to provide demographic or occupational information (e.g., years of professional experience or sex)-variables that may serve as potential confounders-will be excluded from adjusted and stratified analyses that require such covariates.
• For Chest CT Scans
• CT scans of pediatric patients (age \< 18 years).
• Contrast-enhanced chest CT studies.
• Studies performed for specific procedural guidance (e.g., biopsy, ablation).
• Studies deemed technically inadequate for primary interpretation by radiologist (e.g., severe motion artifact, incomplete study).
• Studies for which the AI system fails to generate a valid preliminary report draft. This includes possible system failures, algorithm errors, or cases where the generated draft is deemed technically unusable (e.g., empty, garbled, or based on critically flawed image analysis).
• The lack of relevant information (diagnosis, clinical scenario, etc.). Chest CT data will be excluded from corresponding analyses if the required information, which is necessary for confounding control, subgroup analyses, or other pre-specified analyses, is unavailable. Such scenarios include data that cannot be retrospectively retrieved, incompletely recorded, or restricted due to ethical or institutional requirements.

Sponsors & Collaborators

• Shanghai Zhongshan Hospital: lead

Study Sites (2)

Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai

Shanghai, China

Location

United Imaging Intelligence, Shanghai, Shanghai

Shanghai, China

Location

Related Publications (2)

• Teo ZL, Thirunavukarasu AJ, Elangovan K, Cheng H, Moova P, Soetikno B, Nielsen C, Pollreisz A, Ting DSJ, Morris RJT, Shah NH, Langlotz CP, Ting DSW. Generative artificial intelligence in medicine. Nat Med. 2025 Oct;31(10):3270-3282. doi: 10.1038/s41591-025-03983-2. Epub 2025 Oct 6.

  PMID: 41053447 BACKGROUND

• Chen SF, Alyakin A, Seas A, Yang E, Choi JJ, Lee JV, Chen AL, Warman PI, Bitolas RT, Steele RJ, Alber DA, Oermann EK. LLM-assisted systematic review of large language models in clinical medicine. Nat Med. 2026 Mar;32(3):1152-1159. doi: 10.1038/s41591-026-04229-5. Epub 2026 Mar 3.

  PMID: 41776077 BACKGROUND

MeSH Terms

Conditions

Thoracic Diseases

Condition Hierarchy (Ancestors)

Respiratory Tract Diseases

Study Officials

• Mengsu Zeng, MD, PhD

  Department of Radiology, Zhongshan Hospital, Fudan University

  STUDY CHAIR

• Dinggang Shen, PhD

  United Imaging Intelligence, Shanghai

  STUDY DIRECTOR

• Jianying Gu, MD, PhD

  Department of Radiology, Zhongshan Hospital, Fudan University

  STUDY DIRECTOR

• Dijia Wu, PhD

  United Imaging Intelligence, Shanghai

  STUDY DIRECTOR

Central Study Contacts

Xiaodan Ye, MD, PhD

CONTACT

+86-13761459998; yuanyxd@163.com

Weiqiu Jin, MD

CONTACT

jinwqzsh@fudan.edu.cn

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: May 27, 2026
• First Posted: June 11, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): August 1, 2026
• Study Completion (Estimated): December 1, 2026
• Last Updated: June 11, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share

Locations

CN (2)