A “smart toilet” in development uses artificial intelligence (AI) to scan stool for consistency and presence of blood – and early evidence suggests it is more accurate than patient self-reporting, a study reveals.
The remote, automated, real-time analysis and reporting increase the likelihood of physicians detecting gastrointestinal issues earlier, investigators reported.
In a proof-of-concept study, the smart toilet was 85% accurate in categorizing stool consistency as loose, normal, or constipated. The findings were presented at the annual Digestive Disease Week® (DDW).
“This study highlights a very innovative and practical tool that could have major implications for patients and clinicians alike,” Andrea Shin, MD, who was not affiliated with the research, said in an interview.
“Stool form or consistency and signs of bleeding are some of the most important pieces of clinical history when it comes to GI or bowel symptoms,” added Dr. Shin, assistant professor of medicine in the department of gastroenterology and hepatology at Indiana University, Indianapolis.
Image analysis
The researchers tested their AI algorithm on 3,328 images. They assessed photos from the Internet and some submitted anonymously by participants in the study.
Two gastroenterologists also rated a subset of 552 images. The physicians showed “satisfactory agreement” on interrater reliability (the extent to which two or more “raters” [for example, observers, examiners] agree), the investigators noted.
The smart toilet also was 76% accurate for gross blood detection.
“It’s objective and more accurate,” study author Sonia Grego, PhD, said in an interview. In contrast to asking patients to keep a bowel movement diary or recall the frequency and consistency of their stool over time, “the system does it for you,” she added.
“Our technology – by automating the image acquisition – removes the burden of having to track your pattern for weeks or months,” added Dr. Grego, founding director of the Duke Smart Toilet Lab at Duke University in Durham, N.C.
Information provided by patients “can have a big impact on decision-making,” Dr. Shin said. “For example, if I am talking to an individual who suffers from irritable bowel syndrome [IBS], I commonly ask them about how loose or watery and hard or formed their stool is, because this information gives me clues as to the underlying problems that may be driving their symptoms.”
Dr. Shin agreed it can be challenging for people to know what is important to report to their doctor. “This tool has the potential to relieve patient burden and facilitate communication between a patient and their clinician. It’s a great example of how technology can be leveraged to enhance care.”
Working behind the scenes
Together with gastroenterologist Deborah Anne Fisher, MD, an associate professor of medicine at Duke, Dr. Grego and colleagues devised a prototype that positions the image analyzer in the pipes behind the toilet. So the analysis is done post flush.
“We are experts of toilets and toilet technology,” Dr. Grego said. “We have learned that people really don’t like to see anything weird around the toilet bowl.”
The smart toilet system is designed for multiple users in a residential or commercial setting. The technology could be used in hospitals or long-term care facilities, for example. A fingerprint scanner on the flush mechanism tracks each individual user.
