[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100659515":3},{"organization":4,"outcomesModule":7,"designInfo":34,"detailedDescription":39,"studyPopulation":39,"armGroups":44,"interventions":55,"overallOfficials":39,"centralContacts":39,"locations":39,"responsibleParty":61,"collaborators":39,"id":65,"slug":66,"hasResults":67,"nctId":68,"briefTitle":69,"officialTitle":70,"acronym":39,"eligibilityCriteria":71,"healthyVolunteers":72,"sex":73,"minAge":74,"maxAge":39,"enrollmentInfo":75,"targetDuration":39,"studyType":78,"phases":79,"briefSummary":81,"conditions":82,"keywords":39,"overallStatus":85,"whyStopped":39,"lastUpdateSubmitDate":86,"lastUpdatePostDateStruct":87,"startDateStruct":90,"completionDateStruct":92,"leadSponsor":94,"locationsCount":39},{"fullName":5,"class":6},"Huazhong University of Science and Technology","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":16,"otherOutcomes":23},[9,13],{"measure":10,"description":11,"timeFrame":12},"Presence of at Least One Confirmed Residual Quality-Control Problem in the Final Radiology Report","For each eligible final radiology report, this binary outcome indicates whether at least one confirmed prespecified residual quality-control problem is present (yes\u002Fno). The outcome-assessment process will be independent of the intervention AI system and will include human review. Prespecified categories include textual\u002Fterminology errors, sex or examination-type inconsistencies, formatting\u002Fnumerical errors, findings-impression inconsistencies, lesion location\u002Fcount discrepancies, omissions, and missing or incorrect diagnostic classifications.","During the first month after intervention initiation",{"measure":14,"description":15,"timeFrame":12},"Radiology Report Turnaround Time","Turnaround time will be measured for each eligible radiology report as the elapsed time, from completion of the imaging examination to final report approval. Both timestamps will be obtained from the hospital information systems. Lower values indicate faster completion of the radiology reporting workflow.",[17,20],{"measure":18,"description":19,"timeFrame":12},"Inter-Report Interval","Workflow-pace proxy measured between consecutive reports completed by the same reporting radiologist on the same calendar day. This measure reflects overall reporting pace rather than active time spent on a specific report and will therefore be analyzed as a secondary outcome.",{"measure":21,"description":22,"timeFrame":12},"Inter-Check Interval","Workflow-pace proxy measured between consecutive report approvals completed by the same reviewing radiologist on the same calendar day. This measure reflects overall reviewing pace rather than active time spent reviewing a specific report and will therefore be analyzed as a secondary outcome.",[24,28,31],{"measure":25,"description":26,"timeFrame":27},"Patient Adherence","Patient adherence will be operationalized using downstream clinical records linked to eligible index radiology reports. Indicators may include whether recommended follow-up imaging or other recommended follow-up care is completed, time to completion, and related subsequent health-care utilization used to characterize follow-up behavior. Health-care utilization not linked to a documented recommendation will be treated as exploratory and will not by itself be interpreted as adherence.","During the 3-month secondary evaluation period",{"measure":29,"description":30,"timeFrame":27},"Patient Satisfaction","Patient satisfaction will be assessed by telephone follow-up or a prespecified questionnaire.",{"measure":32,"description":33,"timeFrame":27},"Referring-Clinician Satisfaction","Satisfaction among clinicians who use radiology reports will be assessed using a prespecified questionnaire.",{"allocation":35,"interventionModel":36,"interventionModelDescription":37,"primaryPurpose":38,"observationalModel":39,"timePerspective":39,"maskingInfo":40},"RANDOMIZED","PARALLEL","Individual radiologists are randomized to AI quality-control access or the usual reporting workflow. The unit of randomization is the radiologist. For reports that involve a reporting and a reviewing radiologist, report-level exposure is classified by the randomized assignments of both radiologists, producing a 2×2 reporter-AI-by-reviewer-AI structure.","HEALTH_SERVICES_RESEARCH",null,{"masking":41,"maskingDescription":39,"whoMasked":42},"SINGLE",[43],"OUTCOMES_ASSESSOR",[45,51],{"label":46,"type":47,"description":48,"interventionNames":49},"AI Quality-Control Group","EXPERIMENTAL","Radiologists enrolled in this arm receive access to the study AI radiology report quality-control system within the routine reporting workflow. After report submission, the system performs automated pre-review and may present alerts and suggested revisions. Radiologists retain final decision authority.",[50],"Device: Radiology Report GPT (AI-Based Radiology Report