There are a lot of far-fetched claims made in the article that don't pass the smell test (heh).

For example, in the article:

> there is evidence that dogs can quickly and accurately detect COVID-19 infection

In the linked source:

> but researchers say large-scale studies are needed before the approach is scaled up.

I imagine it is similar for every other diagnosis they tout. Small scale tests under ideal conditions very rarely survive real world application.