New vistas in digital quackery

Apparently, computer-based diagnostic algorithms provided cheaply via a smartphone aren't reliable. Who would have guessed? There's a slew of new apps available that allow you to take a picture of your weird mole or mysterious skin lesion, and they'll then scan it and tell you whether you've got melanoma or not. You should be wary. When real doctors actually test their competence, the dermatology apps fail miserably.

Dermatologists are less than thrilled. In fact, they say, the apps are worthless. Writing in JAMA Dermatology, a team of physicians from the University of Pittsburgh put four melanoma apps to the test against 188 clinical images—pictures they’d taken of patients’ skin lesions and later determined, via biopsy, to be malignant or benign. How would a machine stack up against a board-certified dermatologist?

Not so well. Of the three auto-diagnosing apps, the best program missed malignant growths 30 percent of the time; a second performed only slightly better than flipping a coin.

One app, instead of using an algorithm, simply forwarded the photo to an accredited dermatologist, who responded with his considered opinion 24 hours later. At five dollars per lesion, this was the most expensive program, though the e-doctor misdiagnosed just one in 53 melanomas.

They've got testimonials from users praising the results, which makes me wonder…if your phone told you you didn't have cancer, how the hell would you know if it was right or not?

It's the oldest principle of quackery: tell the patient what they want to hear, and they'll reward you with agreement.

More like this

Less than a month ago, I got a bit perturbed by some vile rhetoric written by a left-wing blogger named Matt Stoller, who referred to John McCain as a "crazy, cancer-ridden dishonest madman." As you recall, I administered a bit of not-so-Respectful Insolence to him. It wasn't so much because I like…
About a month and a half ago, I discussed an e-mail that was being propagated far and wide that described the case of the mother of a 17 year old male who, or so the e-mail claimed, cured her son of stage IV melanoma using "natural means" and was supposedly thrown in maximum security prison by the…
Last week I went to the dermatologist. I have a few moles, and some of them were looking a little funny. The dermatologist did a full skin exam, and agreed that some of my moles looked funny, and she removed them. About a week later a pathology report confirmed that I have dysplastic nevi, and…
The NYT reports on the differing wait times between high-cost cosmetic procedures in dermatology, and low-cost potentially life-saving screenings for melanoma and other skin cancers. Patients seeking an appointment with a dermatologist to ask about a potentially cancerous mole have to wait…

Long time reader, first time commenter etc..

I really enjoy your blog and find it very insightful and fun (the series of posts regarding evolutionary psychology was fantastic), but as a biology student I do have to wonder:

These creationists obviously have nothing interesting to say, scientifically. They're insane, or, at the very least, dogmatic.

Why bother grappling with them over facts?

I understand that they're a major political influence in America and that defending evolutionary biology is an issue, but their "scientific" claims don't really appear to warrant serious answers - in fact, from where I'm standing, answering them just seems to ratify their claim that there's even a "controversy" that needs to be debated.

Wouldn't it be better to engage the Science Vs. Creationism debate on a theological or philosophical level, instead of letting their voice tarnish the scientific debate?

I mean, scientists work hard, gather evidence and build theories in order to gain the right to engage in scientific debates - why grace creationists with that right for free?


By Adam Etzion (not verified) on 04 Feb 2013 #permalink

Whoops, wrong post!
Please disregard the comment here.


By Adam Etzion (not verified) on 04 Feb 2013 #permalink


The last one (with the actual dermatologist doing the work) is kind of interesting. The concept of "tele-medicine" is up and coming (or at least so some people say), but I am worried about the limitations of it. You can do a lot by picture, but a) what ensures reproducible image quality and b) what about diagnostic criteria that are not captured in a 2D image, like elevation, texture and the like? I'm mostly thinking about it from the perspective of medical microbiology, of recognizing germs based on their colony morphology, but I'd assume similar things apply to other fields of (tele-)medicine.


A principled practicioner would be able to state upfront his limitations, and refer you to an in-person practicioner when neccesary. Principled will, I expect, be the rub. Image quality can be assured by requiring that the telemedicine patient visit a kiosk or similar; or by requiring a software check of available hardware, several of our local pharmacies have such kiosks available.