A developing artificial intelligence tool at Duke University can be added to the standard toilet to help analyze patients’ stools and provide gastroenterologists with the information they need to provide the right treatment, according to a research that was selected. to present it at Digestive Disease Week (DDW) 2021 New technology can help manage chronic gastrointestinal problems such as inflammatory bowel disease (IBD) and irritable bowel syndrome (IBS).
“Typically, gastroenterologists should rely on patients’ self-reported information about their stools to help determine the cause of their gastrointestinal health problems, which can be very unreliable, ”said Deborah Fisher, MD, one of the authors main study and associated. professor of medicine at Duke University in Durham, North Carolina. “Patients often do not remember the appearance of their stools or how often they have a bowel movement, which is part of the standard control process. Smart toilet technology will allow us to gather the long-term information needed to obtain a more accurate information and timely diagnosis of chronic gastrointestinal problems “.
The technology can be adapted to the pipes of an existing toilet. Once a person has a bowel movement and washes, the toilet will take a picture of the stool inside the pipes. Data collected over time will provide the gastroenterologist with a better understanding of the patient’s form of feces (i.e., loose, normal, or constricted) and the presence of blood, which will allow him to diagnose the patient and provide appropriate treatment. for their condition.
To develop the artificial intelligence imaging tool for the smart toilet, the researchers analyzed 3,328 unique stool images found online or provided by research participants. All images were reviewed and annotated by gastroenterologists according to the Bristol Stool Scale, a common clinical tool for classifying feces. Using a computationally efficient approach to convolutional neural networks, which is a type of deep learning algorithm that can analyze images, the researchers found that the algorithm accurately classified feces at 85.1 percent of the time; the detection of raw blood had an accuracy of 76.3%.
“We are optimistic about patients’ willingness to use this technology because it can be installed on their own toiletand it doesn’t require the patient to do anything that isn’t washed, “said Sonia Grego, Ph.D., the study’s lead researcher and founding director of the Duke Smart Toilet Lab.” be diagnosed using the Smart Toilet and the patient’s response to treatment with technology can be monitored. This can be especially helpful for patients living in long-term care settings who may not be able to report their conditions and may help improve the initial diagnosis of acute conditions. “
The prototype has promising viability, but is not yet available to the public. Researchers are developing additional features of the technology to include the sampling of stool samples for the analysis of biochemical markers that will provide very specific disease data to satisfy patientsneeds of gastroenterologists and.
Dr. Fisher will present data from the study, “Automated Analysis of Stool Images by Artificial Intelligence in a Smart Toilet,” summary Sa652, on Saturday, May 22 at 12:15 pm EDT.
Provided for the week of digestive diseases
Citation: Smart toilet can soon analyze feces for health problems (2021, May 22) recovered on May 22, 2021 at https://medicalxpress.com/news/2021-05-smart-toilet-stool -health-problems.html
This document is subject to copyright. Apart from any fair treatment for the purposes of private study or research, no part may be reproduced without written permission. Content is provided for informational purposes only.