- Fecal Incontinence
|A Smartphone Application Using Artificial Intelligence Is Superior to Subject Self-Reporting When Assessing Stool Form
Am J Gastroenterol. 2022 Mar 14. doi: 10.14309/ajg.0000000000001723. Online ahead of print.
Mark Pimentel 1 2, Ruchi Mathur 1 3, Jiajing Wang 1, Christine Chang 1, Ava Hosseini 1, Alyson Fiorentino 1, Mohamad Rashid 1, Nipaporn Pichetshote 2, Benjamin Basseri 2, Leo Treyzon 2, Bianca Chang 2, Gabriela Leite 1, Walter Morales 1, Stacy Weitsman 1, Asaf Kraus 4, Ali Rezaie 1 2
1Medically Associated Science and Technology (MAST) Program, Cedars-Sinai, Los Angeles, California, USA.
2Karsh Division of Gastroenterology and Hepatology, Cedars-Sinai, Los Angeles, California, USA.
3Division of Endocrinology, Diabetes and Metabolism, Cedars-Sinai, Los Angeles, California, USA.
4Dieta Health, Oak Park, California, USA.
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. Here 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 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 subject-reported 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 validation-phase (n = 14), there was good agreement between 2 experts and AI characterizations for BSS (intraclass correlation coefficients [ICC] = 0.782-0.852), stool consistency (ICC = 0.873-0.890), edge fuzziness (ICC = 0.836-0.839), fragmentation (ICC = 0.837-0.863), and volume (ICC = 0.725-0.851). AI outperformed subjects' self-reports in categorizing daily average BSS scores as constipation, normal, or diarrhea. In implementation-phase (n = 25), agreement between AI and self-reported BSS scores was moderate (ICC = 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 to 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.