A university in Rome is conducting a pilot run for a patented artificial intelligence-based tool developed by three biotechnology students and a professor from Mumbai, which they claim can test COVID-19 through voice-based diagnosis using a smartphone application. The tool is being tested by the University of Tor Vergata in Rome and has already been tested on 300 individuals.
According to the students and the professor from DY Patil Institute of Bio Technology and Bio Informatics, Mumbai, the tool is based on a voice-based diagnosis through an app. The team includes bioinformatics students Rashmi Chakraborty, Priyanka Chauhan and Priya Garg.
Brihanmumbai Municipal Corporation (BMC) will start screening suspected Covid-19 patients through artificial intelligence (AI), using their voice samples from Wednesday. On the occasion of Ganesh Chaturthi, the civic body signed the memorandum of understanding (MOU).Each human voice has 6,300 parameters, and only a few units, less than a dozen, specifically characterize individuals. The human ear, apart from colds, is not able to distinguish them, but artificial intelligence does. Each one of our internal organs is sort of a resonator, so if we have a problem with our lungs or our heart, this is reflected in our voice.
Artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals. Leading AI textbooks define the field as the study of "intelligent agents" any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term "artificial intelligence" is often used to describe machines (or computers) that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem solving".
The gold standard test for diagnosis of the Sars-Cov-2 virus, which causes Covid-19, is reverse transcription-polymerase chain reaction (RT-PCR). But it takes over eight hours to provide the result. Though rapid antigen tests give test results within 30 minutes, as per the Indian Council of Medical Research (ICMR), its false negativity rate is higher. With the ongoing unlocking of the national lockdown, the civic body needs more economical alternatives to rapidly and accurately diagnose cases of Covid-19. Thus, BMC has decided to start voice analysis to detect the virus within 30 seconds.
Dr Neelam Andrade, dean of Nair Dental Hospital and in-charge of NESCO, explained the process. When the symptoms of Covid-19 manifest, the person starts having breathing problems that affect the amount of air exhaled. Then the air interacts with inflamed muscles on its journey to production voices or speeches. These interactions impact the voice modulations — measurable qualities that form the basis of their biomarkers. Depending on its variations, an individual can be detected with Covid-19.
“We signed the MOU on Saturday and the study will start from Wednesday under the supervision of Dr RN Cooper Municipal General Hospital,” said Suresh Kakani, additional commissioner, BMC. “It will take two to three months to conclude the study,” he said.
“While several foreign universities are trying to launch a voice-based AI tool for COVID-19 detection, this Indian 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,” professor Santosh Bothe, who supervised the project, told PTI.(Press Trust of India).
A team at the Indian Institute of Science (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 audio-based disease diagnosis tool can find coronavirus from the timbre of the voice.
The application will analyse voices of three types of people — suspected, confirmed and negative with Covid-19. Depending on their vocal biomarkers (VB), they will be diagnosed. For example, if a person’s VB is below the standard point — 0.5, he/she will be considered as negative. But if anyone records VB above it, he/she will be suspected with Covid-19 and an RT-PCR test will be conducted for confirmation.
Vocal-biomarkers is a technique that enables machines to understand human emotions by analyzing, recording and detecting raw voice intonations as people speak. Biomarkers in the voice of a person have been linked to disorders such as depression, coronary artery disease, and anxiety.
According to an infographic shared by Shiv Sena MLA Aditya Thackerey on Twitter, the process involves:
- A suspected patient will be asked to speak into a cellphone (or computer) where the voice analysis app has been uploaded. The patient’s vital parameters too will be taken.
- The voice sample will be analysed by the app, powered by a programme based on artificial intelligence (AI)
- The sample will be compared with the voice of a person not suffering from COVID-19 to provide an analysis. The app comes preloaded with thousands of voice patterns.
This is a good angle of fighting against covid-19. I am looking forward to see the results of this study.
No comments:
Post a Comment