January 17, 2013
Innovative Smartphone Apps Are Not Accurate When It Comes To Melanoma Diagnosis
Lawrence LeBlond for redOrbit.com - Your Universe Online
Got Melanoma? There´s an app for that. But I wouldn´t rely too heavily on what it might be telling you.
These apps, which are marketed as educational only tools, are not covered as medical devices under Food and Drug Administration (FDA) regulations. But it seems that isn´t stopping many people from relying on the relatively inexpensive apps rather than going to see a dermatologist for a possibly life-threatening condition, said the researchers.
Joel A. Wolf, BA, and his colleagues at the University of Pittsburgh Medical Center (UPMC), tested the sensitivity, specificity and positive and negative predictive values of four smartphone cancer apps to measure their performance in evaluating photographs of skin lesions that may or may not be malignant.
The authors used 188 images of lesions in their analysis, each of which was evaluated by the four apps. The lesions were either recorded as positive, negative or un-evaluable. Of the lesions included, 60 were malignant and the remaining 128 were benign.
Sensitivity of the four apps ranged from 6.8 percent to 98.1 percent; specificity ranged from 30.4 percent to 93.7 percent; positive predictions ranged from 33.3 percent to 42.1 percent; and negative predictions ranged from 65.4 percent to 97 percent. The highest sensitivity for melanoma diagnosis was observed for one app that sends the image directly to a board-certified dermatologist for analysis. The lowest sensitivity for melanoma diagnosis were applications that use automated algorithms to analyze the images.
"Physicians must be aware of these applications because the use of medical applications seems to be increasing over time“¦ the dermatologist should be aware of those relevant to our field to aid us in protecting and educating our patients," the authors wrote.
"There's no substitute, at this point, for a complete skin exam performed by an expert dermatologist for picking up melanoma as well as other skin cancers," said Dr. Karen Edison, a dermatologist from University of Missouri in Columbia who wasn't involved in the new study.
"Just sending a picture to someone you don't know anywhere in the world can be reassuring if it's very clear that (the lesion) is benign, so that's a good thing, but it's kind of fraught with other issues that we haven't grappled with adequately, I don't think,” she told Reuters Health.
Edison said even if an app makes a correct diagnosis of melanoma, that doesn´t necessarily help if the user doesn´t know where to go to get a biopsy or doesn´t have insurance to pay for it. "We're all for technology, but we need to keep it in perspective, and make it a tool."
The researchers said all but one of the apps classified more than half of the benign lesions as problematic, which is cause for concern in its own right. For users who get an incorrect positive diagnosis for melanoma, it could lead to un-necessitated worries.
Malignant melanoma is the most serious type of skin cancer, with more than 11,700 Britons diagnosed with the disease each year and 2,300 people dying.
The American Cancer Society (ACS) estimates that the risk of developing invasive melanoma in the US is 1 in 41 for men and 1 in 61 for women, averaging out to a an overall 1 in 50 chance of developing the deadly disease in your lifetime. The incidence of people under 30 developing melanoma is increasing faster than any other demographic groups, soaring 50 percent in young women since 1980.
With an increase in the incidence rate seen in the younger generation, it is especially worrisome since this is possibly the most likely age group using, and relying on, their smartphone to diagnose potentially dangerous melanomas. If the app is incorrect in a negative diagnosis, it could lead to further melanoma threats going unchecked.
Laura Ferris, assistant professor of the Dept. of Dermatology at University of Pittsburgh School of Medicine, said that relying on apps instead of consulting a physician could be a costly mistake.
“Smartphone usage is rapidly increasing, and the applications available to consumers have moved beyond communication and entertainment to everything under the sun, including health care,” said Ferris, lead author of the report.
“These tools may help patients be more mindful about their health care and improve communication between themselves and their physicians, but it´s important that users don´t allow their ℠apps´ to take the place of medical advice and physician diagnosis,” she added.
She said that innovative tools that “decrease the mortality rate by improving self- and early-detection of melanomas would be a welcome addition to dermatology. But we have to make sure patients aren´t being harmed by tools that deliver inaccurate results.”
London consultant dermatologist David Fenton told Daily Mail's Jenny Hope that, for people who are “sufficiently concerned to check a suspicious lesion with an app,” should be foregoing that diagnosis and seeking medical advice from a dermatologist first hand.
“They need to see their GP who may also decide to refer them to a dermatologist,” added Fenton.
The researchers in the study said they would not release the names of the apps they used in their study because their purpose was to determine the accuracy of the type of tool, and not the tool itself.
Ferris said for those who are concerned about melanoma, there are apps out there that can actually help patients.
"There are apps that will do things like teach you about melanomas," she said. "There are ones that will remind you to do your own skin check - that's great."
The researchers said tele-dermatology–consulting with a dermatologist through photo or video–can be a useful tool. Edison said she once used it to diagnose a farmer living hours away with melanoma during harvest season.
But they acknowledge that for now–and probably for the foreseeable future–the best and safest way to get your skin lesions checked is with a personal visit to your dermatologist.
The study was funded by the National Institutes of Health (NIH) and the University of Pittsburgh Clinical and Translational Science Institute.