That’s the vision of a team of researchers at the California Institute of Technology. Led by Nate Lewis, a chemist, the team is developing an e-nose that can sense chemical vapors. And Lewis’s grad student Heather McCraig thinks the technology will someday be small and affordable enough that a doctor can carry it around on her iPhone, and use it to perform instant diagnoses on her patients. “You wouldn’t need to send samples off to a lab, you would immediately be able to start treatment,” she explains near the end of this cool video from the American Chemical Society.
Just the idea that you can smell illness–never mind the part about doing it via a smart phone–might be new to some people. But of course, smell is just another form of chemical detection, and chemical detection is at the heart of many diagnostic tests. “You can learn a lot just by smelling your patients with the unaided nose,” one prominent physician has asserted, citing no less than Hippocrates as an antecedent in the diagnosis-via-nostril trend. (More history on breath analysis for medical diagnosis can be found here.)
In August, Courtney Humphries elucidated in TR how an electronic nose could essentially smell tuberculosis in a urine sample. The findings, from a team in New Delhi, India, were remarkable:
“The researchers collected urine samples from more than 100 newly diagnosed TB patients in New Delhi. They analyzed molecules from the urine that evaporate quickly in the air, called volatile organic compounds (VOCs), using gas chromatography and mass spectrometry, which give a detailed readout of chemical components and their concentrations. Using this method to hunt for patterns, they identified several VOCs that occurred in significantly different concentrations in infected individuals. Using this signature, they were able to predict TB infection in another group of patients with nearly 99 percent accuracy.”
A 2008 article in Chemical Review (PDF) actually gave an exhaustive analysis of the electronic nose (subtitle: “Current Status and Future Trends”). The article outlined various different approaches to e-sniffing (everything from gas chromatography to infrared spectrometry) and examined various applications of the technology beyond disease diagnosis (food and beverage analysis as well as environmental monitoring also get a look). “[T]he possibilities for the application of the electronic nose in the medical field are very diverse,” conclude the study authors, citing uremia, fungal respiratory disease, asthma, and even lung cancer as diseases that might be detectable by an e-nose.
So when might we see this thing in the wild? I wouldn’t hold your breath (so to speak). Although the Daily Mail and other outlets that suggest an affordable iPhone-sized e-nose might be coming someday “soon,” the researcher Humprhies spoke to was less optimistic. He told TR that it would actually be a “hugely complex job” to shrink the device and make it affordable.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
The walls are closing in on Clearview AI
The controversial face recognition company was just fined $10 million for scraping UK faces from the web. That might not be the end of it.
This horse-riding astronaut is a milestone in AI’s journey to make sense of the world
OpenAI’s latest picture-making AI is amazing—but raises questions about what we mean by intelligence.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.