A Smart Phone Dermatology App Review From The Medical Futurist

This is a copy of the news letter I recently received in my email from The Medical Futurist:


Read my article on The Medical Futurist!

And below are excerpts from the newsletter.

Amsterdam-based SkinVision developed a smartphone app to easily evaluate risk factors for skin cancer and keep track of potentially problematic moles. So far, the app was downloaded in over 1.2 million instances globally, with the most downloads coming from the UK, Australia, the Netherlands, New Zealand, and Germany. The smart algorithm coupled with dermatologists’ expertise has found over 27,000 cases of skin cancer. The company works closely with Generali in Germany, Central Health Insurance in the Netherlands, providing their entire insured population with the service. These partnerships naturally led to the expansion into Dutch and German versions of the originally English-language app in late 2018.

The Medical Futurist asked Matthew Enevoldson, PR Manager at SkinVision about their app, the algorithm behind it and how they see the future of dermatology.

What’s the story behind the SkinVision app?

Enevoldson: “SkinVision originally came out of Ph.D. research into Fractal Geometry in 2011. In 2013, the use of this algorithm for the recognition of skin cancer received its first clinical backing in several scientific papers. While dermatologists have been involved in the creation of the app since its start, it was in 2015 when they were brought onboard to manually review photos to be able to further test and improve the algorithm. Since 2015, the app and the company have continued to grow, to a point today where we have a staff of more than 35, including 9 dermatologists for quality assurance.”

How does the examination process work – from taking a photo until a potential diagnosis?

Enevoldson: “So for a user, it starts with downloading the app and taking a photo with the automatic camera, that ensures that all images come out framed the same. The proprietary mathematical algorithm then calculates the fractal dimension of skin lesions and surrounding skin tissues and builds a structural map that reveals the different growth patterns of the tissues involved. The algorithm checks for irregularities in color, texture, and shape of the lesion. It indicates which skin spots should be tracked over time and gives it a low, medium or high-risk indication within 30 seconds.

Our dermatologists perform continuous quality control of the assessments, by evaluating the output of the risk assessment with their professional experience. All high-risk photos receive additional personal advice from our doctors on next steps to take within two working days stating whether they should rest assured, continue monitoring the lesion or seek immediate medical attention.”

Do you have any statistics about the precision of the algorithm?

Enevoldson: “Our machine learning algorithm has been tested in several clinical scientific studies. The most recent data shows that our service has a sensitivity of 97% and specificity of 78% – this paper is currently undergoing peer review. Although it is safe to say that the results are well above that of a GP (sensitivity 60%), a dermatologist (sensitivity 75%) and even a specialist dermatologist (sensitivity 92%).”
This entry was posted in Dermatology, Family Medicine, Health Services Marketing, Internal Medicine, Medical Apps, Pediatrics, Telemedicine. Bookmark the permalink.