Skin LesionsNCT07468357
Human-AI Uncertainty Callibration for Improved Skin Lesion Segmentation
A study testing Base Model and FDM in people with Skin Lesions, run by Copenhagen Academy for Medical Education and Simulation.
Trial summary
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… Read more about this study
- Who is it for?
- Any ageHealthy volunteers can take part
- Conditions the study is for
- Skin Lesions
- What is being tested?
- Base Model and FDM
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 50 participants
- Where
- No sites listed yet
- Study dates
- 1 Mar 2026to Nov 2026
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages Any age
- All sexes
- Healthy volunteers accepted
- Child, Adult, Older adult
Who may be able to join
- Board certified dermatologists with clinical experience in dermoscopic diagnosis.
Who cannot join
- Doctors who have not yet finished their specialization and dermatologists.
- Dermatologists without clinical experience in dermoscopic diagnosis.
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
Official title: 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.
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.
The 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.
Read more
The investigators expect to see a higher increase in diagnostic certainty for the FDM intervention compared to the diagnostic certainty in the Base Model intervention.
The investigators expect to see a higher amount of diagnosis changes from incorrect to correct in the FDM group compared to the Base Model group.
The investigators do not expect any learning effect during the study.
Participants 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.
Read the detailed description
A detailed description of the FDM is presented in the references.
- Conditions
- Skin Lesions
- Being tested
- Base Model, FDM
- Keywords
- Dermatology, AI, Artificial Intelligence, Uncertainty Calibration, Dermoscopy, Bayesian Deep Learning, Human-AI Decision Model
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Base ModelOther
Also called Intervention 1
See arm description.
FDMOther
Also called Final Decision Model, Intervention 2
See arm description
| Study group | Role | What they receive |
|---|---|---|
| Base Model | Active comparator | 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.
After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty. Receives: Other: Base Model |
| FDM | Experimental | 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).
After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty. Receives: Other: FDM |
What is being measured
The primary outcome is the main question the study is designed to answer.
Accuracy
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.
Measured: Immediately after the intervention.
Secondary outcomes (2)
Uncertainty
Changes in self-assesed uncertainty ranging from 0 (very uncertain) to 10 (very certain) from pre- to post-intervention.
Measured: Immediately after the intervention.
Cut-off uncertainty
The self-assessed uncertainty of cases where the participant has clicked a "would you like to discuss this case with a collegue"-button.
Measured: Immediately after the intervention.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted12 Mar 2026
- Study start1 Mar 2026 (estimated)
- Primary completionJul 2026 (estimated)
- Study completionNov 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for Skin LesionsStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- 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.
- Masking
- None (open label)
- Enrolment
- 50 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Copenhagen Academy for Medical Education and Simulation
- Sponsor type
- University, hospital or other
- Collaborators
- Technical University of Denmark
- Responsible party
- Principal investigator, Julie Renata Bjerremand, Copenhagen Academy for Medical Education and Simulation
- Investigators
- Martin Tolsgaard, Professor, Study chair, Copenhagen Academy for Medical Education and Simulation
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07468357
- Sponsor's protocol ID
- F-25076782
- Status last verified
- Mar 2026
- First submitted
- 29 Jan 2026
- Last updated
- 12 Mar 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
Publications
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
Study at a glance
From the registry record, last updated by the sponsor on 12 Mar 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- 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.
- ClinicalTrials.gov ID
- NCT07468357
- Acronym / sponsor ID
- F-25076782
- Conditions
- Skin Lesions
- Keywords
- Dermatology, AI, Artificial Intelligence, Uncertainty Calibration, Dermoscopy, Bayesian Deep Learning, Human-AI Decision Model
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 50 participants (estimated)
- Lead sponsor
- Copenhagen Academy for Medical Education and SimulationUniversity, hospital or other
- Collaborators
- Technical University of Denmark
- Study start
- 1 Mar 2026 (estimated)
- Primary completion
- Jul 2026 (estimated)
- Study completion
- Nov 2026 (estimated)
- First posted
- 12 Mar 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
The 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.
The investigators expect to see a higher increase in diagnostic certainty for the FDM intervention compared to the diagnostic certainty in the Base Model intervention.
The investigators expect to see a higher amount of diagnosis changes from incorrect to correct in the FDM group compared to the Base Model group.
The investigators do not expect any learning effect during the study.
Participants 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.
Detailed description
A detailed description of the FDM is presented in the references.
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- 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.
| Arm | Type | Receives |
|---|---|---|
| Base Model | Active comparator | Other: Base ModelThe 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. After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty. |
| FDM | Experimental | Other: FDMThe 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). After the AI input, the study participant is given the chance to change their diagnosis and indicate any potential shift in uncertainty. |
Who may qualify
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Child, Adult, Older adult
Key inclusion criteria (1 listed)
- Board certified dermatologists with clinical experience in dermoscopic diagnosis.
Key exclusion criteria (2 listed)
- Doctors who have not yet finished their specialization and dermatologists.
- Dermatologists without clinical experience in dermoscopic diagnosis.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Base ModelAlso: Intervention 1See arm description. | Other | Base Model |
| FDMAlso: Final Decision Model, Intervention 2See arm description | Other | FDM |
Primary outcome
Accuracy
Time frame: Immediately after the intervention.
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.
2 secondary outcomes
Uncertainty
Time frame: Immediately after the intervention.
Cut-off uncertainty
Time frame: Immediately after the intervention.
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 12 Mar 2026.
- BackgroundKampen, 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
Related trials for Skin Lesions
Enrolling by invitation
TruScore Standalone Clinical Study
Melanoma and Other Malignant Neoplasms of Skin, Basal Cell Carcinoma of Skin
RecruitingPhase 3
A Study of MACI in Patients Aged 17 to 65 Years With Symptomatic Chondral or Osteochondral Defects of the Ankle
Chondral Defect, Articular Cartilage Defect
Not yet recruitingPhase 2/3
Efficacy and Safety of Immunoglobulin Plus Firsekibart in Patients With Kawasaki Disease
Kawasaki Disease
Active, not recruitingPhase 2
Ultra Low Dose Radiation Therapy in Treating Patients With Mycosis Fungoides
Localized Skin Lesion, Mycosis Fungoides
Active, not recruiting
A Novel Fluorescent Ductal Needle for Localization and Sampling of Micro Lesions in Breast Ducts
Mammary Tumor, Nipple Discharge
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Martin Tolsgaard, Professor study chair
Copenhagen Academy for Medical Education and Simulation
Questions about this trial
What is this clinical trial studying?
A study testing Base Model and FDM in people with Skin Lesions, run by Copenhagen Academy for Medical Education and Simulation.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 1 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 12 Mar 2026. Status can change between updates, so confirm with the study contact before making plans.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Julie Renata Bjerremand (+45 53593700, julierenata@outlook.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Accuracy (time frame: Immediately after the intervention.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07468357, which also lists 1 linked publication.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 12 Mar 2026.