[ad_1]
Numerous studies have shown that trained dogs can detect many types of diseases – including lung, breast, ovarian, bladder and prostate cancers, and possibly Covid-19 – simply by the smell. In some cases, involving prostate cancer for example, dogs have had a 99% success rate in detecting the disease by sniffing patients’ urine samples.
But it takes time to train such dogs, and their availability and time are limited. Scientists are looking for ways to automate the amazing olfactory abilities of dogs’ noses and brains in a compact device. Now, a team of researchers from MIT and other institutions have developed a system capable of detecting 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 to identify the distinctive characteristics of disease-carrying samples.
The findings, which the researchers say could one day lead to an automated odor detection system small enough to fit into a cell phone, are published today in the journal. PLOS One, in an article by Clare Guest of Medical Detection Dogs in the UK, MIT researcher Andreas Mershin and 18 others from Johns Hopkins University, the Prostate Cancer Foundation, and several other universities and organizations.
“Dogs, for about 15 years, have proven to be the earliest and most accurate disease detectors for anything we have ever tried,” Mershin says. And their performance in controlled tests has in some cases exceeded that of today’s best lab tests, he says. “So far, many types of cancer have been detected earlier by dogs than any other technology.”
Additionally, dogs seemingly detect connections that have hitherto escaped human researchers: When trained to respond to samples from patients with one type of cancer, some dogs have subsequently identified several other types of cancer – although the similarities between the samples were not obvious to humans.
These dogs can identify “cancers that don’t have identical biomolecular signatures in common, nothing in the scent,” Mershin says. Using powerful analytical tools, including gas chromatographic mass spectrometry (GCMS) and microbial profiling, “if you are analyzing samples, say, for skin cancer and bladder cancer and breast cancer and lung cancer – anything the dog has been shown to be able to detect – they have nothing in common. Still, the dog can somehow generalize from one type of cancer to be able to identify others.
Mershin and the team over the past few years have developed and continued to improve a miniaturized detection system that integrates stabilized mammalian olfactory receptors to act as sensors, whose data streams can be processed in real time by the capabilities. of a typical smartphone. He envisions a day when every phone will have a built-in scent detector, just as cameras are now ubiquitous in phones. Such detectors, equipped with advanced algorithms developed through machine learning, could potentially detect the first signs of disease much earlier than conventional screening regimes, he says – and could even warn of smoke or a gas leak.
In the latest tests, the team tested 50 urine samples from confirmed cases of prostate cancer and controls known to be disease-free, using both dogs trained and handled by Medical Detection Dogs at UK and the miniaturized detection system. They then applied a machine learning program to identify similarities and differences between the samples that could help the sensor-based system identify the disease. By testing the same samples, the artificial system was able to match the dogs’ success rates, with both methods achieving over 70%.
The miniaturized detection system, Mershin says, is actually 200 times more sensitive than a dog’s nose in terms of the ability to detect and identify tiny traces of different molecules, as confirmed by controlled tests commissioned by DARPA. But in terms of interpreting these molecules, “it’s 100% dumber”. This is where machine learning comes in, to try and find the elusive patterns dogs can infer from the scent, but humans haven’t been able to grasp from a chemical analysis.
“Dogs don’t know any chemistry,” Mershin says. “They don’t see a list of molecules popping up in their heads. When you smell a cup of coffee, you don’t see a list of names and concentrations, you get an integrated sensation. This sense of smell is what dogs can exploit.
While the physical apparatus for the detection and analysis of molecules in air has been under development for several years, with a large emphasis on reducing its size, until now the analysis has been default. “We knew the sensors are already better than what dogs can do in terms of detection limit, but what we haven’t shown before is that we can train artificial intelligence to mimic dogs,” he said. “And now we’ve shown that we can do it. We have shown that what the dog does can be replicated to some extent.
This achievement, say the researchers, provides a solid framework for further research aimed at developing the technology to a level suitable for clinical use. Mershin hopes to be able to test a much larger set of samples, perhaps 5,000, to identify significant indicators of the disease in more detail. But such tests don’t come cheap: It costs around $ 1,000 per sample for clinically tested and certified disease-free carrier urine samples to collect, document, ship and analyze, he says.
Reflecting on how he got involved in this research, Mershin recalled a study on the detection of bladder cancer, in which a dog kept mistakenly identifying a member of the control group as being positive for disease, even though it had been specifically selected on the basis of hospital testing as being disease free. The patient, who was aware of the dog’s test, opted for further testing and a few months later it was discovered that he had the disease at a very early stage. “Even though this is just one case, I have to admit it influenced me,” Mershin says.
The team included researchers from MIT, Johns Hopkins University of Maryland, Medical Detection Dogs in Milton Keynes, UK, Cambridge Polymer Group, Prostate Cancer Foundation, University of Texas at El Paso, Imagination Engines, and Harvard University. The research was supported by the Prostate Cancer Foundation, the National Cancer Institute, and the National Institutes of Health.
Source link
