New AI Can Detect COVID-19 Using A Smartphone And Voice Sample
Coronavirus or COVID-19 has been very hard to diagnose across the globe with a varying range of symptoms and other variables. One company though, says a voice sample is enough for an accurate diagnosis.
Vocalis, an Isreal-based company has developed an AI app which analyzes voice samples to determine whether a person is infected by the virus or not.
This eliminates the need to visit a hospital or testing center, and furthermore, makes it much easier to screen asymptomatic people as well who wont be detected by a a temperature gun.
Vocalis says that it tested the tech on 2,000 participants, with results that were up to 81.2% accurate.
The firm’s algorithm extracts 512 features from a voice sample and makes an image — a spectrogram — with which it can diagnose possible diseases.
When the company aims to help detect a specific disease, it first holds clinical trials to recognize what kind of voice recordings it would need to collect to identify it, and what signatures in the audio it will need to pinpoint.
For instance, to detect COVID-19 the AI needs to identify characteristics of symptoms such as fever, headache, and shortness of breath.
These tests were conducted in India, where participants spoke in multiple languages, “including English, Hindi, Marathi, and Gujarati. It installed its VocalisCheck tools on smartphones to gauge the efficiency of algorithms.”
Vocalis has made sure that the AI is language agnostic. It asks patients to count from 50 to 70 to train the algorithm. Dr. Shady Hasan, the co-founder of Vocalis, said that this is to preserve a patient’s privacy and not to give away anything about their identity.
The interesting bit here is the fact that a lot of these participants were asymptomatic. TNW tells us that the tool is currently deployed in the US, South Africa, Romania, Chile, Indonesia, and Luxembourg.