A smartphone app can accurately identify Covid-19 infection in people's voices using artificial intelligence (AI), a study conducted in London revealed on Monday.
The software can be utilised in low-income nations where PCR tests are expensive and/or challenging to deliver because it is cheaper, quicker, and easier to use than numerous antigen testing, said the team.
According to Wafaa Aljbawi, a researcher at the Institute of Data Science at Maastricht University in the Netherlands, "the encouraging results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high precision in determining which patients have Covid-19 infection."
"We constructed various artificial intelligence models and analysed which one worked best at classifying the Covid-19 cases," Aljbawi said. "In order to distinguish the voice of Covid-19 patients from those who did not have the disease. Long-Short Term Memory (LSTM) was one of the models that they discovered performed better than the others.
Neural networks, which replicate the way the human brain functions and recognise the underlying correlations in data, are the foundation of LSTM.
Its total accuracy was 89 percent, positive instances could be accurately detected 89 percent of the time, and negative cases could be correctly identified 83 percent of the time.
Compared to state-of-the-art tests procedures like the lateral flow test, the results of this study "suggest a considerable improvement in the accuracy of diagnosing Covid-19," stated Aljbawi. According to the researchers, substantial numbers must be used to validate their findings.
Effects of Pre-Omicron provide protection against new variants: Study
Study finds Spending much time on gadgets make you older early
Parental Smoking habit Exposure and Adolescent Smoking Trajectories