'Robotic nose' could be created after detection dogs sniff out lethal cancer
Click here to watch a report by ITV Anglia reporter Liz Summers
A dog’s nose could hold the key to detecting the most lethal type of prostate cancer, scientists have said.
Results from a study involving Milton Keynes-based charity Medical Detection Dogs could lead to the development of a more sensitive and specific prostate cancer diagnostic method beyond the blood test which is currently used, researchers said.
They hope the work can be replicated in a bigger study and eventually result in the production of a “robotic nose” perhaps in the form of a smartphone app.
Dr Claire Guest, co-founder and chief scientific officer of Medical Detection Dogs, said the publication of the study is “extremely exciting”.
She said: “What we now need to find out is whether or not the dog’s ability to discriminate and detect the very fast-growing, dangerous forms of prostate cancer through this non-invasive and rapid, reliable test could go on to saving millions of lives around the world.”
The Duchess of Cornwall, who is patron of Medical Detection Dogs, was “impressed” in October by a demonstration where Labradors, trained to sniff out Covid-19, were put through their paces in the real-life environment of Paddington station.
For the latest research scientists, knowing already that dogs can accurately sniff out early prostate and other cancers, focused on which elements of scent the animals were detecting and how they were processing the information.
The study, published in the PLOS One Journal, involved four-year-old Labrador Florin and Midas, a seven-year-old Vizsla, who were trained to detect prostate cancer in urine samples.
Researchers combined three approaches – the dogs’ sense of smell, artificial intelligence-assisted chemical analysis, and microbial analysis of urine samples.
The dogs showed 71% sensitivity – the rate at which they correctly identified positive samples – and 70-76% specificity – the rate at which they correctly ignored negative samples including those with other diseases, when detecting the most lethal form of prostate cancer.
They also correctly identified when 73% of blinded patient samples did not have the disease.
Researchers said the results compare favourably to the most commonly used prostate cancer test, the PSA (prostate-specific antigen) blood test.
Dr Guest led the study, which also involved Massachusetts Institute of Technology (MIT) and Johns Hopkins University and was supported by a Prostate Cancer Foundation (PCF) research sponsorship.
She said: “This study showed that a dog’s nose could hold the key to an urgently needed, more accurate, and non-invasive method of early prostate cancer diagnosis.
“Specialist-trained cancer detection dogs Florin and Midas detected extremely aggressive prostate cancers quickly and accurately from urine samples, even discriminating these against urine from patients that had other diseases of the prostate.
“This additional information could support the PSA (test) and would provide earlier, non-invasive, sensitive detection of clinically aggressive prostate cancers that would most benefit from early diagnosis, simply from a urine sample.
“This has enormous potential and in time the ability of the dogs’ nose could be translated to an electronic device.”
Dr Andreas Mershin, a physicist and research scientist at MIT, and study co-author, said a “machine nose” for prostate cancer should be “completely scalable to other diseases”.
He said: “Imagine a day when smartphones can send an alert for potentially being at risk for highly aggressive prostate cancer, years before a doctor notices a rise in PSA levels.
“The incredible work of these dogs is critical as we advance this programme to develop an improved method of early prostate cancer diagnosis.”
Jonathan Simons, PCF president and CEO, and study co-author, said the results “could now lead to the future development of a more sensitive and specific prostate cancer diagnostic beyond the current PSA test”.
He said larger scale studies are being planned to develop a “‘robotic nose’, if you will, that may ultimately take the form of a smartphone app of the future”.