Malaysia
Serba Dinamik develops algorithm to identify Covid-19 through cough
Health workers collect swab samples to test for Covid-19 at the Selcare Clinic in Shah Alam August 1, 2021. u00e2u20acu201d Picture by Yusof Mat Isa

KUALA LUMPUR, Nov 15 — An Artificial Intelligence (AI) algorithm developed by Serba Dinamik Artificial Intelligence Team (SDAI) has correctly identified people with Covid-19 just by the sound of cough.

In a statement today, Serba Dinamik Holdings Berhad said the team, which is led by Artificial Intelligence Society Malaysia (ARTIS) president Dr Azree Shahrel Ahmad Nazri, has performed clinical tests with 150 participants.

Advertising
Advertising

It said the results have achieved 94 per cent sensitivity for symptomatic cases among people who had received official positive Covid-19 RT-PCR test results, while 88 per cent are those who had no other symptoms.

"In mass testing with 1,009 participants, it has achieved 94 per cent accuracy, 96 per cent sensitivity and 94 per cent specificity.

"This application, which was named as AI-Screen, is being evaluated by National Technology & Innovation Sandbox (NTIS), Ministry of Science, Technology & Innovation (Mosti),” the statement read.

According to the statement, practical use cases could be for daily screening of students, workers and public, as schools, jobs and transport reopen or for pool testing to quickly alert the outbreak in groups.

In June 2020, as the outcome from the collaboration of SDAI with ARTIS, it has managed to run up a dataset of 25,000 cough sample sounds and the application has been tested since last year.

Meanwhile, Serba Dinamik Holdings Berhad managing director and chief executive officer Datuk Mohd Abdul Karim Abdullah said users must comply with the existing standard operating procedure, which is to take an RT-PCR test either at a government or private health facility for further confirmation.

"The inability to test at scale has become a major problem in the ongoing war against the Covid-19 pandemic. AI-Screen application is a smartphone application which is able to record and send three cough sounds to an AI engine and can produce a result within two minutes,” he said, adding that the screening tool is deployable anytime anywhere by anyone.

Abdul Karim said cough manifests as a symptom in the majority but not all Covid-19 carriers, but many studies show that coughing is one of the key mechanisms for the spread of Covid-19.

He said a temperature scan is currently the predominant screening method for Covid-19, for example when entering malls.

Between cough and fever, he said, the number of non- Covid-19 medical conditions that can cause fever are much larger than the non- Covid-19 conditions that can cause cough.

Abdul Karim said the AI-Screen application is not meant to replace or compete with the medical grade testing by any means, but instead the application offers complementing use cases to control the pandemic into endemic.

He said the team is targeting to collect more samples by focusing on the Delta variant.

He said this application can be used as a pre-screening method that is accessible by the public by the end of this year after receiving NTIS nod from Mosti. — Bernama

Related Articles

 

You May Also Like