Dogs Help Us Get One Step Closer Disease-Sniffing Device

Training dogs to detect prostate cancer gets one paw closer to a ‘robotic nose’ to diagnose the disease, including most lethal form.
By PCF Staff Writer, February 2021, Updated June 2021
prostate cancer sniffing dog
A study by Medical Detection Dogs, the Prostate Cancer Foundation, Massachusetts Institute of Technology, and Johns Hopkins University combined three current methods of diagnosing prostate cancer for the first time to detect the disease early. Larger-scale studies planned to develop a machine olfaction diagnostic tool – a ‘robotic nose’ – that may ultimately be a smartphone app of the future with prototype developed by MIT.

New research from a multi-national, cross-disciplinary team of scientists from Medical Detection Dogs (MDD) in the UK, the Prostate Cancer Foundation (PCF), Massachusetts Institute of Technology (MIT), Johns Hopkins University – and a friendly pair of specially trained cancer-sniffing dogs at MDD – has scientifically validated that a dog’s nose may hold the key to prostate cancer detection: a more accurate, non-invasive early diagnostic tool able to differentiate between potentially lethal high Gleason Grade cancers and low-grade, less dangerous cancers.

Observations dating back to the mid-2000s have shown that dogs can accurately sniff out early prostate and other cancers with impressive accuracy, but researchers have not known exactly what elements of scent the dogs were detecting and how they were processing the information. In a new paper published today in PLOS ONE, for the first time researchers combined three approaches – canine olfaction detection, artificial intelligence (AI)-assisted chemical analysis of the volatile organic compounds (VOCs) in urine samples, and microbial analysis of the same urine samples of men who underwent biopsy for suspected prostate cancer.

A four-year-old Labrador and a seven-year-old Vizsla were trained to detect the odor of prostate cancer in urine samples collected from patients with the disease, including Gleason 9 prostate cancer – the most lethal tumors that would benefit the most from early detection.

Results showed the dogs’ olfaction system was 71 percent sensitive – the rate at which the dogs correctly identified positive samples – and 70-76% specific – the rate at which the dogs correctly ignored negative samples including those with other diseases – when detecting Gleason 9 prostate cancer from blinded samples. The dogs also correctly identified when 73% of blinded patient samples did not have the disease. This compares favorably to the most commonly used prostate cancer test, the PSA blood test, and demonstrates how a new screening tool based on the dog’s nose could support the PSA test and improve early diagnosis, leading to better health outcomes and saving lives.

GET THE BARK NEWSLETTER IN YOUR INBOX!

Sign up and get the answers to your questions.

Email Address:

This is the first truly controlled study – both human researchers and dogs were double-blinded on which samples were from cancer patients versus otherwise healthy patients. The findings demonstrate that canines can be trained to detect the most aggressive and lethal form of prostate cancer from the VOCs.  While previous studies using analytical techniques such as Gas Chromatography-Mass Spectrometry (GC-MS) to identify individual molecules performed well under tightly controlled laboratory conditions, this new work takes into account the dynamically changing background odor environment of the real world. Identification of the molecules in the odor could lead to the development of an artificial dog nose that detects prostate cancer in urine in much the same way biosensing machines known as machine olfactors are beginning to learn from the way trained dogs sniff out drugs and explosives, which also have unique molecular odorant signatures.

Dr. Claire Guest, Co-Founder and Chief Scientific Officer of Medical Detection Dogs and lead study author, 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 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.”

“One of the main points of this work is that the dogs aren’t just detecting prostate cancer, they are detecting the most lethal prostate cancers – those that would benefit the most from early detection. Results could now lead to the future development of a more sensitive and specific prostate cancer diagnostic beyond the current PSA test,” said Jonathan W. Simons, MD, PCF president and CEO, and study co-author. “With compelling evidence of this approach, we are planning larger-scale studies using canine olfaction, urinary VOCs and urinary microbiota profiling to develop a machine olfaction diagnostic tool, a ‘robotic nose’ if you will, that may ultimately take the form of a smartphone app of the future.”

“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 program to develop an improved method of early prostate cancer diagnosis. Equally important is that men can be citizen scientists and contribute to the bio bank that will help us eventually solve this problem that is urgently needed. Once we have built the machine nose for prostate cancer, it will be completely scalable to other diseases,” added Dr. Andreas Mershin, physicist and research scientist, The Center for Bits and Atoms, Massachusetts Institute of Technology, and study co-author.

Photo credit: MDD/Neil Pollock pcf.org