Smartphone applications designed to help people work out if they have a melanoma are potentially harmful, getting it wrong in up to 30% of cases, according to a new study from the University of Pittsburgh Medical Centre.
In a report published Online First by JAMA Dermatology, Joel A. Wolf and colleagues measured the performance of four smartphone apps that evaluate photographs of skin lesions and provide the user with feedback about the likelihood of malignancy.
Sensitivity of the four applications tested ranged from 6.8% to 98.1%, with the highest sensitivity for melanoma diagnosis observed for an application that sends the image directly to a board-certified dermatologist for analysis, while the lowest sensitivity for melanoma diagnosis were applications that use automated algorithms to analyse images.
“Despite disclaimers that these applications are intended for educational purposes, they have the potential to harm users who may believe mistakenly that the evaluation given by such an application is a substitute for medical advice,” the study authors write.
Australia’s Cancer Council has been approached by a number of app developers to endorse these kinds of technologies over the past two years or so, said Terry Slevin, director of education and research at The Cancer Council WA.
“We’ve been very cautious to lend our name to them, perhaps conservatively, on the basis that their impact remained uncertain,” Mr Slevin said.
“There are some obvious possible advantages, particularly for people in rural and remote settings where seeing a doctor is very difficult.”
However Mr Slevin said the risk was that an incorrect diagnosis led people to have a false sense of security, believing that no further action was needed.
He added that he was confident more research and testing on such applications would be conducted, given the potential benefits.
Mr Slevin said a recent MJA study predicted there would be over 900,000 non melanoma skin cancer lesions diagnosed and treated in Australia per year by 2015.
“The cost of skin cancer is an enormous burden on our health care system.
"Until however the technology is well proven by solid trial data, we are keen that people take the more reliable path by reporting suspicious lesions to their GP.”