This was not a blinded clinical trial. The subjects all knew whether they have COVID-19 or not and knowing how strong psychological effects can be, what's detectable in their cough might be their knowledge they're sick. The researchers even acknowledge in the paper that "sentiment" is a big part of how a forced cough sounds.
What's worrying is also how little of the data was from a diagnostic test (over half of "positive" samples were "self-diagnosed" COVID-19, whatever that means).
I don't think FDA or any other regulatory body would accept such an app as a screening tool without a proper trial being done.
If it works, that would be the most practical and coolest application of ML I've seen - but it still feels like something from the "too good to be true" category at the moment.
It’s just junk science and the title is false. They used an ML model to detect if a person knows they have a diagnosis through a fake cough into a phone app. Even then their results could quite possibly just be overfitting, even with the verification data set separated.
This was not a blinded clinical trial. The subjects all knew whether they have COVID-19 or not and knowing how strong psychological effects can be, what's detectable in their cough might be their knowledge they're sick. The researchers even acknowledge in the paper that "sentiment" is a big part of how a forced cough sounds.
What's worrying is also how little of the data was from a diagnostic test (over half of "positive" samples were "self-diagnosed" COVID-19, whatever that means).
I don't think FDA or any other regulatory body would accept such an app as a screening tool without a proper trial being done.
If it works, that would be the most practical and coolest application of ML I've seen - but it still feels like something from the "too good to be true" category at the moment.