The researchers have trained an artificial intelligence model to detect COVID-19 infections through cellphone-recorded coughs, even if they are asymptomatic.
Obviously, asymptomatic means a person has no perceptible symptoms at all and so, it is through forced coughs that the AI can discern if a person may have the virus.
This is an important development as it clears the fog on whether if a person is ill without he or she knowing.
If cellphone-recorded force coughs determine a person have the virus, then that person can proceed to under the formal test. This is will greatly reduce the change of asymptomatic people from spreading the virus.
Here’s how it works:
“They first trained a general machine-learning algorithm, or neural network, known as ResNet50, to discriminate sounds associated with different degrees of vocal cord strength. Studies have shown that the quality of the sound “mmmm” can be an indication of how weak or strong a person’s vocal cords are. Subirana trained the neural network on an audiobook dataset with more than 1,000 hours of speech, to pick out the word “them” from other words like “the” and “then.”
The team trained a second neural network to distinguish emotional states evident in speech, because Alzheimer’s patients — and people with neurological decline more generally — have been shown to display certain sentiments such as frustration, or having a flat affect, more frequently than they express happiness or calm. The researchers developed a sentiment speech classifier model by training it on a large dataset of actors intonating emotional states, such as neutral, calm, happy, and sad.
The researchers then trained a third neural network on a database of coughs in order to discern changes in lung and respiratory performance.
Finally, the team combined all three models, and overlaid an algorithm to detect muscular degradation. The algorithm does so by essentially simulating an audio mask, or layer of noise, and distinguishing strong coughs — those that can be heard over the noise — over weaker ones.”MIT
The research team is working to incorporate the model for identifying COVID-19 patients into a user-friendly app.
If the model gets the nod from FDA, it will no doubt change the game in our fight against this deadly pandemic.
You can learn more about this exciting new development HERE.
Featured image: MIT.