Sniffing the breath of a patient is nothing new for doctors. It was a well used, and recommended, practice. In the Middle Ages it was believed that a bad smell was the indication of a diseases and "medicus" used some nice smelling perfume to fight the bad smell and avoid contagium.
In much more recent times doctors have learnt the association of some odours to a specific disease and just few years ago, in 2014, researchers were able to associate a form of cancer to a specific smell and looked into the use of electronic noses to detect them.
Now an international team of scientists have run an experiment on 1404 people some of them healthy, others with diseases and have been able to detect the specific disease by analysing their breath using a nano-array sensor and artificial intelligence to interpret the data.
The "sniffing" was able to diagnose 17 different diseases. Our breath contains over hundred types of molecules and some of these may be related to a specific clinical condition. Work so far has allowed the development of breath analyser to detect a specific medical condition, like diabetes, whilst here the researchers, by applying artificial intelligence to the data have been able to detect with a single nano-array several diseases.
The nano-array consists of an organic layer that is capturing the molecules present in the breath, this is actually the sensing layer, and of several resistive layers containing nanoparticles of gold and single wall carbon nanotubes. These layers change their resistivity depending on the molecules trapped by the organic layer and these changes are interpreted by an artificial intelligent analyses to detect a specific disease.
Specifically, the nano-array has been able to detect the following 17 diseases:
Lung cancer, colorectal cancer, head and neck cancer, ovarian cancer, bladder cancer, prostate cancer, kidney cancer, gastric cancer, Crohn’s disease, ulcerative colitis, irritable bowel syndrome, idiopathic Parkinson’s, atypical Parkinsonism, multiple sclerosis, pulmonary arterial hypertension, pre-eclampsia, and chronic kidney disease.