Editor: Bolysbek Dana
Author: Akhmetzhanova Inara
Translator: Tulkibaeva Nursulu
Research scientist Andreas Mershin of the Massachusetts Institute of Technology and 18 other people from Johns Hopkins University, the Prostate Cancer Foundation, and several other universities and organizations have developed a system that can detect the chemical and microbial content of an air sample with even greater sensitivity than a dog's nose. They combined this with a machine learning process that can determine the distinctive characteristics of disease-carrying samples.
Mershin recalls a long-standing study on the detection of bladder cancer, in which the dog continued to mistakenly identify one member of the control group as a person with a positive diagnosis, even though he was healthy. This patient decided to undergo additional tests, and after a few months, it was discovered that the disease was at a very early stage. "Even though it's just one case, I have to admit that did sway me," Mershin says.
According to the scientist, a miniature detection system is actually 200 times more sensitive than a dog's nose, from the point of view of the ability to detect and identify tiny traces of different molecules.
Mershin and his team over the past few years have developed and continued to develop miniature detection system, which includes the olfactory receptors of mammals, more stable to operate as sensors, data streams which can be processed by a conventional smartphone.
In the latest tests, the team tested 50 urine samples from confirmed cases of prostate cancer and a control group that does not suffer from the disease, using dogs trained by Medical Detection Dogs in the UK and a detection system. When testing the same samples, the artificial system was able to compare the success rates of the dogs, with both methods scoring more than 70 percent.
