An interventional study of AI-generated report for chest CT and Standard reporting procedure (no AI assistance) in Thoracic Diseases, sponsored by Shanghai Zhongshan Hospital. Recruiting at 2 sites in China. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-06-09.
Sponsored by Shanghai Zhongshan Hospital · Not applicable, Interventional, and Diagnostic
This study aims to find out if an artificial intelligence (AI) system can help experienced radiologists write chest CT scan reports more quickly without lowering the quality of the report. Chest CT scans are common, and writing reports for them is a major part of a radiologist's job. In this trial, board-certified radiologists will interpret complex chest CT cases. For some cases, they will start with a complete draft report generated by the AI system, which they can review and edit as needed. For other cases, they will write the report from scratch without any AI help, following their usual routine. The main things we are measuring are: 1) how much time the AI draft saves, and 2) whether the final reports created with AI help are as good as or better than those written without it, as judged by other senior doctors who do not know which report came from which method. The hope is that this AI tool can make radiologists' work more efficient while maintaining high standards for patient care.
This study investigates whether an artificial intelligence (AI) system that drafts preliminary radiology reports can help experienced chest CT radiologists work faster while maintaining or improving report quality. The trial is conducted in two sequential phases. The first phase uses a set of complex, real-world historical cases. Radiologists interpret these cases both with and without the help of the AI-generated draft (AI-report) in a controlled, crossover study design. The second phase is a prospective, real-world deployment where the same AI-report system is integrated into the clinical workflow of participating radiologists as they interpret new, incoming chest CT scans in real time. We measure the time it takes to complete reports and, through blinded evaluations by other senior doctors, assess the quality of the final reports created with and without AI assistance. The goal is to determine if this AI tool can make radiologists' work more efficient and support high-quality patient care in actual practice.
1. Detailed Description
1.1 Study Design
This is a two-phase, multicenter, multireader, multicase (MRMC) study designed to evaluate the real-world clinical utility of an AI report generation system (AI-report).
1.2 Objectives
1.3 Study Population
1.4 Intervention
The intervention is the provision of a fully AI-generated draft radiology report (AI-report). In Phase 1, this is provided within a controlled reading platform for historical cases. In Phase 2, the system is integrated into the clinical Picture Archiving and Communication System (PACS)/Radiology Information System (RIS) to generate drafts for prospective, real-time cases.
2. Study Procedures
Phase 1 (Retrospective Crossover): The 400 historical MDT cases are used. The study involves two reading rounds with a washout period. In each round, radiologists interpret a set of cases, with the AI condition (draft provided or not) randomized and crossed over between rounds. Interpretation time is recorded, and all finalized reports are collected for blinded pairwise comparison by the evaluator panel.
Phase 2 (Prospective Deployment): Following Phase 1, the AI-report system is activated in the clinical environment for participating radiologists. During a defined prospective observation period, the system generates drafts for eligible new chest CT scans. Radiologists use these drafts in their daily work. Reporting time and the AI drafts alongside the finalized human-edited reports are collected for analysis. Report quality in this phase is assessed longitudinally and through sampling.
3. Outcome Measures
3.1 Primary Outcomes:
Efficiency: Change in median interpretation time per case with vs. without AI-report assistance (Phase 1) and the distribution of reporting times during real-world use (Phase 2).
Quality: Superiority score from blinded paired comparisons of AI-assisted vs. unassisted reports (Phase 1). Qualitative and quantitative assessment of report adequacy in the prospective cohort (Phase 2).
3.2 Secondary Outcomes:
Clinical significance of radiologist modifications to AI drafts (5-point scale).
System usability and workflow integration scores from post-study surveys.
4. Statistical Analysis
Analysis will account for the MRMC design in Phase 1 using hierarchical models. Phase 2 data will be analyzed using descriptive statistics and statistical process control methods where appropriate. The two phases will be analyzed separately to provide insights into efficacy (Phase 1) and effectiveness (Phase 2).
72 studies on the registry are indexed under Thoracic Diseases; 13 are open to participants now.
This study's planned enrollment of 100 is above the median of 65 across 52 interventional studies indexed under Thoracic Diseases.
Browse Thoracic Diseases studies →Shanghai Zhongshan Hospital is the lead sponsor of 652 studies on the registry; 291 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
This arm involves board-certified radiologists interpreting chest CT cases using the AI system, which generates a preliminary report draft. In Phase 1 (retrospective crossover), each radiologist interprets the same set of historical cases twice: once with the AI-generated draft and once without, with order randomized and a washout period. In Phase 2 (prospective real-world deployment), radiologists use AI drafts for consecutive new chest CT scans in routine practice. The intervention is the provision of the AI-generated report draft; no other changes to standard workflow are introduced.
Device: AI-generated report for chest CT
This arm involves board-certified radiologists interpreting chest CT cases without AI assistance, following standard workflow procedures. In Phase 1 (retrospective crossover), radiologists interpret the same set of historical cases without the AI-generated draft (order randomized with a washout period). In Phase 2 (prospective real-world deployment), this arm represents routine clinical practice where no AI drafts are provided for new chest CT scans. The control condition is standard reporting without AI assistance.
Procedure: Standard reporting procedure (no AI assistance)
A clinical decision support software generates a preliminary report draft for chest CT examinations. Board-certified radiologists then finalize the AI draft.
Standard chest CT reporting procedure without AI assistance. Board-certified radiologists independently interpret chest CT examinations and generate final reports following standard clinical workflow without preliminary AI-generated drafts.
Subjective report quality evaluation based on diagnostic requirements and clinical relevance
Quality is blindly assessed by independent clinicians using pairwise comparisons among three report types: AI-generated raw reports, human-only reports, and human-AI collaborative reports. Superior reports score 1 point, ties score 0.5.
Time frame: CT reports will be distributed for external clinician scoring once all required data are available (typically ≤ 2 weeks post Primary Completion Date); the final aggregated analysis will be completed within 4 weeks post Primary Completion Date.
Significance of radiologist modifications to AI-generated reports
Using a 5-point ordinal scale, independent external clinicians rate the clinical significance of edits made to AI reports. Level 1 denotes minimal changes; Level 5 indicates critical corrections preventing inappropriate/delayed management. Intermediate levels (2-4) represent minor adjustments, beneficial optimizations, and significant refinements impacting diagnostic clarity or treatment selection.
Time frame: CT reports will be distributed for external clinician scoring once all required data are available (typically ≤ 2 weeks post Primary Completion Date); the final aggregated analysis will be completed within 4 weeks post Primary Completion Date.
Plan to share: No
No publications or documents are linked to this record.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.