Please login to the form below

Not currently logged in
Email:
Password:

Digital intelligence blog

Pharma insight on digital marketing, social media, mobile apps, online video, websites and interactive healthcare tools

Melanoma smartphone app claims 'highly variable'

Applications that assess skin cancer risk often misclassify lesions

Smartphone apps that assess the likelihood of a skin lesion proving malignant are “highly variably” and could cause patients harm, according to a new US study.

Researchers from the University of Pittsburgh Medical Center examined four apps that use photographs of skin lesions to make assessments and whether they suggest any type of diagnosis or estimate the risk of malignancy.

Testing their sensitivity, specificity, and positive and negative predictive values, the researchers found that three of the four apps incorrectly classified 30 per cent or more of melanomas as unconcerning.

Writing in JAMA Dermatology the authors suggest that reliance on these applications, which are not subject to regulatory oversight, and not seeking medical consultation can delay the diagnosis of melanoma and potentially harm users.

"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," they conclude.

The study included 188 images of lesions in the analysis, each of which was evaluated by the four smartphone applications, and the test result was recorded as positive, negative or unevaluable. Of these lesions, 60 were melanoma and the remaining 128 were benign.

Sensitivity of the four apps ranged from 6.8 per cent to 98.1 per cent; specificity ranged from 30.4 per cent to 93.7 per cent; positive predictive value ranged from 33.3 per cent to 42.1 per cent; and negative predictive value ranged from 65.4 per cent to 97 per cent.

The highest sensitivity for melanoma diagnosis was 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.

The study should reopen the debate as to whether mobile apps are medical devices and give fresh impetus to US regulators in particular.

Having gained powers to regulate some smartphone apps in July last year under the FDA Safety and Innovation Act, the regulator has yet to clarify how this process will work or which apps it will cover.

23rd January 2013

From: Regulatory, Healthcare

Share

Tags

Featured jobs

Subscribe to our email news alerts

PMHub

Add my company
M3 (EU)

M3 was founded in 2000 with the goal of changing the world of medicine through making full use of the...

Latest intelligence

OUTiCO win Best in UK Pharmaceutical Outsourcing award
The Corporate LiveWire Healthcare and Life Sciences Awards celebrate global companies and individuals who have excelled over the past 12 months....
artificial-intelligence-in-healthcare.jpg
Artificial Intelligence in Healthcare
Artificial intelligence is already out-diagnosing experts, but would you put a computer in charge of your healthcare? The good, the bad; we take a look....
World Pancreatic Cancer Day 2018: Combating misconceptions in pancreatic cancer
Patients diagnosed with pancreatic cancer face a dismal prognosis, with the disease having the lowest survival rate of all major cancers. In spite of this, pancreatic cancer research is chronically...

Infographics