DERM-011 Precision study
Research type
Research Study
Full title
A PRECISION STUDY TO DEMONSTRATE THE REPEATABILITY AND REPRODUCIBILITY OF DERM OUTPUTS
IRAS ID
343731
Contact name
Helen Marsden
Contact email
Sponsor organisation
Skin Analytics
Duration of Study in the UK
0 years, 1 months, 28 days
Research summary
Skin Analytics has created a medical device called DERM that uses artificial intelligence to help doctors check if a skin lesion might be cancerous. It works by analysing close-up pictures of skin spots taken with a smartphone. The results it gives back are either “Suspicious for malignancy” (Possibly cancerous) or “No evidence of malignancy” (No sign of cancer).
This study aims to see how accurate ("precision") DERM is. We want to know if different people taking pictures of the same lesion ("repeatability") or using different devices (specifically, an iPhone 11 with a special lens) to take the pictures ("reproducibility") affects the diagnosis/results. We will involve adults with at least one skin lesion that doctors are checking for cancer, as part of their standard care, to take part.
Suitable lesions will be photographed three times each, by three different people using three sets of the image capture hardware; each image being checked for good image quality as it is captured. An additional 3 "poor quality" images will be captured, making a total of 30 images per lesion. Images will then be transferred electronically to DERM in order to be analysed. The results/findings won't be shared with the patients or doctors involved in the study. The patients will continue to be treated as usual and the study will not change their treatment/management plan.
REC name
South Central - Berkshire B Research Ethics Committee
REC reference
24/SC/0369
Date of REC Opinion
19 Nov 2024
REC opinion
Further Information Favourable Opinion