> Also, dogs can smell cancer in humans

...and the impending onset of dangerously low blood sugar, well before the person realizes that something is wrong. There are diabetes assist dogs available for this [1].

[1] https://www.mayoclinic.org/diseases-conditions/diabetes/expe...

Dogs have been shown to detect certain cancers at later stages (which greatly limits use as a screener.. not to mention how does the sensitivity/specificity compare to state of the art). This is not surprising since as cancers advance they cause gross biochemical changes.

The further issue diagnosing cancer/no cancer or epilepsy/no is an easy problem. But train a dog/machine on 1000 or more rare diseases. Now selectivity is an actual issue. And unless you manage to overcome that, how is all this scent stuff clinically useful?

So the original "sniffer dog" study (The Lancet 8640)[0] pretty much covers a dog sniffing out a melanoma BEFORE it got to a later stage, and saved a woman's life.

I also dont understand how training a machine would have selectivity issues. Machines dont "get trained" on one thing.

0: https://www.sciencedirect.com/science/article/pii/S014067368...

That is not a study. That is a case report written as a letter to the editor. That meets no scientific rigor at all and no generalizable conclusions can be drawn from it, it provides an anecdote for further research. It also doesn’t suggest that sniff tests would fare better compared to any other screening system for melanoma.