New screening tool uses AI voice analysis to detect Covid-19

By Leila Hawkins
Vocalis Health’s Covid-19 screening tool using AI voice analysis has high rate of accuracy...

Israeli startup Vocalis Health has developed VocalisCheck, a tool that has achieved an average accuracy of 81.2% in identifying Covid infection based on people's voice samples. 

Vocalis conducted a study of over 2,000 people in collaboration with the Municipal Corporation of Greater Mumbai (MCGM). Participants counted from 50 to 70, their voice recording transformed to an image containing 512 features.  

That picture is then compared using AI machine learning/deep learning techniques to a composite picture based on the voice recordings of COVID-19 positive participants in clinical trials, to determine whether there is a high or low correlation between them.  

This technology can be integrated into existing mobile or web applications (via an SDK or Software Developers Kit) or can be accessed through a dedicated web-based portal via any connected device without the need for further equipment. This can enable health systems to limit the use of PCR testing to those at higher risk of infection.

However Vocalis Health point out that this is not intended to serve as a diagnostic tool, but as a screening device to guide those who may need additional diagnostic testing, enabling health systems to allocate diagnostic resources more efficiently.

“PCR testing is being used to screen for Covid-19, which is an extremely expensive, resource-intensive and time-consuming approach” said Dr. Shady Hassan, Co-Founder, Chief Operating and Medical Officer of Vocalis Health. 

“Instead of misusing PCR testing for screening, utilising a highly scalable screening tool like VocalisCheck can fill a significant gap in the current approach to Covid screening, with the ability to effectively funnel those with high risk of infection to the appropriate diagnostic test.”

In the study in India, a symptom checker alone correctly identified approximately 66% of the people with Covid-19 infection, while VocalisCheck achieved around 80% accuracy in assessing a person’s risk of Covid-19 infection.

“We are encouraged by the study’s findings, which further validate VocalisCheck’s ability to screen for Covid-19,” explained Tal Wenderow, CEO of Vocalis Health.  

“These new results, combined with our recent CE-mark approval, demonstrate our commercial readiness to deploy the VocalisCheck screening tool to help businesses, governments, universities and others safely return to work, school, healthcare and leisure while lightening the burden on health systems.”

VocalisCheck has received the CE-mark, making it the first device of its kind to gain CE-mark approval.


Featured Articles

Snowflake: Transforming patient healthcare with Gen AI

Jesse Cugliotta, Healthcare & Life Science at Snowflake, discusses revolutionising healthcare efficiency and improving patient care with Gen AI

Johnson & Johnson: Turning supplier spend into local support

Johnson & Johnson’s Global Supplier Diversity & Inclusion team is growing spending with social enterprises around the globe to expand its impact

Seasonal Affective Disorder’s impact on health & solutions

Dr Ravi Gill & Dr. Naomi Newman-Beinart discuss Seasonal Affective Disorder and its treatments, from vitamin D spray to light therapy

CGI teams up with Totalmobile for digital healthcare service

Digital Healthcare

Deloitte: generative AI can improve access to healthcare

Technology & AI

Wipro & NVIDIA’s revolutionary healthcare uses generative AI