London: A smartphone application can be found accurately Kovid-19 infection into people’s voices with the help of artificial intelligence, researchers announced Monday.
The team claimed the app is more accurate than many antigen tests and is cheap, fast and easy to use, meaning it can be used in low-income countries. PCR tests Expensive and/or difficult to deliver.
“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,” said Wafa Aljabawi. Institute of Data ScienceMaastricht University, The Netherlands.
“In addition, they enable remote, virtual testing and have a turnaround time of less than a minute. They can be used, for example, at entry points for large gatherings, enabling rapid population screening,” she told the European Respiratory said at Society International Congress in Barcelona, Spain.
Covid-19 infection usually affects the upper respiratory tract and vocal cords, leading to changes in a person’s voice.
Aljabawi and his supervisors decided to investigate whether it was possible to use AI to analyze voices to detect Covid-19.
They used the data University of CambridgeCrowd sourcing of Covid-19 Sounds app It contains 893 audio samples from 4,352 healthy and unhealthy participants, of which 308 tested positive for Covid-19.
The researchers used a voice analysis technique called Mail Spectrogram analysis, which identifies various characteristics of sound such as loudness, power, and temporal variation.
“To distinguish the voices of Covid-19 patients from those without the disease, we built different artificial intelligence models and evaluated which one did the best job of classifying Covid-19 cases,” Aljabawi added.
They found that a model called long-short term memory (LSTM) outperformed the other models.
LSTMs are based on neural networks, which mimic the way the human brain works and identify underlying relationships in data.
Its overall accuracy was 89 percent, its ability to correctly detect positive cases was 89 percent, and its ability to correctly identify negative cases was 83 percent.
“These results show a significant improvement in the accuracy of the diagnosis of Covid-19 compared to advanced tests such as the lateral flow test,” Aljabawi said.
The researchers say their results need to be validated in larger numbers.
