Browsing by Author "Razavi, Mehdi"

Now showing 1 - 6 of 6
  • 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
    Abdominal Fat Suspension Device for Maintaining Normal Cardiorespiratory Function in Patients Undergoing Conscious Sedation during Surgery: A Feasibility Study
    (Texas Heart Institute, 2014) Truong, Norman F.; Nathan, Joanna C.; Yoon, Daeun; Ochoa, Gabriel; Prevost, Marisa; Yun, Sehyun; Oden, Z. Maria; Razavi, Mehdi; Bioengineering
    Obese patients undergoing conscious-sedation surgery have increased perioperative morbidity because their excess abdominal tissue limits diaphragmatic excursion. We describe a simple device that might help attenuate this risk. We created a noninvasive suction device for abdominal suspension. By lifting the burden of excess weight, this device should decrease respiratory effort. To test the feasibility of excess weight removal in relieving cardiac stress, we tested 22 supine, healthy, normal-weight subjects by measuring their heart rates with and without a 13-kg tissue model on their abdomen to simulate excess weight. There was no significant difference in blood oxygen saturation before and after weight removal (P=0.318). However, the decrease in heart rate was significant (P <0.0001; paired 2-sample, one-tailed t test), which implies decreased respiratory effort. This result suggests the possibility that abdominal mass suspension in obese patients is associated with decreased respiratory effort.
  • Thumbnail Image
    Item
    RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms
    (ACM, 2022) Zhang, Yongan; Banta, Anton; Fu, Yonggan; John, Mathews M.; Post, Allison; Razavi, Mehdi; Cavallaro, Joseph; Aazhang, Behnaam; Lin, Yingyan
    There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2) corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency.
  • Thumbnail Image
    Item
    Systems and methods for wireless treatment of arrhythmias
    (2021-07-27) Sun, Yuxiang; Babakhani, Aydin; Razavi, Mehdi; Burkland, David; Greet, Brian; John, Mathews; Lyu, Hongming; Rice University; Texas Heart Institute; Baylor College of Medicine; United States Patent and Trademark Office
    Wireless treatment of arrhythmias. At least some of the example embodiments are methods including: charging a capacitor of a first microchip device abutting heart tissue, the charging by harvesting ambient energy; charging a capacitor of a second microchip device abutting the heart tissue, the charging of the capacitor of the second microchip device by harvesting ambient energy; sending a command wirelessly from a communication device outside the rib cage to the microchip devices; applying electrical energy to the heart tissue by the first microchip device responsive to the command, the electrical energy applied from the capacitor of the first microchip device; and applying electrical energy to the heart tissue by the second microchip device responsive to the command to the second microchip device, the electrical energy applied from the capacitor of the second microchip device.
  • Thumbnail Image
    Item
    Systems and methods for wireless treatment of arrhythmias
    (2023-08-01) Sun, Yuxiang; Babakhani, Aydin; Razavi, Mehdi; Burkland, David; Greet, Brian; John, Mathews; Lyu, Hongming; Rice University; William Marsh Rice University; Texas Heart Institute; Baylor College of Medicine; United States Patent and Trademark Office
    Wireless treatment of arrhythmias. At least some of the example embodiments are methods including: charging a capacitor of a first microchip device abutting heart tissue, the charging by harvesting ambient energy; charging a capacitor of a second microchip device abutting the heart tissue, the charging of the capacitor of the second microchip device by harvesting ambient energy; sending a command wirelessly from a communication device outside the rib cage to the microchip devices; applying electrical energy to the heart tissue by the first microchip device responsive to the command, the electrical energy applied from the capacitor of the first microchip device; and applying electrical energy to the heart tissue by the second microchip device responsive to the command to the second microchip device, the electrical energy applied from the capacitor of the second microchip device.
  • Thumbnail Image
    Item
    Two Studies from the Development Cycle ofMacroscopic Carbon Nanotube Materials: Rheology of Carbon Nanotubes in Superacids and Characterization of the Electrochemical Circuit Behavior of Carbon Nanotube Fiber Electrodes for Electrophysiology
    (2017-04-21) Young, Colin C; Pasquali, Matteo; Razavi, Mehdi
    Carbon nanotubes (CNTs) possess a variety of properties which make them attractive as building blocks for high performance multi-functional materials. The discovery that superacids such as chlorosulfonic acid (ClHSO3) act as true solvents for CNTs has led to the development of fluid processing techniques by which a variety of macroscopic CNT materials can be fabricated. This work presents two studies which are linked by the common thread of CNT materials development from acid solution precursors. The first study compares the rheology of two different CNT species in ClHSO3 as a function of concentration and frequency. The development of elastic structure with increasing solution concentration is found to depend strongly on the morphology of the liquid crystalline phase domains in the biphasic regime; physical interactions between non-interpenetrating liquid crystal domains are found to be a significant source of viscoelastic stress. An analysis of the scaling of viscoelastic behavior at short time scales, based on models of semiflexible polymer rheology, reveals that the primary contribution to the stress at short times is longitudinal tension resulting from contour fluctuations of individual CNTs; this tension-dominated stress is the primary viscoelastic stress for low concentration solutions. The second study investigates the electrochemical properties of macroscopic CNT fibers for applications in electrophysiology and cardiac medicine. CNT fibers exhibit much lower interfacial impedance with physiological saline and cardiac tissue than platinum wire of the same geometric surface area. Equivalent circuit modeling demonstrates that the low area-specific impedance of these fibers arises from a large double layer capacitance, which in turn arises from wetting of the internal porous surface area. Aging and storage conditions are shown to affect the wettability of this structure, and an electrowetting treatment is demonstrated which creates a stable increase in CNT fiber electrode performance. The specific circuit behavior of the CNT fiber is used to construct a theoretical model for CNT fiber electrode performance in cardiac tissue in vivo and to calculate a transfer function which represents the efficiency with which a cellular action potential may be transmitted through a CNT fiber between two electrically separated regions of cardiac tissue.