Mumbai Biotechnology Students Develop AI-Based Voice Tool To Detect COVID-19

A team of three biotechnology students and a professor from Mumbai has recently claimed to have developed an artificial intelligence-based tool test COVID-19 through voice-based diagnosis using a smartphone. 

The AI-based voice tool is currently being tested in the University of Tor Vergata in Rome, where they are conducting a pilot run for the patented tool. It has already been tested on 300 individuals.

According to the students and the professor from DY Patil Institute of Biotechnology and Bioinformatics, Mumbai, the tool has been based on a voice-based diagnosis through an app.

According to the professor who supervised the project, Santosh Bothe, “This Indian AI-based voice tool is fully functional and currently in use in Italy to identify COVID-19 patients. The students have a full-fledged working software with a rich database of patients and healthy samples. This tool is being currently used by the University of Rome to detect COVID-19 patients with 98% accuracy.”

He explained further — to detect infected people, one has to speak to the microphone on the app, while the tool breaks down the voice in multiple parameters such as frequency and noise distortion. These values are then compared to an average person’s values, and the patented technique then determines if the patient is positive or not.

In a similar effort, a team at the IISc, Bangalore, is also working on a diagnostic tool based on analysis of cough and respiratory sounds.

According to Giovanni Saggio, professor at the Rome university’s Engineering department, the AI-based voice tool can find coronavirus from the timbre of the voice.

Saggio explained that each human voice has 6,300 parameters, specifically characterised for individuals. It gets difficult for a human ear to distinguish them, but it’s an easy job for artificial intelligence. 

He said, “Each one of our internal organs is a resonator, so if we have a problem with our lungs or our heart, this is reflected in our voice. And the same person has one voice when they are healthy, and another if they have a pathology. Since this virus compromises lungs and airwaves, the voice is affected.”

Students in the team believe that this AI-based voice tool can be of significant impact in doing the first level of screening to identify positives and only those who tested positive can go for the lab tests. This can reduce the current bottleneck on the medical infrastructure, help the government to identify hotspot regions in advance through location tracking integration and is possibly the best way to reach out to the remotest part of India by testing through a smartphone.

Further, the team explained that this voice-based diagnosis would fetch zero cost testing to the patient and no wait time. Diagnosis of COVID-19 positive patients can be done in minutes, and medical advice on the next steps can be sought through a video or audio call to the listed doctors.