The Common and Unique Pattern of Microbiome Profiles among Saliva, Tissue, and Stool Samples in Patients with Crohn’s Disease

A Machine Learning-Based Diagnostic Model for Crohn's Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis

Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn's disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.

Characteristics of intestinal microbiota in children with idiopathic short stature: a cross-sectional study

Idiopathic short stature (ISS) accounts for more than 70% of childhood short stature cases, with an undefined etiology and pathogenesis, leading to limited treatment. However, recent studies have shown that intestinal microbiota may be associated with ISS. This study aimed to characterize the intestinal microbiota in children with ISS, effect of treatment with growth hormones, and association between specific bacterial species and ISS. This study enrolled 55 children, comprising 40 diagnosed with ISS at Jinhua Hospital, Zhejiang University, and 15 healthy controls. The subjects with ISS were divided into the untreated ISS group (UISS group, 22 children who had not been treated with recombinant human growth hormone [rhGH]), treated ISS group (TISS group, 18 children treated with rhGH for 1 year), and control group (NC group, 15 healthy children). High-throughput sequencing was used to determine the intestinal microbiota characteristics. Higher abundances of Bacteroides, Prevotella, Alistipes, Parabacteroides, Agathobacter and Roseburia were found in the UISS and TISS groups than in the control group, whereas Bifidobacterium, Subdoligranulum, and Romboutsia were less abundant. The composition of intestinal microbiota in the UISS and TISS groups was almost identical, except for Prevotella. The TISS group had significantly lower levels of Prevotella than did the UISS group, which were closer to those of the NC group. Receiver operating characteristic curve analysis revealed that the abundances of Prevotella, Bifidobacterium, Bacteroides, and Subdoligranulum were effective in differentiating between the UISS and NC groups.

CONCLUSION

Alterations in intestinal microbiota may be associated with ISS. Specific bacterial species, such as Prevotella, may be potential diagnostic markers for ISS.

WHAT IS KNOWN

• ISS is associated with the GH-IGF-1 axis. • Recent studies indicated an association between the GH-IGF-1 axis and intestinal microbiota.

WHAT IS NEW

• Children with ISS showed alterations in intestinal microbiota, with a relative increase in the abundance of gut inflammation-related bacteria. • The relative abundances of Prevotella, Bacteroides, Bifidobacterium, and Subdoligranulum may serve as potential diagnostic markers.

Potential Oral Microbial Markers for Differential Diagnosis of Crohn's Disease and Ulcerative Colitis Using Machine Learning Models

Although gut microbiome dysbiosis has been associated with inflammatory bowel disease (IBD), the relationship between the oral microbiota and IBD remains poorly understood. This study aimed to identify unique microbiome patterns in saliva from IBD patients and explore potential oral microbial markers for differentiating Crohn's disease (CD) and ulcerative colitis (UC). A prospective cohort study recruited IBD patients (UC: n = 175, CD: n = 127) and healthy controls (HC: n = 100) to analyze their oral microbiota using 16S rRNA gene sequencing. Machine learning models (sparse partial least squares discriminant analysis (sPLS-DA)) were trained with the sequencing data to classify CD and UC. Taxonomic classification resulted in 4041 phylotypes using Kraken2 and the SILVA reference database. After quality filtering, 398 samples (UC: n = 175, CD: n = 124, HC: n = 99) and 2711 phylotypes were included. Alpha diversity analysis revealed significantly reduced richness in the microbiome of IBD patients compared to healthy controls. The sPLS-DA model achieved high accuracy (mean accuracy: 0.908, and AUC: 0.966) in distinguishing IBD vs. HC, as well as good accuracy (0.846) and AUC (0.923) in differentiating CD vs. UC. These findings highlight distinct oral microbiome patterns in IBD and provide insights into potential diagnostic markers.

Viable Mycobacterium avium subsp. paratuberculosis Colonizes Peripheral Blood of Inflammatory Bowel Disease Patients

Pathobionts, particularly Mycobacterium avium subsp. paratuberculosis (MAP) and Escherichia coli isolates with adherence/invasive ability (AIEC) have been associated with inflammatory bowel disease (IBD), particularly Crohn's disease (CD). This study aimed to evaluate the frequency of viable MAP and AIEC in a cohort of IBD patients. As such, MAP and E. coli cultures were established from faecal and blood samples (with a total n = 62 for each) of patients with CD (n = 18), ulcerative colitis (UC, n = 15), or liver cirrhosis (n = 7), as well as from healthy controls (HC, n = 22). Presumptive positive cultures were tested by polymerase chain reaction (PCR), for a positive confirmation of MAP or E. coli identity. E. coli-confirmed isolates were then tested for AIEC identity using adherence and invasion assays in the epithelial cell line of Caco-2 and survival and replication assays in the macrophage cell line of J774. MAP sub-culture and genome sequencing were also performed. MAP was more frequently cultured from the blood and faecal samples of patients with CD and cirrhosis. E. coli presumptive colonies were isolated from the faecal samples of most individuals, in contrast to what was registered for the blood samples. Additionally, from the confirmed E. coli isolates, only three had an AIEC-like phenotype (i.e., one CD patient and two UC patients). This study confirmed the association between MAP and CD; however, it did not find a strong association between the presence of AIEC and CD. It may be hypothesized that the presence of viable MAP in the bloodstream of CD patients contributes to disease reactivation.