AI-based Voice Tool to Detect Covid-19
- 17 Apr 2020
- 3 min read
Why in News
A University in Rome (Italy) is conducting a pilot run for a patented Artificial Intelligence (AI)-based tool developed by students and a professor from Mumbai, which they claim can test Covid-19 through voice-based diagnosis using a smartphone.
- The tool has already been tested on 300 individuals and has detected Covid-19 patients with 98% accuracy.
- The tool is based on a voice-based diagnosis through an app. It can find coronavirus from the tone of the voice.
- As someone speaks to the microphone on the app, the tool breaks down the voice in multiple parameters such as frequency and noise distortion.
- These values are then compared to a normal person’s values and the patented technique then determines if the patient is positive or not.
- Each human voice has 6,300 parameters, and only a few units, less than a dozen, specifically characterise individuals. The human ear, apart from colds, is not able to distinguish them, but artificial intelligence does.
- Each one of an individual's internal organs is sort of a resonator, so if anyone has a problem with lungs or heart, this will be reflected in his/her voice.
- The current novel coronavirus cases could be detected this way.
Benefits of the voice-based diagnosis tool
- This tool can be of great 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, and help the government to identify hotspot regions in advance.
- It is possibly the best way to reach out to the remotest part of India by testing through a smartphone, without the risk of exposure, both to the patient and the lab personnel.
- This voice-based diagnosis will fetch zero cost testing to the patient and no wait time.
Artificial Intelligence (AI)
- It describes the action of machines accomplishing tasks that have historically required human intelligence.
- It includes technologies like machine learning, pattern recognition, big data, neural networks, self algorithms etc.
- AI involves complex things such as feeding a particular data into the machine and making it react as per the different situations. It is basically about creating self-learning patterns where the machine can give answers to the never answered questions like a human would ever do.
- AI technology helps in analyzing data and thus can improve the efficiency of the systems like power management in cars, mobile devices, weather predictions, video and image analysis.
- Example (Use): Self driving cars.