Flavio H. Fenton

Flavio H. Fenton

Auto-generated profile, based on publicly available information

Flavio H. Fenton

Georgia Institute of Technology, Atlanta, Georgia

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 April 2022 in Machine Learning with Applications
Verified
Journal Article
Open access
SSShahrokh Shahi
Shahrokh Shahi
FFFlavio H. Fenton
Flavio H. Fenton
ECElizabeth M. Cherry
Elizabeth M. Cherry
In recent years, machine-learning techniques, particularly deep learning, have outperformed traditional time-series forecasting approaches in many contexts, including univariate and multivariate predictions. This study aims to investigate the capability of (i) gated recurrent neural networks, including long short-term memory (LSTM) and gated recurrent unit (GRU) networks, (ii) reservoir computing (RC) techniques, such as echo state networks (ESNs) and hybrid physics-informed ESNs, and (iii) the nonlinear vector autoregression (NVAR) approach, which has recently been introduced as the next generation RC, for the prediction of chaotic time series and to compare their performance in terms of accuracy, efficiency, and robustness. We apply the methods to predict time series obtained from two widely used chaotic benchmarks, the Mackey–Glass and Lorenz-63 models, as well as two other chaotic datasets representing a bursting neuron and the dynamics of the El Niño Southern Oscillation, and to one experimental dataset representing a time series of cardiac voltage with complex dynamics. We find that even though gated RNN techniques have been successful in forecasting time series generally, they can fall short in predicting chaotic time series for the methods, datasets, and ranges of hyperparameter values considered here. In contrast, for the chaotic datasets studied, we found that reservoir computing and NVAR techniques are more computationally efficient and offer more promise in long-term prediction of chaotic time series.

1 January 2013 in Frontiers in Physiology
Verified
Journal Article
Open access
PDF file
AGAlessio Gizzi
Alessio Gizzi
ECElizabeth M. Cherry
Elizabeth M. Cherry
RGRobert F. Gilmour
Robert F. Gilmour
SLStefan Luther
Stefan Luther
SFSimonetta Filippi
Simonetta Filippi
FFFlavio H. Fenton
Flavio H. Fenton
Alternans of action potential duration has been associated with T-wave alternans and the development of arrhythmias because it produces large gradients of repolarization. However, little is known about alternans dynamics in large mammalian hearts. Using optical mapping to record electrical activations simultaneously from the epicardium and endocardium of 9 canine right ventricles, we demonstrate novel arrhythmogenic complex spatiotemporal dynamics. (i) Alternans predominantly develops first on the endocardium. (ii) The postulated simple progression from normal rhythm to concordant to discordant alternans is not always observed; concordant alternans can develop from discordant alternans as the pacing period is decreased. (iii) In contrast to smaller tissue preparations, multiple stationary nodal lines may exist and need not be perpendicular to the pacing site or to each other. (iv) Alternans has fully three-dimensional dynamics and the epicardium and endocardium can show significantly different dynamics: multiple nodal surfaces can be transmural or intramural and can form concave/convex surfaces resulting in islands of discordant alternans. (v) The complex spatiotemporal patterns observed during alternans are very sensitive to both the site of stimulation and the stimulation history. Alternans in canine ventricles not only exhibit larger amplitudes and persist for longer cycle length regimes compared those found in smaller mammalian hearts, but also show novel dynamics not previously described that enhance dispersion and show high sensitivity to initial conditions. This indicate some underlying predisposition to chaos and can help the design of new drugs and devices controlling and preventing arrhythmic events.

1 March 2019 in Science Advances
Verified
Journal Article
Open access
PDF file
AKAbouzar Kaboudian
Abouzar Kaboudian
ECElizabeth M. Cherry
Elizabeth M. Cherry
FFFlavio H. Fenton
Flavio H. Fenton
Supercomputer simulations of accurate cardiac electrophysiology are now possible in real time on desktops and even cell phones.

20 October 2017 in Frontiers in Physiology
Verified
Journal Article
Open access
IUIlija Uzelac
Ilija Uzelac
YJYanyan C. Ji
Yanyan C. Ji
DHDaniel Hornung
Daniel Hornung
JSJohannes Schröder-Scheteling
Johannes Schröder-Scheteling
SLStefan Luther
Stefan Luther
FFFlavio H. Fenton
Flavio H. Fenton
Rationale: Discordant alternans, a phenomenon in which the action potential duration (APDs) and/or intracellular calcium transient durations (CaDs) in different spatial regions of cardiac tissue are out of phase, present a dynamical instability for complex spatial dispersion that can be associated with long-QT syndrome (LQTS) and the initiation of reentrant arrhythmias. Because the use of numerical simulations to study arrhythmic effects, such as acquired LQTS by drugs is beginning to be endorsed by the FDA, it is crucial to validate mathematical models that may be used during this process. Objective: In this study, we characterized with high spatio-temporal resolution the development of discordant alternans patterns in transmembrane voltage (Vm) and intracellular calcium concentration ([Cai]+2) as a function of pacing period in rabbit hearts. Then we compared the dynamics to that of the latest state-of-the-art model for ventricular action potentials and calcium transients to better understand the underlying mechanisms of discordant alternans and compared the experimental data to the mathematical models representing Vm and [Cai]+2 dynamics. Methods and Results: We performed simultaneous dual optical mapping imaging of Vm and [Cai]+2 in Langendorff-perfused rabbit hearts with higher spatial resolutions compared with previous studies. The rabbit hearts developed discordant alternans through decreased pacing period protocols and we quantified the presence of multiple nodal points along the direction of wave propagation, both in APD and CaD, and compared these findings with results from theoretical models. In experiments, the nodal lines of CaD alternans have a steeper slope than those of APD alternans, but not as steep as predicted by numerical simulations in rabbit models. We further quantified several additional discrepancies between models and experiments. Conclusions: Alternans in CaD have nodal lines that are about an order of magnitude steeper compared to those of APD alternans. Current action potential models lack the necessary coupling between voltage and calcium compared to experiments and fail to reproduce some key dynamics such as, voltage amplitude alternans, smooth development of calcium alternans in time, conduction velocity and the steepness of the nodal lines of APD and CaD.

9 June 2022 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
NDNoah DeTal
Noah DeTal
AKAbouzar Kaboudian
Abouzar Kaboudian
FFFlavio H. Fenton
Flavio H. Fenton
We identify and demonstrate a universal mechanism for terminating spiral waves in excitable media using an established topological framework. This mechanism dictates whether high- or low-energy defibrillation shocks succeed or fail. Furthermore, this mechanism allows for the design of a single minimal stimulus capable of defibrillating, at any time, turbulent states driven by multiple spiral waves. We demonstrate this method in a variety of computational models of cardiac tissue ranging from simple to detailed human models. The theory described here shows how this mechanism underlies all successful defibrillation and can be used to further develop existing and future low-energy defibrillation strategies.

1 January 2020 in Computer Methods in Applied Mechanics and Engineering
Verified
Journal Article
Closed access
ABAlessandro Barone
Alessandro Barone
AGAlessio Gizzi
Alessio Gizzi
FFFlavio Fenton
Flavio Fenton
SFSimonetta Filippi
Simonetta Filippi
Veneziani, AlessandroVeneziani, Alessandro
Veneziani, Alessandro