Electrocardiography is the gold standard technique for detecting abnormal heart conditions. Automatic detection of electrocardiogram (ECG) abnormalities helps clinicians analyze the large amount of data produced daily by cardiac monitors. As the number of abnormal ECG samples with cardiologist-supplied labels required to train supervised machine learning models is limited, there is a growing need for unsupervised learning methods for ECG analysis. Unsupervised learning aims to partition ECG samples into distinct abnormality classes without cardiologistsupplied labels-a process referred to as ECG clustering. In addition to abnormality detection, ECG clustering has recently discovered inter and intra-individual patterns that reveal valuable information about the whole body and mind, such as emotions, mental disorders, and metabolic levels. ECG clustering can also resolve specific challenges facing supervised learning systems, such as the imbalanced data problem, and can enhance biometric systems. While several reviews exist on supervised ECG systems, a comprehensive review of unsupervised ECG analysis techniques is still lacking. This study reviews ECG clustering techniques developed mainly in the last decade. The focus will be on recent machine learning and deep learning algorithms and their practical applications. We critically review and compare these techniques, discuss their applications and limitations, and provide future research directions. This review provides further insights into ECG clustering and presents the necessary information required to adopt the appropriate algorithm for a specific application.
Visual impairment is one of the early symptoms of Multiple sclerosis (MS) disease. The objective of this study is evaluating function of Lateral geniculate nucleus, which bridges visual information from retina to other higher order visual processing areas. We collected BOLD fMRI data from 19 MS and 19 control subjects by employing selective visual stimulation tasks to provoke the whole LGN, Magnocellular, Parvocellular, and Koniocellular pathways as part of LGN multilayer structure. Through statistical analysis, we observed a significant reduction (p<0.05) of the average BOLD signal from the whole LGN structure in MS group. Further investigations showed a significant reduction of BOLD signal (p<0.05) in response to Magno and Parvo stimuli compared to healthy controls that suggested a selective functional impairment emerging in primary visual pathways in MS. In summary, we showed functional abnormalities in LGN structure and its M and P subdivisions based on functional MRI.
Recent studies have revealed mappings between brain-wide gene expression profiles and a range of brain structure and activity phenotypes. Most of these studies have used group-averaged expression data. While informative, this approach cannot capture the high degree of individual variation in brain phenotypes. The investigation of this variation to date has been limited by availability of gene expression and neuroimaging data for many individuals. Here, we addressed this limitation by adopting PrediXcan, an established framework for inferring genetically regulated gene expression using localized genetic variants. This framework has allowed us to study the otherwise inaccessible expression profiles for brain regions across many individuals. We used this approach to identify genes whose inferred expression across brain regions of interest correlated with a range of phenotypes. Our analyses bridge a gap in human neuroimaging by enabling the study of associations between individual-level gene expression and brain structure and activity. Ultimately, this approach can help reveal mechanistic pathways from gene expression to healthy or diseased brain function.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.