Harnessing multiomics technologies and machine learning for advancing personalized theranostic approaches in atherosclerosis

Evidence-based lipid-lowering therapies have significantly reduced, but not eradicated, atherosclerosis-induced cardiovascular disease, which remains a significant cause of morbidity and mortality around the world. This article focuses on precision medicine and examines the transformative potential of multiomics and machine learning in advancing theranostic approaches for atherosclerosis. The integration of multimodal data, known as multiomics, encompassing genomics and epigenomics, transcriptomics and epitranscriptomics, proteomics, metabolomics, and lipidomics, can support the comprehensive interrogation of molecular changes associated with disease initiation and progression. Machine learning algorithms are critical for identifying pertinent features of highly diverse and heterogeneous multiomic datasets. The combination of these new laboratory and data science technologies offers unprecedented opportunities for increasing precision in disease prediction, early detection, and monitoring, as well as more personalized treatments with current and new drugs. This article discusses the implications. It discusses their importance in the development and adoption of personalized medicine based on therapeutic approaches. Significance Statement The review article explores new opportunities to develop and adopt theranostic strategies for atherosclerosis, derived from the integration of multiomics and machine learning to enhance personalized pharmacotherapy, precision prognostics, and diagnostics of atherosclerosis and atherosclerosis-derived cardiovascular diseases.