A Smartphone Application Using Artificial Intelligence Is Superior To Subject Self-Reporting When Assessing Stool Form

Abstract

INTRODUCTION: Stool form assessment relies on subjective patient reports using the Bristol Stool Scale (BSS). In a novel smartphone application (app), trained artificial intelligence (AI) characterizes digital images of users' stool. In this study, we evaluate this AI for accuracy in assessing stool characteristics. METHODS:Subjects with diarrhea-predominant irritable bowel syndrome image-captured every stool for 2 weeks using the app, which assessed images for 5 visual characteristics (BSS, consistency, fragmentation, edge fuzziness, and volume). In the validation phase, using 2 expert gastroenterologists as a gold standard, sensitivity, specificity, accuracy, and diagnostic odds ratios of subject-reported vs AI-graded BSS scores were compared. In the implementation phase, agreements between AI-graded and subjectreported daily average BSS scores were determined, and subject BSS and AI stool characteristics scores were correlated with diarrhea-predominant irritable bowel syndrome symptom severity scores. RESULTS:In the validation phase (n 5 14), there was good agreement between the 2 experts and AI characterizations for BSS (intraclass correlation coefficients [ICC] 5 0.782-0.852), stool consistency (ICC 5 0.873-0.890), edge fuzziness (ICC 5 0.836-0.839), fragmentation (ICC 5 0.837-0.863), and volume (ICC 5 0.725-0.851). AI outperformed subjects' self-reports in categorizing daily average BSS scores as constipation, normal, or diarrhea. In the implementation phase (n 5 25), the agreement between AI and self-reported BSS scores was moderate (ICC 5 0.61). AI stool characterization also correlated better than subject reports with diarrhea severity scores. DISCUSSION:A novel smartphone application can determine BSS and other visual stool characteristics with high accuracy compared with the 2 expert gastroenterologists. Moreover, trained AI was superior to subject self-reporting of BSS. AI assessments could provide more objective outcome measures for stool characterization in gastroenterology.

Artificial Intelligence–Enabled Stool Analysis for Lactulose Titration Assistance in Hepatic Encephalopathy Through a Smartphone Application

“…Dieta is an AI-based smartphone application designed and previously validated for assessment of stool characteristics and BSS, through stool images (10). Subjects uploaded pictures of every BM throughout the study.…”

Artificial Intelligence Evaluation of Stool Quality Guides Management of Hepatic Encephalopathy Using a Smartphone App

“…Correlations between AI-BSS/self-BSS in both phases and lactulose dose changes were analyzed. Because this was a pilot and because of cognitive challenges in HE, we aim to enroll around double the 14 patients included in the Dieta IBS-related experience (5).…”

“…Because there is impaired insight in HE (3,4) and using Bristol Stool Scale (BSS) may improve outcomes, automated BSS calculation could be helpful (3). Dieta (https://dietahealth.com/, Figure 1a) is an application that uses artificial intelligence (AI) to define BSS and stool characteristics, which has been studied in irritable bowel syndrome (IBS) (5). The study aims to determine utility of the Dieta app to classify BSS (AI-BSS) vs self-assessment (self-BSS) in longitudinal experiences (6).…”

Picture Perfect: Artificial Intelligence in the Management of Hepatic Encephalopathy

“…Accurate determinations of bowel movement frequency and stool characteristics (Bristol Stool Scale, BSS) allow for medication titration and directly affect HE outcomes (5). However, patients struggle to appropriately assign a BSS to their stool (6), and sending stool photographs to their providers is not feasible and may be avoided to maintain modesty. AI has shown high clinical utility for stool assessments in patients with irritable bowel syndrome.…”