IL18 in acute pancreatitis: Machine learning and two-sample Mendelian randomization study

Abstract

Abstract Objective Acute pancreatitis is a common disease whose treatment is limited to symptomatic support, thus finding effective biomarkers is of great significance for early diagnosis and therapy. Methods Bioinformatics and machine learning were applied to evaluate the expression, clinical features, biological function and immunological effects of the characteristic genes in AP. Meanwhile, AP mice models were constructed to verify the results in vivo. Finally, Mendelian randomization studies were performed to determine the causal relationship between IL-18 and AP through genome-wide association studies. Results A total of 100 core genes were obtained via differential analysis and PPI interaction network. IL18 was identified as the characteristic gene for AP by machine learning through three algorithmic. The expression of IL18 was increased significantly in AP (P < 0.001). The AUC value of IL18 in the diagnosis of AP was 0.917, exhibiting high clinical value. Moreover, IL18 was associated with various immune cells involved in the progression of AP. Through inverse variance weighting (IVW), we found that the OR for IL18 and AP was 0.908 (95%CI = 0.843–0.978, p = 0.011). Conclusions IL18 is a pivotal biomarker predicting the clinical prognosis and immune response in AP, which is proved to serve as a protective factor.