There's a reason they published this in an engineering journal, not medical one. It's very cool, but in terms of practical use, is in the realm of "maybe it's worth doing a real medical study to see if this works" - a valuable contribution, no doubt, but a not really a contribution to diagnostics in itself (yet).

That said, I like that they're thinking outside the box on this one. A free digital test with a low false negative rate would be a game changer.