Feb. 10 (UPI) -- Smartphone apps promising quick and easy screening for certain types of skin cancer may not be as accurate as promised, an analysis of existing research published Monday by the BMJ has found.
The authors, from various institutions in England, reviewed nine studies evaluating six different apps designed to provide a risk assessment of a new or changing mole -- the most obvious sign of skin cancer. In general, the team reports that the few studies that checked the efficacy of these apps involved small numbers of people and were overall of poor quality.
The software missed as many as 12 percent of all skin cancer cases and falsely diagnosed non-cancerous moles as being cancerous, they said.
"Although I was broad minded on the potential benefit of apps for diagnosing skin cancer, I am now worried given the results of our study and the overall poor quality of studies used to test these apps," co-author Hywel Williams, professor of dermatology at the University of Nottingham, said in a press release. "My advice to anyone worried about a possible skin cancer is 'if in doubt, check it out with your general practitioner.'"
The World Health Organization estimates that as many as 3 million non-melanoma skin cancers and nearly 150,000 melanoma skin cancers occur globally each year. Survival is high if melanoma is spotted early, which makes prompt detection and treatment crucial -- and quick, easy tests appealing.
Smartphone apps designed to assess skin cancer risk typically use specialized algorithms to try to detect possible skin cancers.
While artificial intelligence-based, or AI, smartphone apps offer the potential for earlier detection and treatment of suspicious moles, they could be harmful, particularly if false reassurance leads to delays in people seeking medical advice, the authors of the BMJ paper said.
Currently, in Europe, two apps -- SkinVision and SkinScan -- are available and regulated as class 1 medical devices, considered to have a low to moderate risk to the user.
To date, no skin cancer apps have been approved for use by the U.S. Food and Drug Administration, due to stricter regulatory requirements, the authors said.
According to the research, SkinScan has been evaluated in a single study of 15 moles with five melanomas. Notably, the app did not identify any of the melanomas.
Meanwhile, SkinVision has been evaluated in two studies. One study included 108 moles, including 35 cancerous or precancerous moles, and achieved a sensitivity of 88 percent and a specificity of 79 percent. This translates to 12 percent of people with cancerous or precancerous moles being missed, while 21 percent of those non-problematic moles would be incorrectly diagnosed with cancer.
"This is a fast-moving field and it's really disappointing that there is not better quality evidence available to judge the efficacy of these apps," said Jac Dinnes, of the Institute of Applied Health Research at the University of Birmingham. "It is vital that healthcare professionals are aware of the current limitations both in the technologies and in their evaluations."
The research team also noted that the studies evaluated the apps using images taken by experts rather than those from app users. In addition, many studies did not identify whether lesions identified as "low risk" by the apps were in fact benign, further compromising the results, the researchers said.
They also warn that the current regulatory processes in Europe "are inadequate for protecting the public against the risks created by using smartphone diagnostic or risk stratification apps."
Healthcare professionals, the researchers wrote, "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."