A new mobile phone app is able to detect Coronavirus in under one minute just by listening to your voice - and claims to be more accurate than a lateral flow test.
The scientific breakthrough has been powered by artificial intelligence, and is both more user friendly and accurate than LFTs according to the big brains behind it.
The iPhone and Android app reportedly gives an accurate positive result some 89 per cent of the time, as well as an 83 per cent success rate for negative cases - delivering a confirmation in less than 60 seconds as opposed to LFTs which can take up to 15 minutes to expose.
The Mirror reports that the app could in-turn revolutionise the approach to testing for Covid-19, especially in poorer countries where the gold-standard PCR tests are more costly and harder to distribute. In the UK, it could also help keep the virus suppressed in the long-run, with the Government abandoning free LFTs some time ago.
But just how does the app work?
The Dutch creators say that Covid usually affects the vocal chords of a person due to it hitting the upper respiratory tract - which in-turn leads to subtle changes in their voice. The team then investigated the possibility of using this to detect the novel virus.
During the development process, they used data from the University of Cambridge's crowdsourcing Covid-19 Sounds App, which contained 893 audio samples from 4,352 participants - 308 of whom had tested positive for the virus. The app would also take some basic information on users, including demographic, medical history and whether they smoke or not.
Next, it would ask them to record some respiratory sounds like coughing, breathing deeply, and reading short sentences. A voice analysis technique known as Mel-spectrogram analysis would then be used, identifying key features in the voice - including volume, power and variation over time.
Lastly, an AI-based on human neural networks was used to work with the information and data collated to detect the deadly virus.
Researcher Wafaa Aljbawi, from the University of Maastricht, 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.
“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.
“In other words, we could miss 11 out 100 cases who would go on to spread the infection, while the lateral flow test would miss 44 out of 100 cases. The high specificity of the lateral flow test means that only one in 100 people would be wrongly told they were COVID-19 positive when, in fact, they were not infected, while the LSTM test would wrongly diagnose 17 in 100 non-infected people as positive.
“However, since this test is virtually free, it is possible to invite people for PCR tests if the LSTM tests show they are positive.”
Before the app is rolled out worldwide, the team are urging for more participants. Since the start of the project, some 53,449 audio samples from 36,116 participants have been collected and can be used to both improve and validate the accuracy of the model.
The findings will be presented at the European Respiratory Society International Congress in Barcelona, Spain.
Read next:
- Great North Run 2022 route, where the half marathon starts, finishes and goes
- South Shields’ best places to grab food after the Great North Run according to Tripadvisor
-
Great North Run 2022 route, map, start time and road closures for September's half-marathon
-
Great North Run reveals T-shirt and medal design for September's event
