"Non Sento Odori" - can Google help spot pandemic trends?

[TheVat]

Every day, millions of people around the world type their health symptoms into Google. We can use these searches to help detect unknown Covid-19 outbreaks, particularly in parts of the world with poor testing infrastructure.

To see the potential information lying in plain sight in Google data, consider searches for “I can’t smell.” There is now strong evidence that anosmia, or loss of smell, is a symptom of Covid-19, with some estimates suggesting that 30-60 percent of people with the disease experience this symptom. In the United States, in the week ending this past Saturday, searches for “I can’t smell” were highest in New York, New Jersey, Louisiana, and Michigan — four of the states with the highest prevalence of Covid-19. In fact, searches related to loss of smell during this period almost perfectly matched state-level disease prevalence rates, as the accompanying chart shows....

https://www.nytimes.com/2020/04/05/opin ... rches.html


(New York Times articles on CV are free - it may ask you to register, but there's no charge or commitment and you can check a box for no emails)

[Serpent]

I gather from a couple of correspondents who are recovering that loss of smell (and taste) came fairly late in the onset and lingered several days past all other symptoms. They'd got their appetite back, but couldn't tell what they were eating.
By the time such a peculiar symptom is recognized as diagnostic of a specific illness, the illness is already known: the place of origin has been identified, the spread of it is being mapped. I'm guessing, for every patient well enough to Google "I cant smell" (which Google politely asked did you mean I can't spell?) two older ones are gasping in the ICU.
For early detection, you'd want to look for a pre-symptom - so far, patients seem to have none afaik - and one that's as nearly common to all those affected as possible without being too general. Fever, cough and SOB are not specific to any particular strain of influenza.
Still, if there was a sudden acute interest in any group of symptoms in a clearly demarcated region, WHO might have a program to flag it for investigation.

Here's something similar:

We experiment with two variations of an existing surveillance architecture: the first aggregates tweets related to different symptoms together, while the second considers tweets about each symptom separately and then aggregates the set of alerts generated by the architecture.

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7077840/