Application of machine learning in understanding atherosclerosis: Emerging insights

Abstract

Biological processes are incredibly complex—integrating molecular signaling networks involved in multicellular communication and function, thus maintaining homeostasis. Dysfunction of these processes can result in the disruption of homeostasis, leading to the development of several disease processes including atherosclerosis. We have significantly advanced our understanding of bioprocesses in atherosclerosis, and in doing so, we are beginning to appreciate the complexities, intricacies, and heterogeneity atherosclerosi. We are also now better equipped to acquire, store, and process the vast amount of biological data needed to shed light on the biological circuitry involved. Such data can be analyzed within machine learning frameworks to better tease out such complex relationships. Indeed, there has been an increasing number of studies applying machine learning methods for patient risk stratification based on comorbidities, multi-modality image processing, and biomarker discovery pertaining to atherosclerotic plaque formation. Here, we focus on current applications of machine learning to provide insight into atherosclerotic plaque formation and better understand atherosclerotic plaque progression in patients with cardiovascular disease.

The Inflamm-Aging Model Identifies Key Risk Factors in Atherosclerosis

“…Network markers were also identified by calculating the betweenness of each aging–disease shortest path; the top 10 markers are shown in Table 8 . The network marker with the greatest betweenness ( Munger et al, 2021 ) was RPL35 ( Figure 5A ; Table 8 ). RPL35 is an important component of the 60S ribosomal subunit, with a key role in mRNA translation and protein synthesis ( Wu et al, 2021 ).…”

“…At present, there are many omics profiles to be further analyzed; thus, proper prediction models need to be developed ( Munger et al, 2021 ). Machine learning (ML), which is regarded as an extension of classical statistical modeling, can digest large amounts of data to identify high-order correlations and generate predictions ( Alber et al, 2019 ; Zhavoronkov et al, 2019 ).…”

“…Recently, an ML-derived score has been reported to show satisfactory performance in the prediction of cardiovascular events ( Sánchez-Cabo et al, 2020 ). Some studies have also shown that ML can predict CVD and identify key markers related to inflamm-aging and CVD ( Alalawi and Alsuwat, 2021 ; Munger et al, 2021 ; Sayed et al, 2021 ). Network analysis can also be used to find clusters of highly related genes and to associate modules with each other and with external sample traits ( Deshpande et al, 2016 ).…”

Novel Biomarkers of Atherosclerotic Vascular Disease—Latest Insights in the Research Field

“…Traditional biostatistics methods provide a limited overview through the information provided by correlations between a single variable and disease. Analysis of biological metrics and analytes sampled from bigger datasets across not only patients but across scales are available through AI, as machine learning can convert raw data into deployable models [261]. In the atherosclerosis research field, ML applications focus on event prediction, risk stratification, diagnostic classification, or biomarker discovery [262,263].…”

Metaheuristics with Deep Learning Empowered Biomedical Atherosclerosis Disease Diagnosis and Classification

“…This MDSS is depending on supervised ML models. Munger et al [11] aim at the present application of ML for providing insights into the atherosclerotic plaque formation and good understanding of atherosclerotic plaque evolution in patients with CVD.…”