Search

Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiovascular disease with a prevalence of 1 in 500 people and varying clinical presentations. Although there is much research on HCM, underlying molecular mechanisms are poorly understood, and research on the molecular mechanisms of its specific clinical presentations is scarce. Our aim was to explore the molecular mechanisms shared by HCM and its clinical presentations through the automated extraction of molecular mechanisms. Molecular mechanisms were congregated by a query of the INDRA database, which aggregates knowledge from pathway databases and combines it with molecular mechanisms extracted from abstracts and open-access full articles by multiple machine-reading systems. The molecular mechanisms were extracted from 230,072 articles on HCM and 19 HCM clinical presentations, and their intersections were found. Shared molecular mechanisms of HCM and its clinical presentations were represented as networks; the most important elements in the intersections’ networks were found, centrality scores for each element of each network calculated, networks with reduced level of noise generated, and cooperatively working elements detected in each intersection network. The identified shared molecular mechanisms represent possible mechanisms underlying different HCM clinical presentations. Applied methodology produced results consistent with the information in the scientific literature.

Hypertrophic cardiomyopathy (HCM) is a relatively common inherited cardiac disease that results in left ventricular hypertrophy. Machine learning uses algorithms to study patterns in data and develop models able to make predictions. The aim of this study is to identify HCM subtypes and examine the mechanisms of HCM using machine learning algorithms. Clinical and laboratory findings of 143 adult patients with a confirmed diagnosis of nonobstructive HCM are analyzed; HCM subtypes are determined by clustering, while the presence of different HCM features is predicted in classification machine learning tasks. Four clusters are determined as the optimal number of clusters for this dataset. Models that can predict the presence of particular HCM features from other genotypic and phenotypic information are generated, and subsets of features sufficient to predict the presence of other features of HCM are determined. This research proposes four subtypes of HCM assessed by machine learning algorithms and based on the overall phenotypic expression of the participants of the study. The identified subsets of features sufficient to determine the presence of particular HCM aspects could provide deeper insights into the mechanisms of HCM.