Browsing by Author "Muguli, Ananya"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A graph-based cardiac arrhythmia classification methodology using one-lead ECG recordings
    (Elsevier, 2024) EPMoghaddam, Dorsa; Muguli, Ananya; Razavi, Mehdi; Aazhang, Behnaam
    In this study, we present a novel graph-based methodology for an accurate classification of cardiac arrhythmia diseases using a single-lead electrocardiogram (ECG). The proposed approach employs the visibility graph technique to generate graphs from time signals. Subsequently, informative features are extracted from each graph and then fed into classifiers to match the input ECG signal with the appropriate target arrhythmia class. The six target classes in this study are normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), atrial premature contraction (A), and fusion (F) beats. Three classification models were explored, including graph convolutional neural network (GCN), multi-layer perceptron (MLP), and random forest (RF). ECG recordings from the MIT-BIH arrhythmia database were utilized to train and evaluate these classifiers. The results indicate that the multi-layer perceptron model attains the highest performance, showcasing an average accuracy of 99.02%. Following closely, the random forest achieves a strong performance as well, with an accuracy of 98.94% while providing critical intuitions.
  • Thumbnail Image
    Item
    The biophysics of neuron-astrocyte-vascular modeling in conditions of normalcy, Intracerebral Hemorrhagic (ICH) stroke and electrical stimulation
    (2024-12-03) Muguli, Ananya; Aazhang, Behnaam
    Intracerebral Hemorrhagic (ICH) stroke is the second most common type of stroke, but the deadliest. Nearly $45\%$ of patients succumb to complications, while the ones surviving suffer a high degree of morbidity and lose the previous quality of life. Neuromodulation has been used in past as a part of therapeutic regimens for post ischemic stroke (most common type of stroke) rehabilitation during the chronic stages. The idea of neuromodulation as a rehabilitation technique has been not formally studied from the first principles for ICH strokes whose outcomes are way more severe than ischemia. While our experimental work focuses on understanding whether neuromodulation can be applied in a practical setting of ICH during the acute phase to control outcome of the patient, this project explores the theoretical underpinnings of the effect of neuromodulation at a cellular systemic level of neuron-astrocyte-vascular system in the normal and acute conditions post ICH. We improvise the Hodgkin-Huxley neuron model to incorporate a presynaptic neuron, calcium transients in a neuron, the tripartite synapse along with the astrocytes, astrocytic calcium signaling, the post synaptic neuron, the cerebral blood flow as well as the oxygen and energy consumption dynamics. We simulate the various biochemical pathways that set in during the acute phase post ICH and implement electrical stimulation both in the normal and post stroke settings. The goal of this work is to understand qualitatively, the effects of electrical stimulation paradigms as a therapeutic strategy by analysing a set of non-linear Ordinary Differential Equations(ODEs). This is the first work of its kind, wherein electrical stimulation has been studied in such an elaborate setting incorporating not only the biophysics but also the bioenergetic effects of neurostimulation. The solution for the ODEs consists of traces and limit cycles, which exhibit the behaviour of different components under normal conditions, during stroke and during electrical stimulation. From these, it is safe to say that we get a closer look at the effects of various electrical neuromodulation paradigms under the given assumptions. This will be used to look into the gaps of theoretical understanding of such complex phenomena, paving the way for better future modeling of neurodegenerative diseases and various treatments for it.