Based on a new study published in the BMJ, the detection of skin cancer through smartphone apps is not reliable.
The apps access suspicious moles to study signs of cancer. Based on the report however researchers warn that the current regulatory process for such apps “does not provide adequate protection to the public.”
Survival from cases of melanoma skin cancer is high if they are detected at an early stage, thus ensuring early treatment. Artificially intelligent (AI) smartphone apps help with earlier detection and treatment of suspicious moles. These could however be harmful, particularly if false reassurance leads to delays in people seeking medical advice.
Two medical apps SkinVision and SkinScan are available in Europe and regarded as class 1 medical devices, Experts believe these have low to moderate risk to the user. However the latest study suggests high chance of skin cancers are being overlooked by such apps.
A research team led by Professor Jon Deeks at the University of Birmingham and Professor Hywel Williams at the University of Nottingham therefore evaluated the validity and findings of such studies by using algorithm based smartphone ‘skin’ apps.
Six different apps were studied. The findings revealed that the suspicious moles were found by clinicians and not by app users.
Furthermore, SkinScan revealed that 15 moles were with five melanomas, out of which the app did not identify any of melanomas. SkinVision revealed 108 moles, out of which 35 were cancerous or precancerous moles. It had 88% sensitivity and 79% specificity. This would ultimately also mean that 12 % of patients with cancerous or precancerous moles were missed, whereas 12% with non-problematic moles were wrongly identified as potentially cancerous.
“Our review found poor and variable performance of algorithm based smartphone apps, which indicates that these apps have not yet shown sufficient promise to recommend their use,” commented the authors on the research findings.
In addition the authors also warn that the current regulatory processes “are inadequate for protecting the public against the risks created by using smartphone diagnostic or risk stratification apps.”
And they say healthcare professionals “need to be aware of the limitations of algorithm based apps to reliably identify melanomas, and should inform potential smartphone app users about these limitations.”