Smart Model to Distinguish Crohn’s Disease from Ulcerative Colitis

Carboxymethyl Chitosan Oligosaccharide Holds Promise for Treatment of Stenosis Crohn's Disease

Crohn's disease (CD) is a chronic intestinal disturbance mediated by mucosal immune hyperactivity that is often associated with the formation of stenosis. No reliable solution to stenosis CD exists so far. Therefore, we generated carboxymethyl chitosan oligosaccharide (CMCOS) as a new promising therapy and investigate its efficacy in an improved rat CD model. CMCOS was synthesized by enzymatic hydrolysis, and its biosafety was evaluated in vivo. The rat model of stenosis CD was optimized by an orthogonal experiment of 75 or 100 mg/kg trinitrobenzenesulfonic acid (TNBS) in a 50 or 75% ethanol enema. The therapeutic efficacy of CMCOS on the rat model of stenosis CD was investigated and compared with the commercial drug 5-aminosalicylic acid over a 28 day period of disease progression. The rat model of stenosis CD was well established by intracolonic administration of 75 mg/kg TNBS in 75% ethanol. CMCOS significantly alleviated CD symptoms morphologically, hematologically, and pathologically, promoting functional recovery of intestinal epithelium in a dose-dependent manner. CMCOS reduced infiltrations of inflammatory cells by regulating the IL-17A/PPAR-γ pathway and reduced fibro-proliferation and fibro-degeneration of the colon tissue by downregulating the TGF-β1/WT1 pathway. 75 mg/kg TNBS in a 75% ethanol enema induces a rat model of stenosis CD suitable for preclinical pathology and pharmacological studies. The safety, antifibrosis, and functional repair performance of CMCOS make it a promising candidate for the treatment of stenosis CD.

Gut microbiome-based supervised machine learning for clinical diagnosis of inflammatory bowel diseases

Despite the availability of various diagnostic tests for inflammatory bowel diseases (IBD), misdiagnosis of IBD occurs frequently, and thus, there is a clinical need to further improve the diagnosis of IBD. As gut dysbiosis is reported in patients with IBD, we hypothesized that supervised machine learning (ML) could be used to analyze gut microbiome data for predictive diagnostics of IBD. To test our hypothesis, fecal 16S metagenomic data of 729 subjects with IBD and 700 subjects without IBD from the American Gut Project were analyzed using five different ML algorithms. Fifty differential bacterial taxa were identified [linear discriminant analysis effect size (LEfSe): linear discriminant analysis (LDA) score > 3] between the IBD and non-IBD groups, and ML classifications trained with these taxonomic features using random forest (RF) achieved a testing area under the receiver operating characteristic curves (AUC) of ∼0.80. Next, we tested if operational taxonomic units (OTUs), instead of bacterial taxa, could be used as ML features for diagnostic classification of IBD. Top 500 high-variance OTUs were used for ML training, and an improved testing AUC of ∼0.82 (RF) was achieved. Lastly, we tested if supervised ML could be used for differentiating Crohn's disease (CD) and ulcerative colitis (UC). Using 331 CD and 141 UC samples, 117 differential bacterial taxa (LEfSe: LDA score > 3) were identified, and the RF model trained with differential taxonomic features or high-variance OTU features achieved a testing AUC > 0.90. In summary, our study demonstrates the promising potential of artificial intelligence via supervised ML modeling for predictive diagnostics of IBD using gut microbiome data.NEW & NOTEWORTHY Our study demonstrates the promising potential of artificial intelligence via supervised machine learning modeling for predictive diagnostics of different types of inflammatory bowel diseases using fecal gut microbiome data.