Detecting Covid as easy as catching drunk people? AI-powered gadget will diagnose COVID-19 in seconds

A team of scientists at the University of Colorado (CU) Boulder has created a new breathalyser test powered by artificial intelligence (AI) and based on laser technology that can accurately detect COVID-19 in real-time. The innovative frequency comb breathalyser is capable of distinguishing between different molecules using laser light, and it has the potential to transform medical diagnostics.

In a study published in the Journal of Breath Research, the team collected breath samples from 170 CU Boulder students between May 2021 and January 2022. The students had taken a polymerase chain reaction (PCR) test in the previous 48 hours, either by submitting a saliva or a nasal sample. Half of the students had tested positive for COVID-19, while half tested negative.

The test showed a matching result of 85 per cent when compared to the PCR test, which is considered the gold standard for COVID-19 testing. An accuracy rate of 80 per cent or higher is deemed "excellent" in medical diagnostics. The researchers pointed out that the accuracy could have been higher if the breath sample and the saliva/nasal swab had been collected simultaneously.

The breathalyser test is non-invasive, unlike a nasal swab. And unlike a saliva sample, users are not required to refrain from eating, drinking or smoking before using it. The test does not require costly chemicals to break down the sample, and it could be used on individuals who are not conscious.

The breathalyser test consists of a complex array of lasers and mirrors, about the size of a banquet table. The breathalyser device takes in a breath sample through a tube and uses lasers to emit mid-infrared light at thousands of frequencies. This light is then reflected back and forth by dozens of tiny mirrors, allowing it to travel up to 1.5 miles through the molecules in the sample. Because each kind of molecule absorbs light differently, breath samples with different molecular make-up cast distinct shadows.

Within seconds, the machine can differentiate between the various shadows or absorption patterns, and convert millions of data points into a straightforward positive or negative result for COVID-19. Scientists are currently working on shrinking these systems to the size of a chip, enabling individuals to monitor their health in real-time while on the move.

"Our results demonstrate the promise of breath analysis as an alternative, rapid, non-invasive test for COVID-19 and highlight its remarkable potential for diagnosing diverse conditions and disease states," said Qizhong Liang, a PhD candidate at CU Boulder and the study's first author. 

"There is a real, foreseeable future in which you could go to the doctor and have your breath measured along with your height and weight. Or you could blow into a mouthpiece integrated into your phone and get information about your health in real-time," said Jun Ye, an adjoint professor at CU Boulder and senior author of the study.

Also Read 

'Buying Netflix at $4 billion would've been better instead of...': Former Yahoo CEO Marissa Mayer

ChatGPT beats top investment funds in stock-picking experiment