Integrating Bioinformatics and Machine Learning to Investigate the Mechanisms by Which Three Major Respiratory Infectious Diseases Exacerbate Heart Failure

Background Heart failure (HF) is a severe cardiovascular disease often worsened by respiratory infections like influenza, COVID-19, and community-acquired pneumonia (CAP). This study aims to uncover the molecular commonalities among these respiratory diseases and their impact on HF, identifying key mediating genes. Methods Datasets from the GEO database were analyzed for differential expression to find common molecular features of the three respiratory diseases. Weighted Gene Co-expression Network Analysis (WGCNA) was used to identify gene modules associated with HF. GO and KEGG enrichment analyses determined the biological processes and pathways involved in HF exacerbation by respiratory diseases. Key genes were screened using LASSO, RF, and SVM-RFE machine learning algorithms, with accuracy validated by ROC curves. Single-sample GSEA (ssGSEA) was performed, and the Drug Signature Database (DSigDB) was used for drug prediction. Immune infiltration analysis was conducted using CIBERSORT. Results We identified 51 characteristic genes of respiratory diseases and 10 potential genes exacerbating HF, primarily involved in innate immune response, inflammation, and coagulation pathways. Machine learning algorithms identified RSAD2 and IFI44L as key genes with high accuracy (AUC > 0.7). ssGSEA indicated RSAD2’s involvement in complement and coagulation cascades, while IFI44L is associated with myocardial contraction in HF progression. DSigDB predicted six potential therapeutic drugs. Immune infiltration analysis revealed significant differences in eight immune cell types between HF patients and healthy controls. Conclusion Our findings enhance the understanding of molecular interactions between respiratory diseases and heart failure, paving the way for future research and therapeutic strategies.