The "smart" app is even more accurate, according to its creators, than rapid tests
A new Dutch mobile app can accurately detect coronavirus infection in a person's voice thanks to built-in artificial intelligence. The "smart" app is even more accurate, according to its creators, than rapid antigen tests, and is also cheap, fast and easy to use, meaning it could be particularly useful in regions and countries where there is difficulty in accessing low-cost molecular tests.
Researchers from the Institute of Data Science at the University of Maastricht, led by Wafaa Alibawi and Professor of Pulmonology Sammy Simmons, made the announcement at the European Lung Society's international conference in Barcelona. They reported that the application has an accuracy of 89% (sensitivity) in correctly diagnosing a positive case of Covid-19 (compared to about 56% of a rapid test) and 83% in correctly diagnosing a negative case (specificity), and is significantly better than rapid tests in asymptomatic people.
"With our smart application we would only miss 11 out of 100 Covid-19 cases, which would then spread the infection, whereas the rapid lateral flow test would miss 44 out of 100," said Alibawi.
"Our very encouraging results show that simple voice recordings and their analysis with artificial intelligence algorithms can achieve high accuracy in detecting patients with Covid-19 infection. Such tests can be performed at no cost and are simple to interpret. Moreover, they allow remote testing and give a result in less than a minute. They could, for example, be used at the entry points of large gatherings, enabling rapid mass population screening," he added.
Covid-19 usually affects the upper respiratory tract and vocal cords, leading to changes in a person's voice. The new app is installed on the user's mobile phone and initially asks for basic information (demographic, medical history, smoking, etc.). It then asks the user to cough three times, breathe deeply through the mouth three to five times and read aloud near the screen a short sentence three times. A voice analysis technique (Mel-spectrogram) then identifies the different characteristics of each voice, while an artificial intelligence model (Long-Short Term Memory -LSTM) based on neural networks distinguishes a person's unique voice from its alteration due to Covid-19.
Source: protothema.gr
Contents of this article including associated images are belongs to Cyprus Times
Views & opinions expressed are those of the author and/or Cyprus Times
Source[/URL]