[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100644831":3},{"organization":4,"armGroups":7,"interventions":14,"overallOfficials":10,"centralContacts":19,"locations":25,"responsibleParty":44,"collaborators":10,"id":46,"slug":47,"hasResults":48,"nctId":49,"briefTitle":50,"officialTitle":51,"acronym":52,"eligibilityCriteria":53,"healthyVolunteers":48,"sex":54,"minAge":55,"maxAge":10,"enrollmentInfo":56,"targetDuration":10,"studyType":59,"phases":10,"briefSummary":60,"conditions":61,"keywords":10,"overallStatus":67,"whyStopped":10,"lastUpdateSubmitDate":68,"lastUpdatePostDateStruct":69,"startDateStruct":72,"completionDateStruct":74,"leadSponsor":76,"locationsCount":77},{"fullName":5,"class":6},"Hospital of the Ministry of Interior, Kielce, Poland","OTHER",[8],{"label":9,"type":10,"description":11,"interventionNames":12},"Dental radiology records",null,"Structured dental radiology records used to evaluate large language model-assisted generation of narrative dental radiology reports.",[13],"Other: Large language model-assisted radiology report generation",[15],{"type":6,"name":16,"description":17,"armGroupLabels":18,"otherNames":10},"Large language model-assisted radiology report generation","Structured dental radiology data will be processed using a large language model to generate narrative dental radiology reports. The model will transform predefined structured findings into report text for research evaluation. The model will not independently interpret radiographic images, make clinical diagnoses, recommend treatment, or replace professional review. Generated reports will be assessed for completeness, factual consistency with the source data, clarity, terminology, errors, safety, and potential workflow usefulness.",[9],[20],{"name":21,"role":22,"phone":23,"phoneExt":10,"email":24},"Kamila Chęcińska, dr inż.","CONTACT","+48 694 816 344","kamila.checinska@pimmswia.gov.pl",[26],{"facility":27,"status":10,"city":28,"state":29,"zip":30,"country":31,"countryCode":32,"cosmosGeoPoint":33,"geoPoint":38,"contacts":39},"Department of Maxillofacial Surgery","Kielce","Świętokrzyskie Voivodeship","25-375","Poland","PL",{"type":34,"coordinates":35},"Point",[36,37],20.62752,50.87033,{"lat":37,"lon":36},[40],{"name":41,"role":22,"phone":42,"phoneExt":10,"email":43},"Maciej Sikora, dr hab.","+48 41 260 55 85","maciej.sikora@pimmswia.gov.pl",{"type":45,"investigatorFullName":10,"investigatorTitle":10,"investigatorAffiliation":10,"oldNameTitle":10,"oldOrganization":10},"SPONSOR","100644831","large-language-models-for-dental-radiology-report-generation-from-structured-textual-data-100644831",false,"NCT07676318","Large Language Models for Dental Radiology Report Generation From Structured Textual Data","Evaluation of Large Language Models for Transforming Structured Dental Radiology Data Into Narrative Radiology Reports","DENT-LLM","Inclusion Criteria:\n\n* Dental radiology records based on dental X-ray examination performed on the basis of a written referral from a dentist or physician\n* Dental X-ray examinations performed for screening, diagnostic, or treatment-planning purposes\n* Records from patients with permanent dentition after completion of exfoliation\n\nExclusion Criteria:\n\n* Records from patients with mixed dentition before completion of exfoliation\n* Records with incomplete, ambiguous, or internally inconsistent structured dental radiology data preventing reliable report generation\n* Records with missing information required for evaluation of the generated report\n* Duplicate records from the same radiographic examination\n* Records in which anonymization or pseudonymization cannot be ensured","ALL","18 Years",{"count":57,"type":58},100,"ESTIMATED","OBSERVATIONAL","The purpose of this observational methodological study is to evaluate whether large language models can transform structured dental radiology data into clear narrative radiology reports. Large language models are computer programs that can generate text from information provided to them. In this study, the input will consist of organized dental radiology findings, such as chart-style or diagram-based information about teeth and surrounding structures.\n\nDental radiology reports are used by dentists and other health care providers to understand imaging findings and support clinical documentation. Preparing narrative reports may be time-consuming, and the wording of reports may vary between clinicians. This study will examine whether language-model-assisted report generation can produce reports that are complete, accurate, understandable, and clinically useful.\n\nThe study will compare reports generated with support from large language models with traditionally prepared reports. Researchers will also assess how the wording of the prompt and selected model parameters influence report quality. In addition, the study will analyze errors and safety risks in generated reports and evaluate whether such a system could be practical in a dental radiology workflow. The language model will not make treatment decisions, and generated reports will be used for research evaluation only.",[62,63,64,65,66],"Radiography","Oral Health","Large Language Model","Natural Language Processing (NLP)","Dentistry","NOT_YET_RECRUITING","2026-06-24",{"date":70,"type":71},"2026-06-30","ACTUAL",{"date":73,"type":58},"2026-06-29",{"date":75,"type":58},"2026-07-26",{"name":5,"class":6},1]