New AI listens to toilet sounds to detect diarrhea

December 27, 2022 — Artificial intelligence has taken another big step: discerning the sound of an unhealthy bowel movement.

A design for a “diarrhea detector” that could alert health officials to outbreaks like cholera was recently presented by engineers at the Georgia Tech Research Institute. One day, AI could even be used with home smart devices to monitor gut health.

A prototype accurately identified diarrhea 98% of the time when tested, engineers said at an Acoustical Society of America conference in Nashville. Even with background noise, it was correct 96% of the time.

Cholera infects millions of people each year, killing up to 143,000 who become dehydrated from severe diarrhea, according to the World Health Organization. Many deaths could be prevented with oral rehydration solution if the outbreak is detected quickly enough. Cholera can be fatal within 24 hours of the onset of symptoms.

The device could be installed in public restrooms where inadequate plumbing increases the risk of a cholera outbreak.

“Cholera usually has a more watery sound — it can sound a lot like urination, and it doesn’t have a lot of flatulence notes in general,” says project co-lead Maia Gatlin, an aerospace engineer and PhD student at the Georgia Tech Research Institute. “Whether someone has severe diarrhea and they have a lot of it – that can be captured.”

The idea grew out of conversations about how COVID-19 can be monitored by analyzing wastewater, says project co-lead Alexis Noel, PhD, a biomechanical engineering researcher at the institute.

Other researchers have considered video analysis to look for diarrhea.

“I was curious if we could detect diarrhea using sound,” says Noel, “because some people are a little wary of having a camera pointed at their butt in the toilet.”

First, the researchers collected 350 publicly available audio samples of bathroom sounds from YouTube and Soundsnap. Some clips had up to 10 hours of diarrhea sounds.

The researchers listened to the samples to establish their authenticity.

“We didn’t know these people, we didn’t know how they were recording, so we had to listen to quite a bit of it,” Gatlin says. “There were definitely a lot of fart noises where we were like, ‘That’s not a fart, that’s someone blowing his elbow. “”

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.