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

People have now learned to co-exist with COVID-19. While we are almost living a normal life now, cases of coronavirus are still being recorded and how. With advancements in technology, people no longer need to wait in line to take a COVID test. There are also several home test kits available. Now what if we say a smartphone app can do a COVID test? Surprising, right? That’s what a study says. That a phone app can accurately detect COVID-19 infection.

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

The 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 PCR tests are relatively expensive or where it is difficult for the government to distribute it.

Wafaa Aljbawi, a researcher at the Institute for Data Science at Maastricht University, the Netherlands, said: “The promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high accuracy. to determine which patients are infected with Covid-19”. “In addition, they enable remote virtual testing and have a turnaround time of less than a minute. They could be used, for example, at entry points to large gatherings, allowing rapid screening of the population” , added Aljbawi during his presentation at the international congress of the European Respiratory Society in Barcelona, ​​Spain.

While working on the project, Aljbawi and his superiors first investigated whether it was possible to use AI to analyze voices to recognize COVID-19 infection. The team reportedly used information from the University of Cambridge’s crowdsourced COVID-19 Sounds app, 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 of voice analysis known as Mel spectrogram analysis, which identifies several voice characteristics such as loudness, loudness and fluctuations over 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 for classifying Covid-19 cases,” explained Aljbawi. The research team found that long-term memory (LSTM) worked better than the others. The model is based on neural networks, which replicate the functioning of the human brain and recognize underlying patterns in the data.

The team revealed that the app’s overall accuracy was 89%. The app was approximately 89% accurate in identifying positive COVID-19 cases and 83% accurate in identifying negative Covid-19 cases. “These results show a significant improvement in the diagnostic accuracy of COVID-19 compared to state-of-the-art tests such as the lateral flow test,” Aljbawi said.

Notably, the team is still performing the tests and their results require even more testing and finding based on a larger population.

— ENDS —

Comments are closed.