A new detection strategy has been developed at the Polytechnic of Montreal

(Montreal) A device the size of a microwave oven may soon be able to detect many health problems, from COVID-19 to cancer and concussions within a few seconds, believes a researcher at the Polytechnic of Montreal.

Posted on February 9

Jean Benoit Legault
Canadian Press

Best of all, samples do not need to be shipped to the lab, causing delays in getting results, or treated with reagents that can be harmful to the environment and are difficult to obtain in times of high demand.

This means that the analysis can be done by almost anyone, almost anywhere, and the results will be available very quickly.

“We can imagine, for example, the hockey team: before going on the ice, everyone can take the test relatively quickly, explains Professor Frederic Leblond, who first shared the conclusions of his work with La Canadian Press. In half an hour, the matter was settled, passed Everyone, everyone got their results.”

PHOTO CAROLINE PERRON, provided by Polytechnic

Frederic Leblond

In short, Raman Spectrography – named after the Indian physicist who won the 1930 Nobel Prize in Physics for his discovery of the “Raman effect” – uses a laser beam to determine the composition of a sample, whether it be saliva, blood, or cells.

In the case of COVID-19, Professor Leblond and colleagues at the Chom Research Center have found that a simple drop of dried saliva will be enough for Raman spectroscopy and machine learning, a form of artificial intelligence, to determine, in a few moments, whether a patient has SARS-CoV. -2.

The researchers, led by postdoctoral fellow Catherine Ember, analyzed 37 saliva samples from COVID-19 patients as well as 513 healthy patients to train a machine learning tool to distinguish samples from infected or healthy individuals.

The resulting images are useless to human eyes, but they do mask the fingerprint of COVID-19 that AI can detect — though the researchers admit they don’t know exactly what the tool is detecting.

Regardless, the tool was able to identify positive cases with a success rate of 79% to 84% and negative samples with a rate of 64% to 75%, depending on whether the sample came from a man or a woman.

Improvements since the end of the work revealed in the Journal of Biomedical Optics have amplified detection of positive cases to 95% and negative cases to 80%.

Professor Leblond admits, however, that his discovery may come a little late in the fight against COVID-19, at a time when the epidemic is likely to show signs of running out of steam and when other methods of detecting the virus are widely available.

“But what’s interesting is that our method is not specific to COVID,” he said. We can re-adapt all of that to detect other things like influenza, we can imagine detecting Lyme disease, we can think about early cancer screening tests…”

He added that the fact that the method can be used to detect COVID-19, with all the problems involved, indicates its ability to detect other health conditions.

“It’s as if we took a very difficult example at first,” Professor Leblond said. It really opens the door to many things. »

Professor Leblond won the Quebec Science Discovery of the Year in 2017 with his assistant surgeon, Kevin Petrica, for his use of Raman spectroscopy as a tool to distinguish cancerous tissue from healthy tissue during surgical procedures.

Leave a Reply

Your email address will not be published.