'Close to 100% accuracy': Helsinki airport uses sniffer dogs to detect Covid | Hacker News Reader

'Close to 100% accuracy': Helsinki airport uses sniffer dogs to detect Covid

theguardian.com

12 pointsCiantic9 comments

> A dog is capable of detecting the presence of the coronavirus within 10 seconds and the entire process takes less than a minute to complete

Considering Covid tests are only about 75% accurate, this is pretty amazing. Hope those dogs can't get Covid though

To me this article is not interesting because of dogs, or accuracy of this experiment. It's about possibility what artificial sniffing machine could one day do.

It would be interesting to hear from someone working on state of the art air particle detectors, and why haven't they still reached dogs abilities?

I don't think it's necessarily to do with machines necessarily being bad at this, but that dogs are incredible. A quote from the article:

> Dogs are also able to identify Covid-19 from a much smaller molecular sample than PCR tests, Helsinki airport said, needing only 10-100 molecules to detect the presence of the virus compared with the 18m needed by laboratory equipment.

Amazing.

%age accuracy is meaningless. They need to talk about sensitivity and selectivity. Without those the article is useless.

Can you elaborate?

Since active covid cases are still pretty rare day-to-day at a population level, "Close to 100% accuracy" is ambiguous, and could be very good or basically useless. For example, if 3% of the people moving through that airport actually have coronavirus, a detector that just reads negative for everything would have 97% accuracy - but a 100% false negative rate.

Like, the reported stats are misleading? I get your point. Though this research has been going on for a while - https://www.bbc.co.uk/news/uk-52686660 - Would be helpful if the report did provide more details on the source for that figure.

I wouldn't even say the reported stats are misleading, just that "accuracy" in a headline is too vague to ascertain performance when you're trying to detect (relatively) rare events.

A somewhat more detailed description of the efficacy of dogs, in testing for Coronavirus if you're interested: https://bmcinfectdis.biomedcentral.com/articles/10.1186/s128...

Some way off 'Near 100%', but also appears to be high enough to make this one of the better methods of testing currently known.

Which is amazing in itself. Incredible, actually, because the more common swab tests are said to have closer to 70% accuracy.

Reply on news.ycombinator.com