Maryland: Research has found that an artificial intelligence tool under development at Duke University can be added to standard toilets to help analyze patient stools and give gastroenterologists the information they need to provide a appropriate treatment. The research has been shortlisted for presentation at Digestive Disease Week (DDW) 2021. New technology could help manage chronic gastrointestinal issues such as inflammatory bowel disease (IBD) and irritable bowel syndrome (SCI).

“As a general rule, gastroenterologists should rely on patient self-reported information about their stool to help determine the cause of their gastrointestinal health issues, which can be very unreliable,” said Deborah Fisher, MD. , a lead author of the study and associate professor of medicine at Duke University Durham, North Carolina.

“Patients often don’t remember what their stool looks like or how often they have a bowel movement, which is part of the standard monitoring process. The Smart Toilet technology will allow us to collect the long-term information needed to make a and rapid diagnosis of chronic gastrointestinal problems. “

The technology can be retrofitted into the pipes of an existing toilet. After a person has a bowel movement and flushes the toilet, the toilet takes a picture of the stool in the pipes. The data collected over time will allow the gastroenterologist to better understand a patient’s stool shape (i.e., soft, normal, or constipated) and the presence of blood, allowing them to diagnose the patient. and provide the right treatment for his condition.

To develop the artificial intelligence image analysis 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 using the Bristol Stool Scale, a common clinical tool for classifying stool. Using an efficient computational approach to convolutional neural networks, which is a type of deep learning algorithm capable of analyzing images, the researchers found that the algorithm accurately classified stool 85.1% of the time. ; raw blood detection had an accuracy of 76.3%.

“We are optimistic about patients’ willingness to use this technology, as it is something that can be installed in their toilet pipes and does not require the patient to do anything other than flush the toilet.” said Sonia Grego, PhD, principal investigator of the study and founding director of the Duke Smart Toilet Lab.

“An IBD flare could be diagnosed using the smart toilet, and the patient’s response to treatment could be monitored using the technology. This could be particularly useful for patients who live in long-term care facilities and who may not be able to report their condition. and could help improve the initial diagnosis of acute conditions. “

The prototype has a promising feasibility, but it is not yet available to the public. Researchers are developing additional features of the technology to include sampling of stool samples for analysis of biochemical markers that will provide highly disease-specific data to meet the needs of patients and gastroenterologists.