Ignite Creation Date:
2026-03-26 @ 3:16 PM
Ignite Modification Date:
2026-03-30 @ 8:55 PM
Study NCT ID:
NCT07468357
Status:
NOT_YET_RECRUITING
Last Update Posted:
2026-03-12
First Post:
2026-01-29
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Human-AI Uncertainty Callibration for Improved Skin Lesion Segmentation
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2026-03-25'}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'NONE'}, 'primaryPurpose': 'DIAGNOSTIC', 'interventionModel': 'PARALLEL', 'interventionModelDescription': 'Each participant will undergo the same training phase. Subsequently, the participants are randomized into one of the intervention arms. Each participant will be their own control.'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 50}}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2026-03-01', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2026-03', 'completionDateStruct': {'date': '2026-11', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2026-03-11', 'studyFirstSubmitDate': '2026-01-29', 'studyFirstSubmitQcDate': '2026-03-11', 'lastUpdatePostDateStruct': {'date': '2026-03-12', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2026-03-12', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2026-07', 'type': 'ESTIMATED'}}, 'outcomesModule': {'otherOutcomes': [{'measure': 'Time', 'timeFrame': 'Immediately after the intervention.', 'description': 'Time from the start to finish of each case with a split time corresponding to the end of the control phase (the time "Show AI input"-button is clicked).'}], 'primaryOutcomes': [{'measure': 'Accuracy', 'timeFrame': 'Immediately after the intervention.', 'description': 'Diagnostic accuracy in differentiating between melanoma, nevus, and benign keratosis. Defined as the percentage of correct diagnoses. Ground truth is based on histopathologically verified diagnoses.'}], 'secondaryOutcomes': [{'measure': 'Uncertainty', 'timeFrame': 'Immediately after the intervention.', 'description': 'Changes in self-assesed uncertainty ranging from 0 (very uncertain) to 10 (very certain) from pre- to post-intervention.'}, {'measure': 'Cut-off uncertainty', 'timeFrame': 'Immediately after the intervention.', 'description': 'The self-assessed uncertainty of cases where the participant has clicked a "would you like to discuss this case with a collegue"-button.'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Dermatology', 'AI', 'Artificial Intelligence', 'Uncertainty Calibration', 'Dermoscopy', 'Bayesian Deep Learning', 'Human-AI Decision Model'], 'conditions': ['Skin Lesions']}, 'referencesModule': {'references': [{'type': 'BACKGROUND', 'citation': 'Kampen, P.J.T. et al. (2026). Uncertainty-Aware Classification: A Human-Guided Bayesian Deep Learning Framework. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2025. Lecture Notes in Computer Science, vol 16166. Springer, Cham. https://doi.org/10.1007/978-3-032-06593-3_19'}]}, 'descriptionModule': {'briefSummary': 'The goal of this randomized controlled study is to compare the effect of a new, personalized uncertainty-aware decision model (FDM) to a standard image recognition model in improving the diagnostic accuracy while reducing diagnostic uncertainty in experienced dermatologists tasked with differentiating between melanomas, moles and other benign skin lesions. The main question it aims to answer: Is the FDM a feasible method for an improved human AI partnership in which trust is build, misdiagnoses are avoided, and uncertainty is duly introduced or reduced.\n\nThe investigators expect to see only a slight increase in collective diagnostic accuracy for both interventions as the the human participants are skilled dermatologist and thus have high accuracies pre-intervention.\n\nThe investigators expect to see a higher increase in diagnostic certainty for the FDM intervention compared to the diagnostic certainty in the Base Model intervention.\n\nThe investigators expect to see a higher amount of diagnosis changes from incorrect to correct in the FDM group compared to the Base Model group.\n\nThe investigators do not expect any learning effect during the study.\n\nParticipants will start by answering a series of training cases consisting of images of skin lesions. These are used to train their individual FDM (only for the FDM-intervention group). From here, the participants will be randomized into two arms determining which of the two interventions they are exposed to. The participants will solve each case withouth any intervention first, and this reply will act as a control.', 'detailedDescription': 'A detailed description of the FDM is presented in the references.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['CHILD', 'ADULT', 'OLDER_ADULT'], 'healthyVolunteers': True, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Board certified dermatologists with clinical experience in dermoscopic diagnosis.\n\nExclusion Criteria:\n\n* Doctors who have not yet finished their specialization and dermatologists.\n* Dermatologists without clinical experience in dermoscopic diagnosis.'}, 'identificationModule': {'nctId': 'NCT07468357', 'briefTitle': 'Human-AI Uncertainty Callibration for Improved Skin Lesion Segmentation', 'organization': {'class': 'OTHER', 'fullName': 'Copenhagen Academy for Medical Education and Simulation'}, 'officialTitle': 'The Effect of Human-AI Uncertainty Calibration vs. AI Uncertainty Alone on the Diagnostic Accuracy of Human Experts for Skin Lesions - a Randomized Controlled Trial.', 'orgStudyIdInfo': {'id': 'F-25076782'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'ACTIVE_COMPARATOR', 'label': 'Base Model', 'description': 'The study participant is presented with a patient case including patient demographics (gender, age, placement of lesion) and two lesion images: 1 overview image, and 1 dermoscopic image. They are asked first to indicate an initial diagnosis along with their self-perceived uncertainty for this specific case before they receive Intervention 1. This initial diagnosis will act as the control. Intervention 1 is AI-generated multi-class probabilities (from a model trained on a large dataset of dermoscopic and overview images similar to the ones used for testing) and only the most likely diagnosis is presented accompanied by uncertainty estimates in percent.\n\nAfter the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty.', 'interventionNames': ['Other: Base Model']}, {'type': 'EXPERIMENTAL', 'label': 'FDM', 'description': 'The initial diagnosis and indication of self-perceived uncertainty follows the same procedure as for Intervention 1. Intervention 2 is the most likely diagnosis accompanied by a calibrated uncertainty generated by the FDM model (i.e. trained on the study participants previous answers + the crowd annotations on the training data + the base model prediction).\n\nAfter the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty.', 'interventionNames': ['Other: FDM']}], 'interventions': [{'name': 'Base Model', 'type': 'OTHER', 'otherNames': ['Intervention 1'], 'description': 'See arm description.', 'armGroupLabels': ['Base Model']}, {'name': 'FDM', 'type': 'OTHER', 'otherNames': ['Final Decision Model', 'Intervention 2'], 'description': 'See arm description', 'armGroupLabels': ['FDM']}]}, 'contactsLocationsModule': {'centralContacts': [{'name': 'Julie Renata Bjerremand', 'role': 'CONTACT', 'email': 'julierenata@outlook.com', 'phone': '+45 53593700'}], 'overallOfficials': [{'name': 'Martin Tolsgaard, Professor', 'role': 'STUDY_CHAIR', 'affiliation': 'Copenhagen Academy for Medical Education and Simulation'}]}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Copenhagen Academy for Medical Education and Simulation', 'class': 'OTHER'}, 'collaborators': [{'name': 'Technical University of Denmark', 'class': 'OTHER'}], 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Principal Investigator', 'investigatorFullName': 'Julie Renata Bjerremand', 'investigatorAffiliation': 'Copenhagen Academy for Medical Education and Simulation'}}}}