MIT scientists have developed AI that can detect Covid-19 by listening to a person force out a cough, even if that person is otherwise asymptomatic. To make this possible, the scientists developed neural networks that can distinguish subtle changes indicative of the novel coronavirus’ effects.
As reported by Engadget, one neural network detects sounds associated with vocal strength. Another listens for emotional states that reflect a neurological decline, such as increased frustration or a “flat affect.” A third network, meanwhile, gauges changes in respiratory performance. Throw in an algorithm that checks for muscular degradation (that is, weaker coughs) and it provides a more complete picture of someone’s health.
In early tests, the AI has proven itself highly accurate, recognizing some 98.5 percent of coughs from people with confirmed COVID-19 cases. It also identified 100 percent of people who were ostensibly asymptomatic.
To be clear, the technology isn’t meant to diagnose symptomatic people. Rather, the idea is that the AI will be applied to a “user-friendly” app that could be used as a prescreening tool for the virus. You might only have to cough into your phone each day to determine if it’s safe for you to head outside, or if you should go get yourself tested.
