Integrative Analysis of Multi-Omics and Genetic Approaches—A New Level in Atherosclerotic Cardiovascular Risk Prediction

Abstract

Genetics and environmental and lifestyle factors deeply affect cardiovascular diseases, with atherosclerosis as the etiopathological factor (ACVD) and their early recognition can significantly contribute to an efficient prevention and treatment of the disease. Due to the vast number of these factors, only the novel “omic” approaches are surmised. In addition to genomics, which extended the effective therapeutic potential for complex and rarer diseases, the use of “omics” presents a step-forward that can be harnessed for more accurate ACVD prediction and risk assessment in larger populations. The analysis of these data by artificial intelligence (AI)/machine learning (ML) strategies makes is possible to decipher the large amount of data that derives from such techniques, in order to provide an unbiased assessment of pathophysiological correlations and to develop a better understanding of the molecular background of ACVD. The predictive models implementing data from these “omics”, are based on consolidated AI best practices for classical ML and deep learning paradigms that employ methods (e.g., Integrative Network Fusion method, using an AI/ML supervised strategy and cross-validation) to validate the reproducibility of the results. Here, we highlight the proposed integrated approach for the prediction and diagnosis of ACVD with the presentation of the key elements of a joint scientific project of the University of Milan and the Almazov National Medical Research Centre.

Oral Porphyromonas gingivalis and Fusobacterium nucleatum Abundance in Subjects in Primary and Secondary Cardiovascular Prevention, with or without Heterozygous Familial Hypercholesterolemia

“…The study population included 40 patients (30 patients without HeFH and 10 patients with HeFH,) in secondary ASCVD prevention, as defined by previous MI with/without PCI-DES or double/triple CABG and/or CEA. All of these patients at high risk of CVD were optimally treated with an individual combination of hypocholesterolemic drugs (statins, ezetimibe, proprotein convertase subtilisin/kexin type 9 (PCSK9) inhibitors) at the maximally tolerated dose, according to the most recent guidelines [ 25 ], and anti-platelet drugs. When appropriate, other drugs, including anti-hypertensive, β-blockers, and others, were also used.…”

Application of Multiple Omics to Understand Postoperative Delirium Pathophysiology in Humans

“…Bioinformatics uses inferential statistics to identify statistically significant differentially expressed molecules, adjust for multiple comparisons (using approaches such as Benjamini-Hochberg [103]), and consider the magnitude of alteration (fold change). These differentially expressed molecules are then used to develop predictive classifiers, using standard techniques such as logistic regression, or a variety of newer machine learning (ML) methods such as support vector machine (SVM), random forest, elastic net, Lasso, neural networks, gradient boosting (GBM), and K-nearest neighbors (KNN) [104][105][106]. Newer ML approaches are able to model complex, nonlinear relationships between the molecules and disease outcome [107].…”

Defining atherosclerotic plaque biology by mass spectrometry-based omics approaches

“…These techniques can be easily applied to different sample sources like cell lines, tissues, animal models, human clinical samples, autopsy samples and large population cohorts, enhancing our understanding of the differential cell function across tissues. 51 Proteomics-based approaches are mainly accomplished by liquid chromatography-mass spectrometry analytical platforms (Fig. 3).…”