New test can diagnose cancer and other diseases by "smelling" your breath

An “artificially intelligent nanoarray” can offer a fast and inexpensive diagnosis of 17 diseases, by identifying their unique chemical signatures in your breath.
An international team of researchers led by Professor Hossam Haick of the Technion-Israel Institute of Technology has proven an ancient hypothesis that certain diseases can be detected through a patient’s breath, which could lead to a future of quick and non-invasive tests for early detection of those diseases.
The team’s research, which was published in the journal ACS Nano, used breath samples collected from 1404 subjects, each of which were previously diagnosed as having one of 17 different disease conditions, and used “an artificially intelligent nanoarray based on molecularly modified gold nanoparticles and a random network of single-walled carbon nanotubes” to detect and quantify chemical compounds in the samples.
Although the system isn’t quite ready for use in diagnosis by the wider medical community, according to Technion, the team’s work has been able to detect and classify various diseases “with an average accuracy of 86%.”
The study used breath samples from patients with lung cancer, colorectal cancer, head and neck cancer, ovarian cancer, bladder cancer, prostate cancer, kidney cancer, stomach cancer, Crohn’s disease, ulcerative colitis, irritable bowel syndrome, Parkinson’s disease (two types), multiple sclerosis, pulmonary hypertension, preeclampsia and chronic kidney disease. An analysis using the artificially intelligent nanoarray showed that “each disease has its own unique breathprint,” and the presence of one disease “would not screen out others.” According to the published findings, the team found that “13 exhaled chemical species, called volatile organic compounds, are associated with certain diseases, and the composition of this assembly of volatile organic compounds differs from one disease to another.”
 
You can read the full story on Treehugger by clicking here