Search

Irritable bowel syndrome (IBS) includes diarrhea-predominant (IBS-D) and constipation-predominant (IBS-C) subtypes. We combined breath testing and stool microbiome sequencing to identify potential microbial drivers of IBS subtypes.IBS-C and IBS-D subjects from 2 randomized controlled trials (NCT03763175 and NCT04557215) were included. Baseline breath carbon dioxide, hydrogen (H 2 ), methane (CH 4 ), and hydrogen sulfide (H 2 S) levels were measured by gas chromatography, and baseline stool microbiome composition was analyzed by 16S rRNA sequencing. Microbial metabolic pathways were analyzed using Kyoto Encyclopedia of Genes and Genomes collection databases.IBS-C subjects had higher breath CH 4 that correlated with higher gut microbial diversity and higher relative abundance (RA) of stool methanogens, predominantly Methanobrevibacter , as well as higher absolute abundance of Methanobrevibacter smithii in stool. IBS-D subjects had higher breath H 2 that correlated with lower microbial diversity and higher breath H 2 S that correlated with higher RA of H 2 S-producing bacteria, including Fusobacterium and Desulfovibrio spp. The predominant H 2 producers were different in these distinct microtypes, with higher RA of Ruminococcaceae and Christensenellaceae in IBS-C/CH 4 + (which correlated with Methanobacteriaceae RA) and higher Enterobacteriaceae RA in IBS-D. Finally, microbial metabolic pathway analysis revealed enrichment of Kyoto Encyclopedia of Genes and Genomes modules associated with methanogenesis and biosynthesis of methanogenesis cofactor F420 in IBS-C/CH 4 + subjects, whereas modules associated with H 2 S production, including sulfate reduction pathways, were enriched in IBS-D.Our findings identify distinct gut microtypes linked to breath gas patterns in IBS-C and IBS-D subjects, driven by methanogens such as M. smithii and H 2 S producers such as Fusobacterium and Desulfovibrio spp, respectively.

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.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 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.In the validation phase (n = 14), there was good agreement between the 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 the implementation phase (n = 25), the 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.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.