A study presented at the British Association of Dermatologists’ Annual Meeting in Edinburgh outlined three major failings of smartphone apps used to diagnose skin cancer. Flaws in the technology used to analyze photos, lack of input during the app development phase from specialists, and lack of extensive published trials proving safety and efficacy, are the major drawbacks that researchers observed.
Notably, without specialist input, apps may not recognize suspicious lesions and more unusual cancers. Even efficient programs may not be able to detect red-flag symptoms if they have not been developed with specialist input from a dermatologist.
Another deficiency that increases false negatives and treatment delays is that apps have difficulty recognizing ulcerated, scaly, crusted areas or amelanotic melanomas (melanomas that do not produce pigment).
Furthermore, apps that are designed to advise patients whether to seek professional advice, based on a risk calculation, may advise incorrectly because they cannot identify finer details that would be pinpointed with a dermatoscope or an in-person consultation with a dermatologist.
“Future technology will play a huge part in skin cancer diagnosis. However, until adequate validation and regulation of apps is achieved, members of the public should be cautious when using such apps as they come with risk,” said study author Maria Charalambides, PhD, Reader in Mechanics of Materials at Imperial College London and researcher at the University of Birmingham’s College of Medical and Dental Sciences in Birmingham, U.K., in a press release. “Any software that claims to provide a diagnostic element must be subject to rigorous testing and ongoing monitoring.”
Researchers reviewed medical literature on various types of skin cancer apps to analyze their effectiveness. Copyright-free photo from Pixabay.com.
Apps also cannot register changing symptoms or lesions, such as a new mole that has grown. In clinic a patient in this case would be advised to have the mole removed, however, an app may not be able to provide such personalised recommendations.
“Apps specifically based on patient education of skin cancer can offer public health benefits in terms of how to stay safe in the sun, or the warning signs to look out for. But as per the British Association of Dermatologists recommendations, most apps cannot currently substitute dermatologist review when it comes to actual diagnosis,” said Dr. Charalambides.
Be that as it may, researchers found that a number of the dermatological apps currently available for patients have a comparatively high success rate for the diagnosis of skin cancer. Teledermatology (forwarding images to a dermatologist for diagnosis, rather than making the diagnosis in-app) correctly identified 88% of people with skin cancer and 97% of those with benign lesions. Apps that use fractal theory analysis algorithms were the next most successful category—these correctly identified 73% of patients with skin cancer and 83% of people with benign lesions.
“These new technologies for the diagnosis of skin cancer are exciting, but the varying quality available makes it a difficult landscape for people to navigate. These apps are not a replacement for an expert dermatologist, but they can be a useful tool in the early detection of skin cancer,” said Matthew Gass, communications officer at the British Association of Dermatologists based in London, U.K.