AI-assisted chest CT report drafting to save radiologist time
Official title: An Evaluation Study of a Text-Based Chest CT-Assisted Diagnostic System: A Two-stage, Multicenter, Multireader Multicase (MRMC), Self-Crossover Controlled Trial
Run by Shanghai Zhongshan Hospital · NCT07634861 · Data updated 2026-11-12
This study tests whether an AI draft report can help experienced chest radiologists write chest CT reports faster without sacrificing quality.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 100 (estimated) |
| Sponsor | Shanghai Zhongshan Hospital Academic / other |
| Locations | 2 sites (Shanghai and 1 other locations) |
| Status | Recruiting |
| Started | June 20, 2026 |
| Main results expected | December 31, 2026 |
| Study ends | February 15, 2027 |
| Registry record updated | June 9, 2026 |
| Trial ID | NCT07634861 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Board-certified radiologists with at least three years of post-certification experience in thoracic imaging and primary responsibility for chest CT reporting.
✕Probably not a fit
Radiologists without access to or familiarity with AI-assisted tools or those in workflows where AI drafting does not integrate well may not see benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This multicenter study evaluates an AI tool that generates preliminary chest CT report drafts to see if it can speed up report writing while preserving report quality. It uses a two-phase design: a retrospective crossover phase comparing AI-assisted and standard reporting on historical cases, followed by a prospective real-world phase where radiologists interpret new scans with AI support integrated into workflow. Outcomes include time saved per case and blinded quality assessments by senior physicians. The goal is to determine if the AI tool improves efficiency without compromising patient care.
Why it matters
Potential benefit: If successful, radiologists may produce faster reports with equal or better quality, potentially reducing turnaround times for chest CT diagnoses.
How similar studies have gone: Previous studies in similar MRMC designs have shown potential efficiency gains with AI-assisted reporting, though results vary by tool and setting.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Active board certification and ongoing routine clinical practice as an attending radiologist * Independent institutional authority for chest CT image interpretation and final official diagnostic report issuance * A minimum of three years of post-certification clinical experience in specialized thoracic imaging * Legal and cognitive competence for study participation, with voluntary provision of written informed consent after full understanding of study purpose, procedures, risks and benefits Exclusion Criteria: * Direct participation in the development, training or validation of the trial's evaluated AI system * Ongoing participation in concurrent studies with potential risks of interpretation bias, cognitive fatigue or study procedure interference (investigator-assessed) * Any actual or perceived conflict of interest related to the evaluated AI system or its developers that may compromise objectivity in image interpretation and diagnostic reporting
Where it's running
-
Department of Radiology, Zhongshan Hospital, Fudan University
Shanghai, China Recruiting -
United Imaging Intelligence, Shanghai
Shanghai, China Recruiting
Study contacts
- Study coordinator: Xiaodan Ye, MD, PhD
- Email: yuanyxd@163.com
- Phone: +86-13761459998
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Manual chest wall vibration to help breathing and remove chest tubes after thoracic surgery
This trial tests whether manual vibration of the chest wall helps clear secretions and shortens chest tube time for people recovering from thoracic surgery.
-
Perioperative high-dose nicotine patch for pain sensitivity in male smokers undergoing thoracic surgery
We will try a high-dose nicotine patch around the time of surgery to see if it reduces pain sensitivity in adult male smokers having thoracoscopic lung surgery.
-
Ciprofol to reduce heart injury after VATS lung surgery
This trial tests whether using ciprofol instead of propofol during general anesthesia for adults having VATS lung or mediastinal surgery can lower the chance of postoperative heart injury (MINS).
-
Erector spinae block for pain management in thoracic surgery
This study is testing if a special pain relief technique using erector spinae blocks can help patients having lung surgery feel less pain and need fewer pain medications after their operation.
-
Tracking daily steps in older thoracic surgery patients
This study tests whether older patients having thoracic surgery are willing to wear a Fitbit to track their daily steps in the week before their surgery.
-
Registry for thoracic disease specimens
This study is collecting samples from patients with lung diseases like lung cancer to help researchers learn more about these conditions and find better treatments.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.