AI could soon be able to smell if you have cancer
Posted: 2 May 2017 | By Michael Garwood
Back in 2011, British newspaper the Daily Mail ran an article appearing to prove the dogs were able to be trained to smell whether a person had lung cancer. An article last month even claimed German Shepherds could sniff out women with breast cancer just by smelling their bandages.
The article, which was also published and debated on the NHS website, stated that a persons sent was altered in the event of illness or disease becoming present in the body.
In an article published in the New York Times, author Kate Murphy stated that as humans, we each carry a unique “odorprint” made up of thousands of organic compounds, capable of revealing who we are, our age, genetics, lifestyle, hometown and even our metabolic processes that underlie our health.
Fast forward to today, this theory is being pursued further, but not with or four legged friends, but through a UK (Cambridge) based technology firm called Owlstone who has raised more than $23.5 million to put its odor analysis technology into the hands of clinicians.
“You’re seeing a convergence of technology now, so we can actually run large-scale clinical studies to get the data to prove odor analysis has real utility,” Billy Boyle, co-founder and president of operations at Owlstone told the New York Times.
Boyle co-founded the company with two friends back in 2004 to develop sensors capable of detecting chemical weapons and explosives, building an impressive client line-up, including the United States government.
However, it was in 2012 when personal tragedy changed the direction of the company, with Mr. Boyle’s girlfriend and eventual wife, Kate Gross, was diagnosed with colon cancer in 2012, sadly passing two years later.
My Boyle promptly turned his attentions to developing and building medical sensors, with an emphasis on cancer detection, in belief that his beloved may still be alive today, if her illness has been detected sooner.
To quote the article, the sensor is a silicon chip stacked with various metal layers and tiny gold electrodes. While it looks like your mobile phone’s SIM card, it works like a chemical filter using.
The molecules in an odor sample are first ionized — given a charge — and then an electric current is used to move only chemicals of diagnostic interest through the channels etched in the chip, where they can be detected using AI.
“You can program what you want to sniff out just by changing the software,” Mr. Boyle said. “We can use the device for our own trials on colorectal cancer, but it can also be used by our partners to look for other things, like irritable bowel disease.”
Britain’s National Health Service has already shown great interest in the technology, and is currently funding a 3,000-subject clinical trial to test Owlstone’s sensor to diagnose lung cancer.
The company also is conducting a 1,400-subject trial, in collaboration with the University of Warwick, to detect colon cancer from urine samples, and is exploring whether its chips can help determine the best drugs for asthma patients by sorting through molecules in their breath.