Breathe, scout. There are regarding ten Franco-Belgian researchers and companies working, for a few years now, on le projet Pathacova machine for detecting the bronchopulmonary cancer thanks to the volatile organic compounds present in the breath. If it is not yet fully developed, this electronic nose promises to save precious time in the early detection of this pathology.
Everyone has had the bitter experience of guessing what a person might have eaten or drunk just by smelling their breath, especially when it comes to garlic or alcohol. However, diagnosing a disease in your interlocutor in this way is another matter, even if the principle remains the same: detect and analyze the volatile organic compounds (VOCs) specific to such food, such drink or such disease. The exercise is not impossible, but not with a human nose. On the other hand, dogs are already succeeding, especially for breast cancer through the project KDOG of the Curie Institute. “I can’t see myself setting up a kennel within the CHU or putting a dog in each GP cabinet”, jokes Professor Arnaud Scherpereel, head of the thoracic pulmonology-oncology department at the Lille University Hospital.
A machine that works like a biological nose
Hence the idea of developing a machine capable of doing the dog’s job of detecting CoVs specific to lung cancer. “The Covs in the organs change when they become cancerous and thus have their own molecular signature”, explains Professor Régis Matran, pulmonologist at the Lille University Hospital. “We collected samples from 500 sick or healthy patients in order to build up a dataset that is a real gold mine,” he continues. This data set will be used to teach the artificial intelligence of the machine to detect and identify the fingerprint of a sick person from a healthy person.
This “sorting” will be the task of several miniaturized gas sensors designed by Doctor Driss Lahem of the company Materia Nova. The module containing the sensors is integrated into the “electronic nose”. “As a whole, the machine works exactly like a biological nose whose receptors transmit information via neurons to the brain”, specifies Justin Martin, the doctoral student from the University of Liège who developed the first prototype. The impression, generated by the “nose” algorithm from the Covs, is sent to the attending physician, who, by including the patient’s data, will be able to arrive at an interpretation.
Researchers still lack sufficient data to make their “nose” work optimally, acknowledges Justin Martin. A lack that should soon be filled by clinical tests on sick patients. The machine itself must also be streamlined to easily integrate GP surgeries. “The goal is to make it a non-invasive, accessible and inexpensive diagnostic tool, upstream of screening by chest scanner”, insists Professor Scherpereel. The stakes are high in terms of public health. Detected early, lung cancer can be treated curatively, offering a life expectancy of 90% at 5 years, compared to 20% over the same period for cancer that has entered the metastatic phase.