Faking a cold so you don’t go to work? AI could tell if you’re really sick – National | globalnews.ca

Artificial intelligence is changing the way we work, do schoolwork, enjoy our waves and now… take sick days?

Anyone planning to fake illness in the future might want to reconsider their plans, as scientists are working on artificial intelligence technology that will be able to detect whether or not a person is sick based on the sound of their voice.

Researchers at the Sardar Vallabhbhai National Institute of Technology in India have been studying how diagnose disease using non-invasive techniques, and are in the process of developing a method that can identify when a person has a common cold, based on the sounds of their speech.

Read more:

What is juice jacking? Don’t use public charging stations, experts say

The study, as reported by The Economist and published earlier this year in the journal Processing and control of biomedical signalsIt is designed for help diagnose diseases over the phone in an effort to minimize medical appointments and prevent the spread of viruses, but could also make it more difficult for people to call in sick when they are not actually sick.

The story continues below the ad

The researchers, led by electronics engineer Pankaj Warule, analyzed the voice patterns of 630 Germans, 111 of whom had colds. They hypothesized that a cold might alter the vocal patterns normally present in those who feel well.

It’s no secret that voices change when sore throats and runny noses come into play, and researchers found that people with colds have uniquely different vocal rhythms, with differences in amplitude and frequency.

Click to play video: 'AI industry experts call for a pause in development'

AI industry experts call for a pause in development

According to the study, subjects were asked to count from one to 40, before counting what they did over the weekend. They were then asked to recite Aesop’s fable. The north wind and the sun — a frequently used text when investigating phonetics.

The proposed new features, which were placed on machine learning algorithms, performed quite well on determine who felt bad; they were able to accurately classify cold and non-cold speech with scores of 69 percent and 67 percent, respectively.

The story continues below the ad

As Insider points out, for the study results to apply to the real world as it is, it would be require a staff member to read the same fable while calling in sick, which sounds kind of silly. Clearly, the research is still in the early stages and the methods and technology would need to be adjusted.

Read more:

Fyre Fest II ‘is finally happening,’ says Billy McFarland a year after his release from prison

The study marks the latest in a long line of how AI is being used to remotely detect disease biomarkers.

The Economist reports that doctors, computer scientists and psychiatrists are already investigating how AI can help detect health problems based on how people walk, talk and write.

In a study published last year, researchers found that AI can be used to detect Parkinson’s disease by analyzing a person’s breathing patterns. And other studies have found that AI-trained vocal pattern analysis can also detect depression and various forms of cancer.

Read more:

DNA results are in: the woman who said she was Madeleine McCann did not lose the girl

In Canada, a Waterloo, Ontario lab used AI to design an advanced form of magnetic resonance imaging (NMR) that could better help identify breast cancer markers and determine a personalized treatment adapted to the individual and their type of cancer.

The story continues below the ad

“The cancer itself just lights up and really shows the different hues and characteristics around it, which makes it much easier to identify not only where the cancer is, the size of the cancer, but also the actual characteristics of the cancer tissue. to help. doctors make better decisions,” Alexander Wong, professor and Canada research chair in artificial intelligence and medical imaging at the University of Waterloo, told Global News.

© 2023 Global News, a division of Corus Entertainment Inc.


Add Comment