Revolutionizing Medical Diagnostics With Frequency Comb Breathalyser

Tuesday - May 16 2023, 04:49 UTC - 1 year ago

Researchers from CU Boulder and the National Institute of Standards and Technology (NIST) have created a laser-based breathalyzer powered by artificial intelligence (AI) capable of detecting COVID-19 in real-time. The team has shifted their focus to a wide range of other diseases in hopes of revolutionizing medical diagnostics, however they need to collect data from other populations in order to build on their results and make the technology more broadly available.

For years, researchers have been trying to tap into the wealth of information in our breath, utilizing the keen sense of smell in animals to detect diseases. Researchers from CU Boulder and the National Institute of Standards and Technology (NIST) have now made an important leap forward in the quest to diagnose diseases using exhaled breath. The team recently published their results in the Journal of Breath Research.

"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 first author Qizhong Liang.

The multidisciplinary team of physicists, biochemists, and biologists are now shifting their focus to a wide range of other diseases in hopes that their "frequency comb breathalyzer"—born of Nobel Prize-winning technology from CU—could revolutionize medical diagnostics.

Jun Ye—senior author of the study and a JILA fellow and adjoint professor of physics at CU Boulder—said " 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. The potential is endless." .

The technology, frequency comb spectroscopy, uses laser light to distinguish one molecule from another and can detect trace molecules at the parts-per-trillion level. They’ve also harnessed the power of AI. "Machine learning analyzes this information, identifies patterns, and develops criteria we can use to predict a diagnosis." .

The research team collected breath samples from 170 CU Boulder students who had, in the previous 48 hours, taken a polymerase chain reaction (PCR) test, either by submitting a saliva or a nasal sample. Half had test results suggesting they were infected with SARS-CoV-2; half tested negative.

The results showed that their breathalyzer algorithm could detect the presence of SARS-CoV-2 with 96 percent accuracy. The study was promising, but it was only conducted on Boulder students. Researchers now need to collect data from other populations to build on their results and make the technology more broadly available.

As Ye said, "The goal of our study was to help accelerate the development of breath analysis for better medical diagnostics—showing insight and what’s doable. But it was just the beginning." .