Ignite Creation Date:
2025-12-25 @ 4:53 AM
Ignite Modification Date:
2025-12-26 @ 3:54 AM
Study NCT ID:
NCT06753318
Status:
NOT_YET_RECRUITING
Last Update Posted:
2024-12-31
First Post:
2024-12-17
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
Validation of Joint-AI in Diagnosing Pancreatic Solid Lesions
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D010190', 'term': 'Pancreatic Neoplasms'}, {'id': 'D010195', 'term': 'Pancreatitis'}, {'id': 'D000081012', 'term': 'Autoimmune Pancreatitis'}], 'ancestors': [{'id': 'D004067', 'term': 'Digestive System Neoplasms'}, {'id': 'D009371', 'term': 'Neoplasms by Site'}, {'id': 'D009369', 'term': 'Neoplasms'}, {'id': 'D004701', 'term': 'Endocrine Gland Neoplasms'}, {'id': 'D004066', 'term': 'Digestive System Diseases'}, {'id': 'D010182', 'term': 'Pancreatic Diseases'}, {'id': 'D004700', 'term': 'Endocrine System Diseases'}, {'id': 'D050500', 'term': 'Pancreatitis, Chronic'}, {'id': 'D001327', 'term': 'Autoimmune Diseases'}, {'id': 'D007154', 'term': 'Immune System Diseases'}, {'id': 'D002908', 'term': 'Chronic Disease'}, {'id': 'D020969', 'term': 'Disease Attributes'}, {'id': 'D010335', 'term': 'Pathologic Processes'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'DOUBLE', 'whoMasked': ['PARTICIPANT', 'OUTCOMES_ASSESSOR'], 'maskingDescription': 'During the endoscopic ultrasound procedure, the allocation of participants will be masked to the endoscopists'}, 'primaryPurpose': 'DIAGNOSTIC', 'interventionModel': 'PARALLEL', 'interventionModelDescription': '1. First, participants are randomized into three parallel groups: conventional diagnosis group, Joint-AI assistance group, and Interpretable Joint-AI assistance group.\n2. For participants within the Joint-AI assistance group and Interpretable Joint-AI assistance group, their groups will be switched after a washout period.'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 716}}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2025-01', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2024-12', 'completionDateStruct': {'date': '2026-01', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2024-12-22', 'studyFirstSubmitDate': '2024-12-17', 'studyFirstSubmitQcDate': '2024-12-22', 'lastUpdatePostDateStruct': {'date': '2024-12-31', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2024-12-31', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2026-01', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Rate of correct diagnostic classification with assistance of the Joint-AI Model', 'timeFrame': 'Through study completion, an average of 1 year', 'description': 'The rate of correct diagnoses in discriminating pancreatic cancer from other non-cancer lesions, determined by comparing endoscopist diagnosis assisted by the Joint-AI model against the final histopathological diagnosis (reference standard).'}, {'measure': 'Rate of correct diagnostic classification with assistance of the Interpretable Joint-AI Model', 'timeFrame': 'Through study completion, an average of 1 year', 'description': 'The rate of correct diagnoses in discriminating pancreatic cancer from other non-cancer lesions, determined by comparing endoscopist assessments assisted by the Interpretable Joint-AI model against the final histopathological diagnosis (reference standard)'}], 'secondaryOutcomes': [{'measure': 'Rate of correct diagnostic classification of the Joint-AI model and the interpretable Joint-AI model', 'timeFrame': 'Through study completion, an average of 1 year', 'description': 'Diagnostic accuracy of the AI models in this prospectively collected dataset.'}, {'measure': 'Endoscopist-reported confidence score in diagnosis with AI assistance (the score is on a scale of 0%-100%, where 0 represents "not confident at all" and 100 represents "completely confident")', 'timeFrame': 'Through study completion, an average of 1 year', 'description': 'Endoscopist-reported confidence in diagnosis will be measured on a scale ranging from 0 to 100, where 0 represents "not confident at all" and 100 represents "completely confident." Higher scores indicate greater diagnostic confidence. The confidence scores will be assessed separately for diagnoses made using the Joint-AI model and the interpretable Joint-AI model.'}, {'measure': 'Rate of correct diagnostic classification of endoscopists without AI assistance', 'timeFrame': 'Through study completion, an average of 1 year'}]}, 'oversightModule': {'isUsExport': False, 'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['pancreatic cancer', 'artificial intelligence', 'endoscopic ultrasound'], 'conditions': ['Pancreatic Cancer', 'Pancreatitis', 'Pancreatic Neuroendocine Neoplasms (pNETs)', 'Autoimmune Pancreatitis', 'Solid Pseudopapillary Neoplasm of the Pancreas']}, 'descriptionModule': {'briefSummary': 'This clinical trial aims to learn if a multimodal artificial intelligence (AI) model can enhance the diagnosis of pancreatic solid lesions. The main questions it aims to answer are:\n\n1. Does the AI model enhance the diagnostic performance of endoscopists in diagnosing pancreatic solid lesions?