Researchers built a mobile app that can detect COVID-19 using your voice

Researchers claimed that the mobile app is more accurate than several antigen tests and is cheap, quick and easy to use.

People have now learnt to co-exist with COVID-19. While we are almost living a regular life now, cases of coronavirus are still being recorded and how. With the advancement of technology, people no longer need to stand in queues to get a COVID tests done. There are several home test kits available as well. Now, if we say that a smartphone app can do a COVID test? Surprising, right? That’s what a study claims. That a phone app can accurately detect COVID-19 infection.

Researchers at the Institute of Data Science, Maastricht University, The Netherlands, have developed a smartphone app that can accurately detect COVID-19 infection in people's voices with the help of AI (artificial intelligence). That’s right, there's no need for nasal specimen.

Researchers claimed that the app is more accurate than several antigen tests and is cheap, quick and easy to use. Now, that means it can be used in low-income countries. The researchers also said that this software can be used by countries where the PCR tests are comparatively expensive or it’s difficult for the government to distribute it.

Wafaa Aljbawi, a researcher at the Institute of Data Science, Maastricht University, The Netherlands said, “The promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high precision in determining which patients have Covid-19 infection.” "Moreover, they enable remote, virtual testing and have a turnaround time of less than a minute. They could be used, for example, at the entry points for large gatherings, enabling rapid screening of the population," Aljbawi added during her presentation at the European Respiratory Society International Congress in Barcelona, Spain.

At the time of working on the project, Aljbawi and her superiors first investigated if it was possible to use AI to analyze voices in order to recognise COVID-19 infection. The team is said to have used information from the crowdsourced COVID-19 Sounds App from the University of Cambridge, which includes 893 audio samples from 4,352 healthy and unhealthy subjects. Of these 308 tested positive for COVID-19. The researcher then followed a method for analyzing voice known as Mel-spectrogram analysis, which identifies several voice characteristics like loudness, power, and fluctuation across time.

"In order to distinguish the voice of Covid-19 patients from those who did not have the disease, we built different artificial intelligence models and evaluated which one worked best at classifying the Covid-19 cases," Aljbawi explained. The research team discovered that the Long-Short Term Memory (LSTM) performed better than the others. The model is based on Neural networks, which replicate the way the human brain functions and recognizes the underlying patterns in data.

The team revealed that the overall accuracy of the app was recorded at 89 per cent. The app was around 89 per cent accurate in identifying positive COVID-19 cases and 83 percent accurate in identifying the Covid-19 negative cases. "These results show a significant improvement in the accuracy of diagnosing COVID-19 compared to state-of-the-art tests such as the lateral flow test," said Aljbawi.