Farts Say More About Your Health Than You Think: Now Scientists Are Listening

Like David Ancal he opened video after video of diarrhea this year, it hit him—it’s not what he expected to do for his PhD.

Ancalle, a mechanical engineering student at Georgia Tech who researches fluid dynamics, is currently working to demystify the acoustics of urination, flatulence and diarrhea. His team is training artificial intelligence to recognize and analyze the sound of every bathroom phenomenon; in fact, research suggests that monitoring the flow of our excretions could benefit public health.

What’s new – Ancalle and Maia Gatlin, an aerospace engineer at the Georgia Tech Research Institute (GTRI), have created a mechanical device loaded with pumps, nozzles and tubes intended to recreate the physics — and sounds — of human bodily function. They called it the human synthetic acoustic reproduction testing machine (yes, SHART).

SHART is now preparing an AI algorithm to one day detect deadly diseases like cholera and stop an epidemic in its tracks, according to a presentation at the American Physical Society’s annual Fluid Dynamics conference last week. Ancalle and Gatlin’s findings have not yet been published in a peer-reviewed journal.

The SHART machine is helping researchers who hope to curb epidemics of gastrointestinal disease.GTR

Here is the background – Diarrheic diseases such as cholera kill 500,000 children a year, making them the third leading cause of infant mortality worldwide. “There is an outbreak and a resurgence in Haiti as we speak,” Gatlin says. Increasing disease detection would strengthen treatment and prevent outbreaks, she says.

Because matter – The goal is to combine the machine learning model with inexpensive sensors and deploy them in regions susceptible to diarrheal disease outbreaks. “And as we classify those events, we can start collecting that data,” Gatlin says. “You can say, ‘Hey, we’re seeing an outbreak of a lot of diarrhea.’ Then we can start diagnosing quickly what’s going on in an area.’”

What have they done – Until recently, Ancalle didn’t think much of diarrhea. “Our initial focus for that first year was really on flatulence and urination,” he says. He and his colleagues were trying to relate the sound of farts to the internal geometry of a rectum: Abnormal changes could mean cancer. “After discussions with gastroenterologists, we thought this would be a good way to try a noninvasive route.”

But the project soon expanded: Ancalle collaborated with GTRI researchers who were looking for ways to passively detect outbreaks of gastrointestinal disease. Perhaps, they wondered, next-generation toilets could do more than collect excrement: They could also help alert communities to an outbreak.

This sensor pack comes with a microphone and could help detect irregular “going out” in the bathroom.GTR

This is where acoustics come into play. Sound is easier to analyze remotely than video or self-report and is less invasive or cumbersome than a doctor visit. And the sounds of our exits – urination, flatulence, solid defecation and diarrhea – are distinct. The team realized that an inexpensive device and an AI algorithm could organize this information about the toilet.

They started by sorting the audio and video of publicly available excretions, capturing the frequency spectrum from each and feeding it to a machine learning algorithm. Their AI then learned from all that doodoo data until it was prepped for SHART machine testing.

The SHART machine is a couple of feet wide and has loads of nozzles and attachments. The team pumps water through the machine and records the sounds. They learned the physics behind the sound of each excretion and designed the device to simulate those same dynamics, tinkering with different wiring for each subsystem. “A lot of thought has gone into each of the sounds,” says Gatlin. “There was a subsystem for every sound on this little machine.”

“It actually performs quite well,” he continues. Their algorithm identified the correct “excretion event” up to 98 percent of the time, according to early data.

The team is also exploring the fundamental physics at play. In the conference presentation, Ancalle described how the team modeled the sound of male urination (streams that turn into droplets squirting in succession).

A mini-computer like the Raspberry Pi could power future fart-monitoring devices.pengpeng/iStock Unreleased/Getty Images

If the geometry of the urethra changes, the flow and sound also change. Now, Ancalle is working with urologists to use the same machine learning approach to detect irregular changes in urination and flatulence based on this idea.

“Self-reporting is not very reliable,” Ancalle says. “We’re trying to find a non-invasive way for people to be notified whether or not they should have a checkup. Like, ‘Hey, your urine isn’t flowing as fast as it should. Your farts don’t sound like they should. You should check it out.'” They propose that changes in the tract – from cancer or another condition – would manifest in these acoustics.

“It’s reasonable to assume that you can detect it with microphones,” says Jared Barber, an applied mathematician at Indiana University who chaired the session but isn’t involved in the research. Ancalle also worked on a female urination model, but only completed the male model in time for her presentation.

What’s next – The researchers are looking to expand their testing and eventually build a deployable device, which could include a tiny Raspberry Pi computer. Gatlin plans to pair this project with ongoing sustainable sanitation projects.

Barber notes that the work is very preliminary but was encouraged by the speech. “It looks like it could have a very big impact,” says Barber. “It all seems doable. They are using techniques that can provide hopeful capability for diagnosis.

It’s still early days, but the team is designing with the final product in mind. “We’re not trying to find million-dollar equipment,” Ancalle says. “We are trying to make this something that can be accessible to everyone, especially as the project focuses on urban areas with weak health systems. The economic aspect is very important to us.”

Leave a Comment

Your email address will not be published. Required fields are marked *