Why Scientists Created a ‘Smart Toilet’ That Recognizes Your Butt
The bidet-like suite of devices detects abnormalities in feces that could flag signs of certain cancers
The future of medicine might start in the bathroom—and Stanford radiologist Sanjiv “Sam” Gambhir and his lab is leading the way. The team has developed and tested a “smart toilet” that analyzes the users’ urine and feces to monitor for abnormalities that could signal certain diseases, infections or even certain cancers, such as colorectal or urologic cancers.
And to match your poo with you, it scans, not your fingerprint, but your “anal print.”
“We know it seems weird, but as it turns out, your anal print is unique,” said Gambhir, senior author of a new study published Monday in Nature Biomedical Engineering, in a press release.
If the idea of having your behind scanned makes you uneasy, the researchers assure that the tech is only used as a tool to match users to their data. According to a Stanford press release, “no one, not you or your doctor, will see the scans.”
The “smart toilet” is actually an assortment of gadgets that researchers attached to a normal toilet to record different metrics. For instance, the contraption uses motion sensors to record urination duration and pressure sensors to measure how long the users takes to do their business, reports Caroline Dilbert for Popular Mechanics. These sorts of measurements can help indicate illnesses like chronic constipation or irritable bowel syndrome. For those who pee standing up, dual high-speed cameras will also measure the velocity, flow and duration of their urine stream, reports Ross Pomeroy at Real Clear Science.
“It’s sort of like buying a bidet add-on that can be mounted right into your existing toilet,” Gambhir says in a statement. “And like a bidet, it has little extensions that carry out different purposes.”
Currently, the toilet can test for up to ten different biomarkers from analyses of stool and urine samples, according to a Stanford press release. To do this, the toilet deploys “urinalysis strips,” or dipstick tests, that can measure white cell blood content, protein levels, and presence of blood. Fluctuation in these biomarkers sometimes indicate infection, kidney failure and some forms of cancer.
Patients with irritable bowel syndrome, prostate cancer, kidney failure and other conditions could benefit from the personalized data collection to monitor their health, the team suggests. Real Clear Science reports, the researchers hope that medical providers could use the toilet’s data to help flag signs of disease.
The toilet automatically sends data to a cloud-based storage system, reports Aaron Holmes for Business Insider. It can use algorithms to identify abnormalities in fecal matter and urine samples.
“Our concept dates back well over 15 years,” Gambhir said in the press release. “When I’d bring it up, people would sort of laugh because it seemed like an interesting idea, but also a bit odd.”
This project is one of the latest examples of researchers using artificial intelligence, or A.I., to generate diagnoses—a trend in the medical industry, as Jeremy Hsu reported for Undark last year. As the use of A.I. and data-gathering wearable technologies proliferates, the question of how to protect user’s data in accordance with HIPAA has become more fraught, as Megan Molteni reported for Wired last year. Gambhir emphasizes that all data will be secure and de-identified when it is uploaded to the cloud, in accordance with the Health Insurance Portability and Accountability Act (HIPAA).
“We have taken rigorous steps to ensure that all the information is de-identified when it’s sent to the cloud and that the information — when sent to health care providers — is protected under HIPAA,” Gambhir says in a statement.
But the device isn’t perfect: its results aren’t accurate enough for daily use and too cost-prohibitive for commercialization—for now, reports Real Clear Science. In any case, a smart toilet is certainly a consistent data source.
“The smart toilet is the perfect way to harness a source of data that’s typically ignored,” he says. “And the user doesn’t have to do anything differently.”