The artificial intelligence laboratory of SberBank has developed an algorithm that within 60 seconds can determine the likelihood of COVID-19 coronavirus infection.
The presence of the virus is determined based on the results of a short symptom survey and three sound patterns – voice, breathing, and coughing.
As the developers explain, the audio files are converted into a spectrogram and then analyzed using a deep convolutional neural network. To train her, only open data was used – these are more than a thousand samples of breathing and coughing sounds collected from diagnosed patients in Russian clinics.
In the near future, it is planned to create a special application that will be available for Android and iPhone smartphones in the App Store and Google Play.
First Deputy Chairman of the Board of Sberbank Alexander Vedyakhin noted:
“At the beginning of November last year, we announced our readiness to create such an algorithm and since then have not wasted time in vain. Of course, our model does not yet achieve the accuracy of biological PCR, which is not surprising, but it already has comparable characteristics. At the same time, it makes it possible to make adjustable sensitivity, much easier to use, more convenient, and, which is important, cheaper. This is not a medical diagnostic tool, but rather a personal daily checker – taking the test and getting the result takes only 60 seconds! “
(Via)
