People have now learned to coexist with COVID-19. While we are now living an almost normal life, cases of the coronavirus are still being recorded and how. With the advancement of technology, people no longer have to stand in lines to get tested for COVID. Several home test kits are also available. Now if we say that a smartphone app can test for COVID? Surprising right? That’s what the study says. That a phone app can accurately detect a COVID-19 infection.
Researchers at the Institute of Data Science, Maastricht University, Netherlands, have developed a smartphone app that can accurately detect COVID-19 infection in people’s voices using AI (artificial intelligence). That’s right, there’s no need for a nose sample.
The researchers said the app is more accurate than several antigen tests and is cheap, fast, and easy to use. This now means it can be used in low-income countries. The researchers also said that countries, where PCR tests are relatively expensive or difficult for the government to distribute, can use the software.
Wafaa Aljbawi, a researcher at the Institute of Data Science, Maastricht University, Netherlands, said: “The promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high accuracy in determining which patients have Covid-19 infection.” they allow remote, virtual testing and have a processing time of less than a minute. They could be used, for example, at the entry points of large gatherings, which would enable rapid screening of the population,” Aljbawi added during her presentation at the European Respiratory Society International Congress in Barcelona, Spain.
While working on the project, Aljbawi and her supervisors first investigated whether it was possible to use AI to analyze voices to detect the infection of COVID-19. The team reportedly used information from the crowdsourced app COVID-19 Sounds from the University of Cambridge, which contains 893 sound 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 characteristics of the voice such as loudness, strength and fluctuations over time.
“To distinguish the voice of patients with Covid-19 from those who did not have the disease, we created different artificial intelligence models and evaluated which one works best in classifying Covid-19 cases,” explained Aljbawi. The research team found that Long-Short Term Memory (LSTM) performed better than others. The model is based on neural networks that replicate the way the human brain works and recognize basic patterns in the data.
The team revealed that the app’s overall accuracy was recorded at 89 percent. The app was approximately 89 percent accurate in identifying positive COVID-19 cases and 83 percent accurate in identifying negative Covid-19 cases. “These results show a significant improvement in the accuracy of the diagnosis of COVID-19 compared to state-of-the-art tests such as the lateral flow test,” Aljbawi said.
Researchers have developed a new smartphone app that can accurately detect Covid-19 infection in people’s voices using artificial intelligence (AI).
The AI model used in the research is more accurate than rapid antigen tests or lateral flow tests and is cheap, fast and easy to use, the researchers said.
The finding was presented on Monday at the international congress of the European Respiratory Society in Barcelona, Spain.
According to the researchers, the AI model is accurate 89 percent of the time, while the accuracy of side-flow tests varies widely by brand.
Also, lateral flow tests are significantly less accurate in detecting Covid-19 infection in people who show no symptoms, they said.
“These promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high accuracy in identifying patients who have Covid-19 infection,” said Wafaa Aljbawi, a researcher at Maastricht University in the Netherlands.
“These tests can be provided for free and are easy to interpret. Moreover, they enable remote virtual testing and have a processing time of less than a minute,” said Aljwabi.
The new test could be used, for example, at the entry points of large gatherings, allowing rapid population screening, the researchers said.
The Covid-19 infection usually affects the upper respiratory tract and vocal cords, leading to changes in a person’s voice.
Aljbawi and her supervisors used data from the crowdsourced application Covid-19 Sounds at the University of Cambridge, which contains 893 audio samples from 4,352 healthy and unhealthy participants, 308 of whom tested positive for Covid-19.
The application is installed on the user’s phone. Participants report some basic information about demographics, medical history, and smoking status and are then asked to record some breath sounds.
These include coughing three times, taking three to five deep breaths through your mouth, and reading a short sentence on the screen three times.
The researchers used a voice analysis technique called Mel-spectrogram analysis, which identifies various voice characteristics such as loudness, strength and changes over time.
“In this way, we can decompose many features of the participants’ voices,” Aljbawi said.
“To distinguish the voice of patients with Covid-19 from those who did not have the disease, we created different artificial intelligence models and evaluated which one performs best in classifying Covid-19 cases,” she added.
They found that one model called Long-Short Term Memory (LSTM) outperformed the other models. LSTM is based on neural networks that mimic the way the human brain works and recognize underlying relationships in data.
Its overall accuracy was 89 percent, its ability to correctly detect positive cases, or “sensitivity,” was 89 percent, and its ability to correctly identify negative cases, or specificity, was 83 percent, the researchers found.
In another study, Henry Glyde, a PhD student at the University of Bristol, showed that AI could be used through an app called myCOPD to predict when patients with chronic obstructive pulmonary disease (COPD) might experience a flare-up of their disease. COPD exacerbations can be very severe and are associated with an increased risk of hospitalization.
Symptoms include shortness of breath, coughing and increased mucus production.
