Frequency comb breath detector can ‘accurately detect COVID-19’ with machine learning

Machine Learning

A team of researchers Jun Ye and David Nesbitt and JILA have been working on an exciting new diagnostic tool that could revolutionize healthcare. JILA was founded in 1962 as a laboratory jointly operated by NIST, the National Institute of Standards and Technology (part of the US Department of Commerce), and the University of Colorado Boulder. JILA was formerly an acronym for “Joint Institute for Laboratory Astrophysics” but is now simply used as JILA (no acronym).

This project uses a frequency comb breath detector to scan human breath containing over 1,000 different trace molecules for markers of specific health conditions, including COVID-19. Frequency combs can measure different colors of light and identify chemical signatures of different molecules based on the color and amount or amount of infrared light absorbed or reflected. Ye and Nesbitt collected breath samples from 170 of his students and staff at the University of Colorado Boulder and used the data to determine whether and how frequency combs could detect COVID-19 in him. It was determined whether it could be detected with a degree of accuracy. It turned out that the machine predicted him to COVID-19 with a fairly high accuracy of about 85%. But the machine’s potential goes far beyond detecting COVID-19. briefly describes the project.

NIST/JILA Fellows Jun Ye, David Nesbitt, and colleagues report that a breath detector that combines Nobel Prize-winning frequency comb and machine learning techniques can accurately detect SARS-CoV-2 infection in human breath. We have proven that we can. Recognized with the 2005 Nobel Prize in Physics, frequency comb technology has the potential to detect many other diseases such as COPD, lung cancer and kidney failure. Frequency combs can accurately measure different colors of light, such as infrared light, which is absorbed by molecules in human breathing. Combining this technology with machine learning can detect the presence of specific combinations of molecules that are hallmarks of disease.

In the first video featured in the NIST article, Nesbitt and Ye provide more context and information about their research. Here’s part of that video I transcribed:

David Nesbitt, Chemical Physicist, NIST & JILA Fellow: I’m basically looking at the frequency of motion of these atoms in molecules. ”

Jun Ye, Physicist, NIST & JILA Fellow: “Atoms and Molecules – They emit light and absorb light. In fact, light is what we use to communicate with the microscopic world of atoms and molecules. A tool, we have developed a tool called Optical, a frequency comb is for timekeeping for an optical atomic clock, you can use it to measure molecules, you can use it to measure a person’s Wouldn’t it be interesting if you could smell a person’s breath and find out about the health of a particular person?”

Nesbitt: “What we’ve been doing is looking at about 150 COVID-positive and COVID-negative participants in this study, looking at their breath samples, and looking at the different frequencies that were absorbed or not absorbed. It’s all about looking at this frequency comb.”

Ye: “We can collect hundreds of thousands of detection channels at once, so we can detect many different kinds of molecules. You can, but you really didn’t know what to do with all that data before machine learning tools were introduced.”

They ultimately harnessed the power of machine learning to process and analyze the data they collected. Their findings could be revolutionary for the healthcare industry. Because frequency comb breath detectors have the potential to provide a quick, accurate, easy, non-invasive diagnostic tool to detect more health conditions than other breath-based analytical tools. “Work is already underway to miniaturize and simplify this technology to make it more portable and easy to use in hospitals and other healthcare settings,” NIST explains. To read more about the project and watch some videos explaining the details, check out this article on the NIST website.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *