[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100660048":3},{"organization":4,"outcomesModule":7,"designInfo":13,"detailedDescription":16,"studyPopulation":17,"armGroups":18,"interventions":11,"overallOfficials":11,"centralContacts":25,"locations":11,"responsibleParty":31,"collaborators":11,"id":35,"slug":36,"hasResults":37,"nctId":38,"briefTitle":39,"officialTitle":40,"acronym":11,"eligibilityCriteria":41,"healthyVolunteers":42,"sex":43,"minAge":44,"maxAge":11,"enrollmentInfo":45,"targetDuration":11,"studyType":48,"phases":11,"briefSummary":49,"conditions":50,"keywords":11,"overallStatus":55,"whyStopped":11,"lastUpdateSubmitDate":56,"lastUpdatePostDateStruct":57,"startDateStruct":60,"completionDateStruct":62,"leadSponsor":64,"locationsCount":11},{"fullName":5,"class":6},"The Third Affiliated Hospital of Southern Medical University","OTHER_GOV",{"primaryOutcomes":8,"secondaryOutcomes":11,"otherOutcomes":11},[9],{"measure":10,"description":11,"timeFrame":12},"The disease exists \u002F does not exist",null,"Baseline (Stage 1 reading) and Week 4 (Stage 2 reading, after a 4-week washout period)",{"allocation":11,"interventionModel":11,"interventionModelDescription":11,"primaryPurpose":11,"observationalModel":14,"timePerspective":15,"maskingInfo":11},"OTHER","RETROSPECTIVE","This is a multi-reader multi-case (MRMC) crossover diagnostic accuracy study using retrospective, de-identified X-ray images. Ten radiologists read the same set of cases under two conditions - unassisted reading and AI-assisted reading - in random order (AB\u002FBA sequence), with a four-week washout between stages. Each radiologist serves as their own control. No patients are prospectively enrolled, and no new imaging procedures are performed.","This study enrolls 10 radiologists from multiple hospitals as readers. They read retrospective, de-identified X-ray images of the chest, abdomen, and lumbar spine, collected from participating hospital image archives and public datasets. The image cases are from adult patients (age 18 years or older) with common X-ray findings across chest, abdominal, and spinal diseases. No patients are prospectively enrolled; all images are reused from routine clinical care after de-identification.",[19,22],{"label":20,"type":11,"description":21,"interventionNames":11},"Unassisted Reading","Radiologists read X-ray images using their usual clinical workflow, without access to any AI tool output. They record their diagnosis, confidence level, and reading time.",{"label":23,"type":11,"description":24,"interventionNames":11},"AI-Assisted Reading","Radiologists read the same X-ray images while having access to the output of an X-ray imaging AI tool, including its diagnostic suggestions and predicted probabilities. The radiologist reviews the AI output and makes the final diagnosis, then records confidence level and reading time.",[26],{"name":27,"role":28,"phone":29,"phoneExt":11,"email":30},"HUANG WeiHong HUANG","CONTACT","+86-13682232823","13682232823@163.com",{"type":32,"investigatorFullName":33,"investigatorTitle":34,"investigatorAffiliation":5,"oldNameTitle":11,"oldOrganization":11},"PRINCIPAL_INVESTIGATOR","Junyan Li","Scientific Research Administrator","100660048","the-impact-of-artificial-intelligence-assisted-x-ray-interpretation-on-radiologists-diagnostic-performance-100660048",false,"NCT07870928","The Impact of Artificial Intelligence-Assisted X-ray Interpretation on Radiologists' Diagnostic Performance","The Impact of Artificial Intelligence-Assisted X-ray Interpretation on Radiologists' Diagnostic Performance: A Multicenter, Multi-Reader, Multi-Case (MRMC) Randomized Cross-Over Study","Inclusion Criteria:\n\n* Participants (radiologists): actively practicing radiologists at participating hospitals, stratified by hospital and professional seniority, trained for the study reading task, and willing to provide written informed consent.\n* Cases (X-ray images): adult patients aged 18 years or older who underwent X-ray imaging of the chest, abdomen, or lumbar spine for clinical indications.\n* Cases with complete basic clinical information.\n* Cases with an established gold-standard diagnosis, defined as the comprehensive clinical diagnosis or a consensus opinion from at least two senior radiologists (deputy chief physician or above).\n\nExclusion Criteria:\n\n* Cases with poor image quality that prevents reliable interpretation.\n* Cases without a clear gold-standard diagnosis or with missing key clinical information.\n* Duplicate cases.\n* Cases in which the patient recently received radiotherapy, chemotherapy, or other treatment that would significantly alter imaging appearance and confound diagnosis.\n* Cases judged by the investigators as unsuitable for the study for any other reason.\n* Radiologists: no additional exclusion criteria beyond the inclusion requirements.",true,"ALL","18 Years",{"count":46,"type":47},500,"ESTIMATED","OBSERVATIONAL","This study tests whether an artificial intelligence (AI) tool helps radiologists read X-rays more accurately.\n\nRadiologists read X-rays to find diseases such as pneumonia, bone fractures, and abdominal problems. AI is a computer program trained on many past X-rays. It may help radiologists spot diseases faster and more correctly. This study compares reading X-rays with the AI tool to reading X-rays without it.\n\nWho takes part\n\n* Ten radiologists from several hospitals.\n* X-ray images from about 300 to 500 past hospital visits.\n* No new X-rays are taken.\n* All names and ID numbers are removed from the images.\n\nWhat happens\n\n* Each radiologist reads the same set of X-rays twice.\n* One time, the radiologist reads without the AI tool.\n* The other time, the radiologist can see the AI result.\n* Half start with no AI and then switch to AI. The other half start with AI and then switch to no AI.\n* There is a four-week break between the two times.\n* The researchers measure how accurate each radiologist is. They also time how long each image takes.\n\nPossible benefits and risks\n\n* The radiologists may get no direct personal benefit.\n* The results may show whether AI can help doctors read X-rays better in the future.\n* This is a low-risk study. The AI tool never tells a patient a diagnosis directly.\n* A qualified radiologist always makes the final diagnosis.\n* Patient data is stored on a locked, encrypted server.",[51,52,53,54],"Nephrolithiasis","Pneumothorax","Intestinal Obstruction","Spondylolysis","NOT_YET_RECRUITING","2026-10-06",{"date":58,"type":59},"2026-10-13","ACTUAL",{"date":61,"type":47},"2026-10",{"date":63,"type":47},"2027-07",{"name":5,"class":6}]