Assessment of Novel Biomarkers for Early Detection of Cardiovascular Diseases

Abstract

As a major cause of morbidity and mortality, cardiovascular diseases (CVDs) pose a serious threat to global health. For the efficient therapy and prevention of CVDs, early identification and risk stratification are essential. The evaluation of novel biomarkers for the early identification of CVDs is explored in this review paper, which divides them into five major categories: genomics, proteomics, metabolomics, imaging, and artificial intelligence (AI). Single nucleotide polymorphisms (SNPs) and epigenetic changes are examples of genomic biomarkers that provide information about genetic predispositions to CVDs. Proteomic biomarkers help in diagnosis and risk assessment, such as cardiac troponin and brain natriuretic peptide (BNP). Metabolomic biomarkers concentrate on metabolic patterns and offer useful data for early detection and individualised care. With the use of AI, imaging biomarkers are better able to evaluate heart shape, spontaneous function, and blood flow. Additionally, AI-driven biomarker discovery uses deep learning and machine learning algorithms to analyse a variety of data sources, speeding up the discovery of new CVD indications. Although encouraging, issues with data privacy, model interpretability, and regulatory approval must be resolved for AI-based biomarkers to be successfully implemented in clinical practise.