Quality-Control System)",{"label":52,"type":53,"description":54,"interventionNames":39},"Usual Workflow Control Group","NO_INTERVENTION","Radiologists enrolled in this arm continue the existing RIS reporting and reviewing workflow without access to the study AI quality-control alerts or suggested revisions.",[56],{"type":57,"name":58,"description":59,"armGroupLabels":60,"otherNames":39},"DEVICE","Radiology Report GPT (AI-Based Radiology Report Quality-Control System)","Radiology Report GPT is an AI-based pre-review and quality-control system for radiology reports. After a report is submitted, the system may identify potential textual\u002Fterminology errors, patient-sex inconsistencies, formatting or numerical errors, examination-type inconsistencies, findings-impression inconsistencies, lesion location\u002Fcount discrepancies, omissions between findings and impression, and missing or incorrect diagnostic classifications. When a potential issue is detected, the system presents an alert and suggested revision. The radiologist remains responsible for the final report and may accept, modify, or ignore the suggestion. The system does not automatically edit or sign the report. The exact software\u002Fmodel version and the trial deployment mode will be locked and documented before intervention activation.",[46],{"type":62,"investigatorFullName":63,"investigatorTitle":64,"investigatorAffiliation":5,"oldNameTitle":39,"oldOrganization":39},"PRINCIPAL_INVESTIGATOR","Luyang Song","Associate Professor","100659515","ai-based-quality-control-for-radiology-reporting-100659515",false,"NCT07865741","AI-Based Quality Control for Radiology Reporting","Effect of an AI-Based Radiology Report Quality-Control System on Report Accuracy and Workflow Efficiency: A Radiologist-Level Randomized Controlled Trial","Inclusion Criteria:\n\n* Radiologist working in the Department of Radiology at Tongji Hospital.\n* Participated in routine radiology reporting during the pre-intervention reference period.\n* Reporting work includes at least one target imaging examination type\u002Fworkflow covered by the study AI quality-control system (CT, MR, and\u002For CR as applicable).\n* Has a valid physician identifier that permits linkage of radiology reports, workflow timestamps, and randomized study assignment.\n* Able and willing to provide informed consent.\n\nExclusion Criteria:\n\n* No additional exclusion criteria.",true,"ALL","18 Years",{"count":76,"type":77},109,"ESTIMATED","INTERVENTIONAL",[80],"NA","The goal of this clinical trial is to learn whether an artificial intelligence (AI)-based radiology report quality-control system can improve the accuracy and workflow efficiency of routine radiology reporting among active radiologists at Tongji Hospital. The main questions it aims to answer are:\n\n* Does access to the AI quality-control system reduce quality problems remaining in final radiology reports?\n* Does access to the AI quality-control system improve reporting and reviewing efficiency?\n* In the two-stage reporting workflow, do the effects of AI differ depending on whether AI is available to the reporting radiologist, the reviewing radiologist, or both?\n\nResearchers will compare radiologists assigned to receive access to Radiology Report GPT with radiologists who continue the usual reporting workflow without access to the study AI system. Radiologists are randomized at the individual level. Because CT and MR reports commonly involve both a reporting radiologist and a reviewing radiologist, report-level analyses will classify reports according to AI availability at the two workflow stages, resulting in four combinations of reporter and reviewer AI exposure. The primary randomized evaluation will cover the first month after intervention initiation, with prespecified secondary and exploratory analyses extending through 3 months.\n\nParticipants will:\n\n* Be assigned to either the AI quality-control group or the usual-workflow control group.\n* Continue their routine radiology reporting and reviewing work during the study period.\n* If assigned to the AI group, receive access to Radiology Report GPT, which automatically pre-reviews submitted radiology reports and provides quality-control alerts and suggested revisions. Radiologists will retain final decision authority over all reports.\n\nFinal-report accuracy will be assessed independently of the intervention AI system and will include human review. Additional prespecified outcomes will examine report revisions, AI interaction measures, stage-specific and cross-stage workflow effects, recommended imaging follow-up and other downstream health-care utilization, patient satisfaction, and referring-clinician satisfaction.",[83,84],"Radiology","Medical Errors","NOT_YET_RECRUITING","2026-10-08",{"date":88,"type":89},"2026-10-13","ACTUAL",{"date":91,"type":77},"2026-10",{"date":93,"type":77},"2027-01",{"name":5,"class":6}]