IISc focusing on tool for COVID-19 detection predicated on cough, speech sounds
16 April, 2020
A team of researchers at the Indian Institute of Science (IISc), Bangalore, is focusing on an instrument for diagnosis of COVID-19 predicated on respiratory, cough and speech sounds.
Israeli start-up called Vocalis Health, backed by the country’s defence ministry, was already developing an iphone app with the same concept.
Similarly the IISc tool, once validated, will provide a test which poses minimum threat of exposure to the doctor and can supply the results faster compared to the current testing method.
The eight-member team, has named the project for speech and sound based diagnostics "Coswara", with an aim to identify and quantify biomarkers of the condition in the acoustics of the sounds.
"As the major symptoms of the condition include respiratory problems, the proposed project aims to detect and quantify the biomarkers of the condition in the acoustics of the sounds,” a team member told PTI.
“The project requires participants to execute a recording of breathing sounds, cough sounds, sustained phonation of vowel sounds and a counting exercise. The complete response requires about 5 minutes of recording time.”
"Along with these recordings, the tool also records the patient's health status in addition to age, gender and location, without the personally identifiable information. The sound dataset collected will be released to researchers around the world to build up a potential diagnostic tool using signal processing and machine learning methods," he added.
The project is in the data collection stage and can proceed through an experimental validation before obtaining full approval as a potential diagnostic tool.
In a similar project, a computer scientist Matt Whitehall at the University of Washington, is soliciting volunteers to record themselves coughing. The info Whitehill is collecting will be utilized to teach an algorithm that detects and counts coughs in patients dealing with COVID, Slate reported.
"Given the highly simplistic and cost-effective nature of the tool, we hypothesize that a good partial success for the tool would allow an enormous deployment as an initial line diagnostic tool for the pandemic," the IISc researcher said.
“The project isn't aimed to displace the chemical testing or the imaging methods but to merely supplement those with a cost-effective, fast and simple technique.”
Source:
TAG(s):