In 2019, Kirill Sokol founded Skinive: a start-up capable of early detection of skin diseases using a smartphone application. By taking a picture of a suspicious skin area with your smartphone, artificial intelligence (AI) can be used to determine if your skin shows signs of skin disease. In other words, it is a kind of digital self-test. Over 1,000 dermatologists and 60,000 patients in Europe now use the app. Nevertheless, some experts are critical.
Sokol explains how the app works: “It basically works the same way as Google Images. You take a photo, put it in a database, and then it’s cross-referenced with other skin disease images. It’s a way to determine if you’re at risk of developing a skin disease like cancer Linda Summer of the KWF Dutch Cancer Society calls Skinive’s app a “fantastic development” as long as it doesn’t lead not to cases of overdiagnosis.” Therefore, if people see a patch that they do not trust, we always recommend that they contact their doctor.”
Artificial intelligence improves care for women with heart attacks – Innovation Origins
Researchers from the University of Zurich have developed an AI-based risk score that improves personalized care for patients suffering from heart attacks.
A self-test every week
Sokol points out that the “self-test” does not provide an official diagnosis, but it does give you a clear picture of a potential diagnosis. Skinive’s database has access to over 650,000 images from healthcare professionals and app users. The more photos users upload, the more reliable the comparisons and therefore the reviews become. The company recommends doing a self-test every week. According to dermatologist Soe Janssens from the Dutch Antoni van Leeuwenhoek (AVL) hospital, this is “totally exaggerated”, because “when a person has had melanoma, we check the whole skin twice a year at most. Asking someone who hasn’t had skin cancer to do their own skin inspection every week is pointless.
Too simple to upload a blurry photo
The dermatologist tested the app for this article. She is critical of it: “I noticed a lot of limitations. For example, it does not take into account a patient’s history, which is really important to make a good assessment of a skin patch. She also raises questions about the use of phone cameras: “If you upload a blurry photo, you don’t get any sort of notification that the photo is too blurry. It’s crazy, because you can’t get good advice that way, can you? Several studies, including one published in the Netherlands Journal of Medicine, show that similar apps have low positive predictive values. The study found that a large portion of app users receive false warnings about possible skin cancer and are promptly advised to seek medical attention.
According to Chief Medical Technology Scientist Arjen Amelink of the Vrije Universiteit Amsterdam, this is easy to clarify. “Most likely they want to be on the safe side as a company. Of course, you don’t want to say there’s nothing wrong if someone turns out to have cancer. I wonder how they keep the line between sending someone for help and saying everything is fine.
According to Sokol, when users use the app, they’re actually directed to the right specialist, which often doesn’t happen these days. “By doing our self-test, you immediately know which specialist to contact: a dermatologist, a beautician, an allergist, an oncologist or an infectious disease specialist. At your general practitioner, you are often referred to a dermatologist without knowing if this is the right specialist to turn to. And for an appointment with a dermatologist, you spend an average of two months on a waiting list. By being sent to the right specialist the first time, you save time and money.
New medical technologies are not always compatible with legal requirements – Innovation Origins
An aging society and new medical technologies are challenging health and legal systems. Laws need to be adapted, amended or rewritten.
Health claims need to be further substantiated
Scientist Amelink sees more and more initiatives like Skinive. However, he has his reservations about the method. “I wonder to what extent this artificial intelligence is sufficiently trained to give sound advice. Each phone camera works differently in terms of light and quality. This could be a factor in the diagnosis.
He compares Skinive to vision of the skin, a similar smartphone app that has been scientifically researched. “Most health apps still lack proper laws and regulations. That means a lot is doable now, but there’s still not a lot of scrutiny to know if it actually works.
According to Amelink, however, this should change in the future. “There will be more regulation on these types of initiatives, and then many companies will fold. If an app makes a certain health claim, it must be scientifically proven to continue to exist.
#Skinive #smartphone #app #helps #prevent #skin #cancer #experts #key #Innovation #Origins