By Peter McLaren-Kennedy •
Published: 05 Sep 2022 • 13:05
Mobile phone app - ESB Professional / Shutterstock.com
Researchers said on Monday, September 5 that the app which can detect COVID in people’s voices using artificial intelligence (AI) is 89 per cent accurate.
The app which has “potentially high precision” is according to the Institute a cheap alternative to lateral flow tests. This that say could be very useful in low-income countries, as well as those that currently make extensive use of existing tests.
Tests carried out by the Institute show that results are available in less than a minute and are a “significant improvement” on the accuracy of lateral flow tests.
Lateral flow tests require swabs to be taken from the upper respiratory tract and have been criticised for their varied results. One of the reasons for this is the need to take an effective swab, which is why the researchers looked for an alternative.
Wafaa Aljbawi, a Researcher at the Institute said: “These 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.
“Such tests can be provided at no cost and are simple to interpret. 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.”
To test the technology, the Institute used recordings from the University of Cambridge’s crowd-sourcing COVID19 Sounds app.
Users of the app were required to give detailed medical history and personal demographics. They were then required to provide sample recordings such as reading and coughing. In the end 893 audio samples from 4,352 healthy and non-healthy people were obtained.
Those samples were then analysed using a voice analysis technique called Mel-spectrogram. This enabled researchers to “decompose the many properties of the participants’ voices.”
Aljbawi said: “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.
“The lateral flow test has a sensitivity of only 56 per cent, but a higher specificity rate of 99.5 per cent. This is important as it signifies that the lateral flow test is misclassifying infected people as COVID-19 negative more often than our test.
“In other words, with the AI LSTM model, we could miss 11 out of 100 cases who would go on to spread the infection, while the lateral flow test would miss 44 out of 100 cases.”
The research, which is being presented to the European Respiratory Society International Congress in Barcelona today, also points to the use of the app in predicting exacerbations in chronic obstructive pulmonary disease.
If the COVID mobile phone app is indeed more accurate than lateral flow tests, this could be a game changer for the medical profession in collecting data as well as in treating the virus.
Thank you for taking the time to read this article, do remember to come back and check The Euro Weekly News website for all your up-to-date local and international news stories and remember, you can also follow us on Facebook and Instagram.
Share this story
Subscribe to our Euro Weekly News alerts to get the latest stories into your inbox!
By signing up, you will create a Euro Weekly News account if you don't already have one. Review our
Originally from South Africa, Peter is based on the Costa Blanca and is a web reporter for the Euro Weekly News covering international and Spanish national news.
Got a news story you want to share? Then get in touch at firstname.lastname@example.org.
Download our media pack in either English or Spanish.