Identification and Evaluation of Key Biomarkers of Acute Myocardial Infarction by Machine Learning

Acute myocardial infarction (AMI) is a severe disease that can occur in all age groups. About 8.5 million patients die of this disease every year. Although the diagnostic technology of AMI is relatively mature, there are still many limitations. We aim to use comprehensive bioinformatics and machine learning algorithms to study the potential molecular mechanism of acute myocardial infarction and seek new prevention and treatment strategies. Methods: The expression profiles of GSE66360 and GSE48060 were downloaded from the Gene Expression Omnibus database, microarray datasets were integrated, and differential genes were obtained to be further analyzed by bioinformatic technique. Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis, Disease Oncology (DO) analysis and Gene Set Enrichment Analysis (GSEA) were performed on the differential genes using R software, respectively. Then the Lasso algorithm was used to identify the AMI-related essential genes in the training set and validate them in the test set. Potential mechanistic analyses of the development of AMI included the following: the expression differences of crucial genes, differences in immune cell infiltration, immune cell correlation, and the correlation between critical genes and immune cells between normal and AMI samples. Results: Finally, five essential genes were screened, including CLEC4D, CSF3R, SLC11A1, CLEC12A, and TAGAP. The expression of critical genes differed between normal, and AMI samples and the genes can be used as a diagnostic factor in patients. Meanwhile, normal and AMI samples showed significant differences in immune infiltration, and the expression of critical genes was closely related to the abundance of immune cell infiltration. Conclusion: In this study, five essential genes were screened, and the underlying molecular mechanisms of AMI pathogenesis were analyzed, which may provide theoretical support for the diagnosis, prevention, prognosis evaluation and targeted immune therapy of AMI patients.