Breath Diagnosis May Become Possible When AI Crunches Data
Animals and even plants identify hundreds of different substances via smell. Humans, however, are handicapped and can’t smell most substances. Using AI, however, will change that.
Laboratories around the world can use machines called gas-chromatography mass-spectrometers or GC-MS, can analyze the air and find thousands of different molecules known as volatile organic compounds. These include chemical compounds in breath samples that may indicate disease.
Andrea Soltoggio, part of a data science team at Loughborough University in Scotland, recently wrote a story in Smithsonian Magazine describing how AI technology will help doctors to reach a medical diagnosis through smell.
Artificial intelligence (AI) is best known for its ability to see (as in driverless cars) and listen (as in Alexa and other home assistants). From now on, it may also smell. My colleagues and I are developing an AI system that can smell human breath and learn how to identify a range of illness-revealing substances that we might breathe out.
Mathematical models inspired by the brain, called deep learning networks, were specifically engineered to “read” the traces left by odors and conclude what diseases could be connected.
read more at smithsonianmag.com