Training Machines to Smell Disease

Machines that can find volatile organic compounds in human breath—gas-chromatography mass-spectrometers—have been around for awhile. But analyzing them is arduous and error-prone; reams of data on complex compounds must be analyzed by hand.

To expedite the process, Loughborough University data scientists are training "deep learning networks"—a form of artificial intelligence technology inspired by the brain—to read the data and quickly identify the markers of disease in breath samples. 

The method could bring quick, non-invasive diagnostic tests, writes Andrea Soltoggio, a Loughborough researcher, and "has a great potential, but it could also prove controversial."

The Conversation via Smithsonian

Comments +


Post a Comment

Restricted HTML

  • Lines and paragraphs break automatically.
  • Web page addresses and email addresses turn into links automatically.
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Back to top