DDW: AI Outperforms Patients in Characterizing Stool Samples

TUESDAY, May 31, 2022 (HealthDay News) -- A novel smartphone application can accurately determine Bristol Stool Scale (BSS) and other visual stool characteristics, according to a study recently published in the American Journal of Gastroenterology and presented at the 2022 Digestive Disease Week, held from May 21 to 24 in San Diego.

Mark Pimentel, M.D., from Cedars-Sinai in Los Angeles, and colleagues evaluated the accuracy of a novel smartphone application that uses trained artificial intelligence to assess stool characteristics.

The researchers found that in the validation phase, there was good agreement between two experts and AI characterizations for BSS, stool consistency, edge fuzziness, fragmentation, and volume. Compared with self-reports from study participants with diarrhea-predominant irritable bowel syndrome, AI outperformed for categorizing daily average BSS scores as constipation, normal, or diarrhea. Agreement between AI and self-reported BSS scores in the implementation phase was moderate. For diarrhea severity scores, AI stool characterization was found to correlate better than participant reports.

"The artificial intelligence tool removes the subjective description that can be part of a patient's description of their bowel specimens," a coauthor said in a statement. "In addition to improving a physician's ability to assess their patients' digestive health, this app could be advantageous for clinical trials by reducing the variability of stool outcome measures."

One author is an employee and board member of Dieta Health.

Abstract/Full Text (subscription or payment may be required)

More Information