Ignite Creation Date:
2025-12-24 @ 3:51 PM
Ignite Modification Date:
2025-12-28 @ 4:56 PM
Study NCT ID:
NCT07166692
Status:
NOT_YET_RECRUITING
Last Update Posted:
2025-09-10
First Post:
2025-08-25
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Evaluation of a Retrieval Augmented Large Language Model as a Diagnostic Copilot in Rheumatology
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D004194', 'term': 'Disease'}], 'ancestors': [{'id': 'D010335', 'term': 'Pathologic Processes'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'SINGLE', 'whoMasked': ['OUTCOMES_ASSESSOR'], 'maskingDescription': 'The evaluation of responses will be performed by assessors blinded to participant identity and treatment assignment.'}, 'primaryPurpose': 'DIAGNOSTIC', 'interventionModel': 'PARALLEL'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 82}}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2025-10-02', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-09', 'completionDateStruct': {'date': '2026-02-02', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-09-08', 'studyFirstSubmitDate': '2025-08-25', 'studyFirstSubmitQcDate': '2025-09-08', 'lastUpdatePostDateStruct': {'date': '2025-09-10', 'type': 'ESTIMATED'}, 'studyFirstPostDateStruct': {'date': '2025-09-10', 'type': 'ESTIMATED'}, 'primaryCompletionDateStruct': {'date': '2026-02-02', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Diagnostic accuracy of top diagnosis', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'Participants in each group will make at least one disease suggestion (top diagnosis) and up to a total of a maximum of 3 suggestions. Percentage of exact matches of the top suggestion with the actual diagnosis will be analyzed'}], 'secondaryOutcomes': [{'measure': 'Diagnostic accuracy of top 3 suggestions', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'Participants in each group will make at least one disease suggestion (top diagnosis) and up to a total of a maximum of 3 suggestions. Percentage of exact matches with the actual diagnosis included in the top 3 suggestions will be analyzed'}, {'measure': 'Diagnostic confidence', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'For each case participants will be asked for their diagnostic confidence (VAS 0-10). The mean score will be compared between groups.'}, {'measure': 'Time spent for diagnosis', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'We will compare how much time (in seconds) participants spend per case between the two study arms.'}, {'measure': 'Perceived Information Timeliness', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'Perceived ability to receive the information needed without delay (Likert scale from 1 to 5)'}, {'measure': 'Perceived diagnostic support quality', 'timeFrame': 'directly (within 10 minutes) after Intervention', 'description': 'Perceived quality of the diagnostic support (Likert scale from 1 to 5)'}, {'measure': 'Diagnostic reasoning', 'timeFrame': 'during evaluation', 'description': 'For each case, participants will receive 1 point for each plausible diagnosis and 2 points for a completely correct response. The total scores will be compared between the randomized groups.'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Clinical reasoning', 'Large language models', 'Computer-assissted diagnosis', 'Rheumatology'], 'conditions': ['Diagnosis']}, 'descriptionModule': {'briefSummary': 'This trial evaluates whether providing physicians with access to Prof. Valmed, a clinical decision support medical product, improves identification of rheumatic diseases and formulation of differential diagnoses compared with conventional decision support.', 'detailedDescription': "Advanced AI, particularly large language models, shows promise for enhancing clinical reasoning, yet most systems such as ChatGPT are not certified as medical products. Prof. Valmed is a clinical decision support medical product designed to assist physicians in diagnostic decision making. Given frequent referral problems and diagnostic delays in rheumatology, evaluating such support is highly relevant for clinical workflows.\n\nThis randomized controlled trial will test whether access to Prof. Valmed improves physicians' diagnostic performance in cases of suspected rheumatic disease compared with conventional decision support. Participants will be randomized to either use Prof. Valmed or rely on conventional tools while working through standardized clinical cases. For each case, participants will submit up to three differential diagnoses and a confidence rating. Independent reviewers, blinded to group allocation, will adjudicate accuracy. Findings will clarify the benefits and limitations of integrating Prof. Valmed into routine practice."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['CHILD', 'ADULT', 'OLDER_ADULT'], 'healthyVolunteers': True, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Participants must be licensed physicians.\n* Training in rheumatology, internal medicine, emergency medicine, family medicine, dermatology or orthopedics.\n\nExclusion Criteria:\n\n* Not currently practicing clinically.'}, 'identificationModule': {'nctId': 'NCT07166692', 'acronym': 'ALLIANCE', 'briefTitle': 'Evaluation of a Retrieval Augmented Large Language Model as a Diagnostic Copilot in Rheumatology', 'organization': {'class': 'OTHER', 'fullName': 'Philipps University Marburg'}, 'officialTitle': 'Evaluation of a Retrieval Augmented Large Language Model as a Diagnostic Copilot in Rheumatology', 'orgStudyIdInfo': {'id': '24-221-1'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'Prof. Valmed', 'description': 'Group will be given access to Prof. Valmed.', 'interventionNames': ['Other: Prof. Valmed']}, {'type': 'NO_INTERVENTION', 'label': 'Control group', 'description': 'Group will not be given access to Prof. Valmed but will be encouraged to use any resources they wish besides large language models (UpToDate, etc).'}], 'interventions': [{'name': 'Prof. Valmed', 'type': 'OTHER', 'description': 'Prof Valmed. decision support system.', 'armGroupLabels': ['Prof. Valmed']}]}, 'contactsLocationsModule': {'locations': [{'zip': '35043', 'city': 'Marburg', 'country': 'Germany', 'contacts': [{'name': 'Johannes Knitza, MD PhD MHBA', 'role': 'CONTACT', 'email': 'knitza@uni-marburg.de', 'phone': '+49 (0)6421 586 2589'}], 'facility': 'Institute for Digital Medicine, University Hospital of Giessen and Marburg, Philipps University Marburg', 'geoPoint': {'lat': 50.80904, 'lon': 8.77069}}], 'centralContacts': [{'name': 'Johannes Knitza, MD PhD MHBA', 'role': 'CONTACT', 'email': 'knitza@uni-marburg.de', 'phone': '0049 06421 586 2589'}], 'overallOfficials': [{'name': 'Johannes Knitza, MD PhD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'University Marburg'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Philipps University Marburg', 'class': 'OTHER'}, 'collaborators': [{'name': 'University Medical Center Hamburg-Eppendorf (UKE)', 'class': 'UNKNOWN'}, {'name': 'Oslo University Hospital', 'class': 'OTHER'}, {'name': 'Diakonhjemmet Hospital', 'class': 'OTHER'}, {'name': 'University Hospital Erlangen', 'class': 'OTHER'}, {'name': 'Charite University, Berlin, Germany', 'class': 'OTHER'}, {'name': 'Rheumazentrum Ruhrgebiet', 'class': 'OTHER'}, {'name': 'University of Lausanne Hospitals', 'class': 'OTHER'}, {'name': 'Klinikum Fulda', 'class': 'OTHER'}], 'responsibleParty': {'type': 'SPONSOR'}}}}