Date: 9th September 2019
Leveraging smartphone applications (SA) to assess the risk of skin lesions.
Skin cancer is one of the most prevalent cancers worldwide (World Health Organisation), however, treatment is often effective thanks in a large part to early detection and diagnosis.
Now, with global access to smartphones increasing, scientists from The Netherlands, USA and Romania have been leveraging smartphone applications (SA) to assess the risk of skin lesions.
Machine learning algorithm
Using the smartphone’s built-in camera users take pictures of the skin, whilst a machine learning algorithm, downloaded as an app, is used to compute the risk factor.
In the article published in the Journal of the European Academy of Dermatology and Venereology, the authors have validated their SA using 285 histopathologically confirmed skin cancer cases. These tests showed this SA to be highly sensitive, outperforming doctor diagnosis. Trained on large datasets, the algorithm had a >90% sensitivity in common cancer detection, whilst it was also able to identify non-disease individuals with around 78% specificity.
Technological advancement for skin cancer
This latest technological advancement in digital health promises to play an important role in the early detection of skin cancer.
For many of us this type of accessibility potentially places our healthcare literally in the palm of our hands, and for those in more remote parts of the world, where healthcare access may be more limited this could prove to be an invaluable tool. Using existing smartphone cameras, the simple downloading of an app, could potentially allow you to detect and track skin changes over a period of time, in essence enabling you to support early detection without the need for medical training or medical imaging.
The Amsterdam-based skin cancer screening app SkinVision and its associated supporting health service will undergo further optimisation, with clinical validation being planned in the coming months.
For more information on SkinVision please visit our digital maps.
Udrea, A., G. D. Mitra, D. Costea, E. C. Noels, M. Wakkee, D. M. Siegel, T. M. de Carvalho and T. E. C. Nijsten “Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms.” Journal of the European Academy of Dermatology and Venereology.
https://doi.org/10.1111/jdv.15935
