Bioinformatics analysis identifies potential diagnostic signatures for coronary artery disease

Abstract

Background Coronary artery disease (CAD) is the leading cause of mortality worldwide. We aimed to screen out potential gene signatures and construct a diagnostic model for CAD. Method We downloaded two mRNA profiles, GSE66360 and GSE60993, and performed analyses of differential expression, gene ontology terms, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. The STRING database was used to identify protein–protein interactions (PPI). PPI network visualization and screening out of key genes were performed using Cytoscape software. Finally, a diagnostic model was constructed. Results A total of 2127 differentially expressed genes (DEGs) were identified in GSE66360, and 527 DEGs in GSE60993. Of the 153 DEGs from both datasets that showed differential expression between CAD patients and controls, 471 biological process terms, 35 cellular component terms, 17 molecular function terms, and 49 KEGG pathways were significantly enriched. The top 20 key genes in the PPI network were identified, and a diagnostic model constructed from five optimal genes that could efficiently separate CAD patients from controls. Conclusion We identified several potential biomarkers for CAD and built a logistic regression model that will provide a valuable reference for future clinical diagnoses and guide therapeutic strategies.

Long-Term Outcomes for Chinese COPD Patients After PCI: A Propensity Score Matched, Double-Cohort Study

“…Fortunately, there are a number of novel diagnostic methods coming into clinical practice. For example, through bioinformatics analysis, Zhang et al ( 29 ) have managed to identify several biomarkers that could potentially be used to differentially diagnose CADs in terms of genetic signatures ( 29 ). Likewise, Jing et al have found that the levels of expression of Homer 1, IL-1β, and TNF-α may be used to differentially diagnose CADs ( 30 ), meaning that there are opportunities on the horizon which will improve diagnosis beyond spirometry.…”

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

“…Finally, to test the performance, a logistic regression model was built using the top five predictor genes to classify individuals into the presence or absence of CAD. The model achieved an AUC of 0.9295 and 0.8674 in the training and internal validation sets respectively [ 20 ].…”

Artificial Intelligence-Based Clinical Decision Support Systems in Cardiovascular Diseases

“…These models combined clinical and demographic characteristics with quantitative variables as assessed by visual interpretation, or SPECT, to better predict CAD compared to quantitative variables alone. 21 , 22 Cardiovascular imaging techniques have big data, and AI-powered solutions create a suitable study field. In particular, AI can be used to measure cardiovascular risk, especially in CAD, in 2 main ways: (1) by applying DL algorithms directly to image data for automatic quantification of prognostic biomarkers or (2) through the integration of traditional or AI-based imaging measures with tabular data in ML models for individualized outcome prediction.…”