DERM impact study
Research type
Research Study
Full title
Impact of an Artificial Intelligence platform (DERM) on the healthcare resource utilisation (HRU) needed to diagnose skin cancer when used as part of a UK-based teledermatology service
IRAS ID
267067
Contact name
Lucy Thomas
Contact email
Sponsor organisation
Skin Analytics
Clinicaltrials.gov Identifier
Duration of Study in the UK
0 years, 6 months, 30 days
Research summary
Research Summary
DERM, an Artificial Intelligence (AI)-based diagnosis support tool, has been shown to be able to accurately identify melanoma, non-melanoma skin cancers (NMSC) and other conditions from historical images of suspicious skin lesions (moles).This study aims to establish whether the use of DERM in the patient pathway could reduce the number of unnecessary referrals to dermatologist review and/or biopsy.
Suspicious skin lesions that are due to be photographed for a dermotologist to review, will have two additional photographs taken using a commonly available smartphone camera with and without a specific lens attachment. The images will be analysed by DERM, and the results compared to the clinician's diagnosis (all lesions) and histologically-confirmed diagnosis (any lesion that is biopsied).
Summary of Results
700 patients who attended a medical photography clinic, with at least one skin lesion that was referred for dermatology assessment, were recruited into the study. Standard of care photographs were assessed by dermatologists remotely ("teledermatology"), while photographs captured on a smartphone were assessed by a medical device powered by artificial intelligence (called DERM). DERM classifies lesions as one of a number of different skin diseases including skin cancer and benign conditions that look similar to skin cancer. The aim of the study was to see if DERM was able to correctly identify lesions that could safely be discharged better than teledermatologists.
Of 867 lesions included in the study, 817 had both a final diagnosis and a DERM classification. 73 of these lesions were diagnosed as skin cancer. DERM correctly classified significantly more benign lesions that did not need to be referred, compared to the teledermatologists. DERM identified a comparable proportion of lesions that needed further assessment compared to teledermatologists. This means DERM could potentially help to reduce the number of face-to-face dermatology appointments and unnecessary biopsies.
A patient survey demonstrated a good acceptability of technology being used as part of the decision-making process about their care.REC name
West Midlands - Edgbaston Research Ethics Committee
REC reference
19/WM/0354
Date of REC Opinion
23 Dec 2019
REC opinion
Further Information Favourable Opinion