\n2. Does the addition of interpretability analysis further improve the diagnostic performance of the assisted endoscopists? Researchers will compare the diagnostic performance of endoscopists with or without the assistance of the AI model.\n\nParticipants will:\n\n1. Their clinical data will be prospectively collected.\n2. They will be randomized to the AI-assist group and the conventional diagnosis group.', 'detailedDescription': "The investigators have previously developed a multimodal AI model (Joint-AI) based on endoscopic ultrasound images and clinical data to diagnose pancreatic solid lesions. This study aims to improve the Joint-AI model's performance with a prospectively collected dataset and validate it through a randomized controlled clinical trial."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Imaging examinations (MRI, CT, B-ultrasound) show a solid mass in the pancreas, which requires endoscopic ultrasound guided-fine needle aspiration/biopsy (EUS-FNA/B) to clarify the nature of the lesion in patients.\n* Written consent provided\n\nExclusion Criteria:\n\n* Age under 18 years old'}, 'identificationModule': {'nctId': 'NCT06753318', 'briefTitle': 'Validation of Joint-AI in Diagnosing Pancreatic Solid Lesions', 'organization': {'class': 'OTHER', 'fullName': 'Huazhong University of Science and Technology'}, 'officialTitle': 'Validation of a Multimodal Artificial Intelligence Model in in Diagnosing Pancreatic Solid Lesions: a Prospective, Multicenter, Randomized, Controlled Trial', 'orgStudyIdInfo': {'id': 'Joint-AI 2024'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'NO_INTERVENTION', 'label': 'Conventional diagnosis', 'description': 'Endoscopists diagnose pancreatic solid lesions according to endoscopic ultrasound images and clinical data.'}, {'type': 'EXPERIMENTAL', 'label': 'Joint-AI assisted diagnosis', 'description': 'Endoscopists diagnose pancreatic solid lesions based on endoscopic ultrasound images, clinical data, and predictions made by the Joint-AI model.', 'interventionNames': ['Diagnostic Test: The assistance of the Joint-AI model']}, {'type': 'EXPERIMENTAL', 'label': 'Interpretable Joint-AI assisted diagnosis', 'description': 'Endoscopists diagnose pancreatic solid lesions based on endoscopic ultrasound images, clinical data, predictions given by the Joint-AI, and interpretability analysis results used to improve the transparency of the decision-making process of the Joint-AI model.', 'interventionNames': ['Diagnostic Test: The assistance of the interpretable Joint-AI model']}], 'interventions': [{'name': 'The assistance of the Joint-AI model', 'type': 'DIAGNOSTIC_TEST', 'description': 'Predictions given by the Joint-AI model will be provided to the endoscopists during their diagnosis', 'armGroupLabels': ['Joint-AI assisted diagnosis']}, {'name': 'The assistance of the interpretable Joint-AI model', 'type': 'DIAGNOSTIC_TEST', 'description': 'Predictions given by the Joint-AI model and the results of the interpretability analysis will be provided to the endoscopists during their diagnosis', 'armGroupLabels': ['Interpretable Joint-AI assisted diagnosis']}]}, 'contactsLocationsModule': {'locations': [{'zip': '430030', 'city': 'Wuhan', 'state': 'Hubei', 'country': 'China', 'contacts': [{'name': 'Bin Cheng', 'role': 'CONTACT', 'email': 'b.cheng@tjh.tjmu.edu.cn', 'phone': '86-13986097542'}], 'facility': 'Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology', 'geoPoint': {'lat': 30.58333, 'lon': 114.26667}}], 'centralContacts': [{'name': 'Bin Cheng', 'role': 'CONTACT', 'email': 'b.cheng@tjh.tjmu.edu.cn', 'phone': '86-13986097542'}]}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Huazhong University of Science and Technology', 'class': 'OTHER'}, 'collaborators': [{'name': 'Beijing Union Hosptial', 'class': 'UNKNOWN'}, {'name': 'Affiliated Drum Tower Hospital of Nanjing University Medical School', 'class': 'UNKNOWN'}, {'name': 'Shanghai Longhua Hospital', 'class': 'UNKNOWN'}, {'name': 'Beijing Friendship Hospital', 'class': 'OTHER'}, {'name': 'Qilu Hospital of Shandong University', 'class': 'OTHER'}, {'name': 'Sir Run Run Shaw Hospital', 'class': 'OTHER'}], 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Professor', 'investigatorFullName': 'Bin Cheng', 'investigatorAffiliation': 'Huazhong University of Science and Technology'}}}}