CAPE TOWN – Researchers use artificial intelligence that analyses changes in the lungs and respiratory performance identifying Covid-19 in asymptomatic with an accuracy of 97 percent.
The biggest challenges during the Covid-19 pandemic was to contain the outbreak of the novel virus with scientists rushing to develop tools and technology to help identify infections easily and quickly in order to isolate, quarantine and treat those infected.
Scientists have now developed a new artificial intelligence model that detects Covid-19 in a forced cough that may possibly be used in smartphone devices with researchers believing it could become a useful tool for early screening.
The AI model analysed over a thousand hours of human speech, a dataset of words spoken in various emotional states and also a database of coughs to identify changes in the lung and respiratory performance using machine-learning.
“The sounds of talking and coughing are both influenced by the vocal cords and surrounding organs,” says research scientist Brian Subirana, from the Massachusetts Institute of Technology (MIT). “This means that when you talk, part of your talking is like coughing, and vice versa.”
“It also means that things we easily derive from fluent speech, AI can pick up simply from coughs, including things like the person’s gender, mother tongue, or even emotional state. There’s in fact sentiment embedded in how you cough.”
The AI model then analysed around 2 500 cough recordings of infected Covid-19 patients, correctly identifying 97.1 percent as positive and 100 percent of the asymptomatic cases.
Although the results look promising, there is still further development required, with the researchers also saying that this tool is not meant to diagnose anyone of Covid-19 but can simply be used as a pre-screening or early warning tool to advise isolation or a Covid-19 test which can be used easily and freely.
“The effective implementation of this group diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, or a restaurant,” said Subirana.
For LIVE updates on the Coronavirus pandemic, follow us on Twitter: @sacoronamonitor