Identification of Macrophage-Related Genes in Sepsis-Induced Acute Respiratory Distress Syndrome (ARDS) Using Bioinformatics and Machine Learning

A new study published in Scientific Reports has used bioinformatics and machine learning to identify macrophage-related genes to increase the scope of potential biomarkers for diagnosing sepsis-induced acute respiratory distress syndrome (ARDS). The research team conducted various analyses on differentially expressed genes between the control and sepsis-induced ARDS groups. They found 325 common differentially expressed genes and their enrichment analysis suggested that the genes are correlated with immune function and reactive oxygen species metabolism. Furthermore, immune infiltration analysis revealed high levels of monocytes, neutrophils, macrophages, and MDSCs in ARDS patients. These findings helped identify 48 macrophage-related differentially expressed genes that were correlated with the 325 differentially expressed genes. Subsequent machine learning and validation analyses showed that SGK1, DYSF, and MSRB1 genes exhibited good diagnostic value in ARDS. The nomogram analysis of these three genes showed an area under the curve (AUC) of 0.809, demonstrating that the prediction effect of the model was better than that of each gene alone. The study could contribute to expanding the field of potential biomarkers and improving diagnostic accuracy for ARDS.