Search

Background: Whether machine learning (ML) can assist in the diagnosis of Crohn's disease (CD) and intestinal tuberculosis (ITB) remains to be explored. Methods: We collected clinical data from 241 patients, and 51 parameters were included. Six ML methods were tested, including logistic regression, decision tree, k-nearest neighbor, multinomial NB, multilayer perceptron, and XGBoost. SHAP and LIME were subsequently introduced as interpretability methods. The ML model was tested in a real-world clinical practice and compared with a multidisciplinary team (MDT) meeting. Results: XGBoost displays the best performance among the six ML models. The diagnostic AUROC and the accuracy of XGBoost were 0.946 and 0.884, respectively. The top three clinical features affecting our ML model's result prediction were T-spot, pulmonary tuberculosis, and onset age. The ML model's accuracy, sensitivity, and specificity in clinical practice were 0.860, 0.833, and 0.871, respectively. The agreement rate and kappa coefficient of the ML and MDT methods were 90.7% and 0.780, respectively (P< 0.001). Conclusion: We developed an ML model based on XGBoost. The ML model could provide effective and efficient differential diagnoses of ITB and CD with diagnostic bases. The ML model performs well in real-world clinical practice, and the agreement between the ML model and MDT is strong. [ABSTRACT FROM AUTHOR]

Objectives: Cag A+Helicobacter pylori chronic infection cause malignant transformation of the human gastric mucosa. N6-methyladenosine (m6A) modifications are the most common and abundant mRNA modifications and one of the pathways affecting tumorigenicity and tumor progression. However, the role of m6A modification in the process of chronic H. pylori infection leading to malignant transformation of gastric mucosa is unclear. Methods: In this study, we used Cag A− and Cag A+H. pylori chronic infection to establish cellular models in GES-1 cells and analyzed the cellular morphology, proliferation, apoptosis, invasiveness and tumorigenicity of gastric mucosal epithelial cells. The m6A expression levels of GES-1 cells after chronic infection with Cag A− and Cag A+H. pylori were examined, and modifying effect of FTO (the fat mass and obesity-associated protein) on CD44 was verified by MeRIP–qPCR. Finally, the FTO expression changes and m6A expression levels were further validated in clinical gastric cancer tissues. Results: Chronic Cag A+H. pylori-infected GES-1 cells exhibit altered cell morphology, apoptosis inhibition, abnormal proliferation, enhanced migration, colony formation, and increased stem cell-like properties. Meanwhile, FTO and CD44 expression was enhanced, and FTO may induce malignant transformation of gastric mucosa by regulating CD44 mRNA m6A methylation modifications. Conclusions: We verified the effect of chronic stimulation of Cag A+H. pylori on malignant transformation of gastric mucosal epithelium. revealing the possibility of FTO in promoting malignant transformation of gastric mucosa by modifying CD44 mRNA methylation, suggesting that FTO expression is a potential molecule for malignant transformation of gastric mucosal epithelial cells. [ABSTRACT FROM AUTHOR]

Background: Helicobacter pylori ( H.pylori ) infection is an important factor in the occurrence of human gastric diseases, but its pathogenic mechanism is not clear. N6-methyladenosine (m6A) is the most prevalent reversible methylation modification in mammalian RNA and it plays a crucial role in controlling many biological processes. However, there are no studies reported that whether H. pylori infection impacts the m6A methylation of stomach. In this study, we measured the overall level changes of m6A methylation of RNA under H. pylori infection through in vitro and in vivo experiment. Methods: The total quantity of m6A was quantified in gastric tissues of clinical patients and C57 mice with H. pylori infection, as well as acute infection model [ H. pylori and GES-1 cells were cocultured for 48 h at a multiplicity of infection (MOI) from of 10:1 to 50:1]. Furthermore, we performed m6A methylation sequencing and RNA-sequencing on the cell model and RNA-sequencing on animal model. Results: Quantitative detection of RNA methylation showed that H. pylori infection group had higher m6A modification level. M6A methylation sequencing identified 2,107 significantly changed m6A methylation peaks, including 1,565 upregulated peaks and 542 downregulated peaks. A total of 2,487 mRNA was upregulated and 1,029 mRNA was downregulated. According to the comprehensive analysis of MeRIP-seq and RNA-seq, we identified 200 hypermethylation and upregulation, 129 hypermethylation but downregulation, 19 hypomethylation and downregulation and 106 hypomethylation but upregulation genes. The GO and KEGG pathway analysis of these differential methylation and regulatory genes revealed a wide range of biological functions. Moreover, combining with mice RNA-seq results, qRT- PCR showed that m6A regulators, METTL3, WTAP, FTO and ALKBH5, has significant difference; Two key genes, PTPN14 and ADAMTS1, had significant difference by qRT- PCR. Conclusion: These findings provide a basis for further investigation of the role of m6A methylation modification in H. pylori -associated gastritis., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Li, Lin, Cheng, Chi, Luo, Tang, Zhao, Shu, Liu and Xu.)