The prostate cancer it is the second type of cancer that causes more deaths in men in the first world. Today, as a prevention activity, population screening with serum antigen (PSA) is used for the detection of this cancer, in order to improve its prognosis and avoid premature mortality. Nevertheless, experts in the field say that PSA tests often fail in their diagnoses, therefore a more precise and faster detection is necessary. And this is where the smell of dogs would come into play.
Canine smell, according to the research being carried out -the latest one is entitled “Feasibility of integrating canine olfaction with chemical and microbial profiling of urine to detect lethal prostate cancer”, it could be a potential method to improve the diagnosis of prostate cancer and this has been given importance over the last three decades. Dogs specifically trained for such detection may be able to discriminate the scent of various human diseases, including a wide number of cancers. In addition, there have also been published cases of dogs that, without training, have spontaneously shown interest in some part of the body of a family member, turning out to be cancer patients. All these discoveries support the hypothesis of a latest study that olfactory cancer detection is the key to developing an effective, rapid and non-invasive method.
Nevertheless, dogs themselves are not very practical diagnostic sensors to have in a hospital, nor are they capable of accumulating data or expanding their operating system. An olfactory machine that simulates the brain of animals would be. Hence, the experts are working on the association of the olfactory capacity of dogs to make it a fundamental piece for the development of an artificial neural network (ANN) that would allow the data obtained with the current PSA tests to be compared and to detect cancers early. more aggressive and lethal.
The purpose of this double-blind project was the detection of volatile organic compounds (VOCs) present in urine samples provided by sick patients. In this way, the same samples were analyzed –or sniffed– on the one hand, by the dogs, Florin and Midas, which they obtained 73.1% correct answers, and on the other, by scientists who used by chemical and microbial methods. In addition, the diagnostics were used as a tool for the future creation of an ANN that simulates the neural complexes of animals and is machine learning.
Although the results show the canine ability to discriminate, learn and improve detection, experts say the challenge remains how to transfer canine intelligence to a machine.
Eddie is an Australian news reporter with over 9 years in the industry and has published on Forbes and tech crunch.