'Smart Toilet' Uses AI to Monitor GI Health
- By John K. Waters
Researchers at Duke University have developed an artificial intelligence (AI) tool that can be installed in the pipes of a standard toilet to provide information gastroenterologists use to determine appropriate treatment for such chronic illnesses as inflammatory bowel disease (IBD) and irritable bowel syndrome (IBS).
The tool captures images of material passing through the pipes after the toilet is flushed, and those images are analyzed using a convolutional neural network (CNN), a deep learning (DL) algorithm designed for working with two- and three-dimensional image data. The network was trained with 3,328 "unique stool images" found online or provided by research participants. All images were reviewed and annotated by human gastroenterologists using the Bristol Stool Scale, a common clinical classification tool.
According to the researchers, the algorithm accurately classified the stool form 85 percent of the time and gross blood detection was accurate in 76 percent of the images.
The work is being done by Duke University’s Center for Water, Sanitation, Hygiene, and Infectious Disease (WaSH-AID), and was presented at the recent Digestive Disease Week 2021 online conference ("Automated Stool Image Analysis by Artificial Intelligence in a Smart Toilet") by Deborah Fisher, MD, associate professor of medicine at Duke University, and one of the lead authors of the study.
The so-called smart-toilet technology could provide physicians to gather the long-term information needed to make a more accurate and timely diagnosis of chronic gastrointestinal problems—things the response of IBD to drugs and/or diet treatments.
WaSH-AID is a collaborative research team working with academic, non-profit, and private industry partners around the world "to facilitate the development and sustainable deployment of novel technology-based solutions for critical health and environmental challenges."
The value of human waste as a diagnostic resource can hardly be overstated. Last year, researchers at Yale University conducted a longitudinal wastewater analysis to track SARS-CoV-2 dynamics at a major urban wastewater treatment facility in Massachusetts. Concentrations of infectious viral particles known as "viral titers" in the wastewater increased exponentially from mid-March to mid-April, they found, after which they began to decline. Viral titers in wastewater correlated with clinically diagnosed new COVID-19 cases, with the trends appearing 4-10 days earlier in wastewater than in clinical data.
In a paper presenting their findings ("SARS-CoV-2 titers in wastewater foreshadow dynamics and clinical presentation of new COVID-19 cases"), the Yale researchers concluded, "This work suggests that longitudinal wastewater analysis can be used to identify trends in disease transmission in advance of clinical case reporting and may shed light on infection characteristics that are difficult to capture in clinical investigations, such as early viral shedding dynamics."
The AI tech being developed at Duke holds great promise for early diagnosis of gastrointestinal (GI) disease, said Sonia Grego, founding director of the Duke Smart Toilet Lab and a lead researcher on the study, in an interview, though it's not yet available to the public. The researchers are developing additional features of the technology to include stool specimen sampling for biochemical marker analysis, Grego said.
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at email@example.com.