Analysis of the robustness of spectral indices during ventricular fibrillation

Requena‐Carrión, Jesús; Alonso‐Atienza, Felipe; Everss, Estrella; Sánchez-Muñoz, Juan J.; Ortiz, Mercedes; García‐Alberola, Arcadi; Rojo-Álvarez, José Luis

doi:10.1016/j.bspc.2013.06.013

Cited by 4 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the last decades, Sh/NSh rhythm detection strategies employ comprehensive measurements of the ECG waveform morphology and heart rhythm periodicity in the time-domain [7,9,11,14,16,[18][19][20][21][22][23][24][25]28,29], specific frequency bands via band-pass filtering for QRS or VF enhancement [11,[13][14][15][21][22][23]30], Fourier transform [11,14,[22][23][24]26,31,32] or time-frequency ECG transformations [10,24,27,33], as well as nonlinear ECG measures [11,12,14,17,[22][23][24]34,35]. Although sets of those classical features measured with computer-based programs have been shown to present good discrimination between Sh/NSh rhythms with state-of-the-art machine learning classifiers (discriminant analysis, logistic regression, bagging and random forests, support vector machines, genetic algorithms) [15,<...>…”

Section: Introductionmentioning

confidence: 99%

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms

Krasteva

Ménétré

Didon

et al. 2020

Sensors

View full text Add to dashboard Cite

Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned to self-extract significant features of the electrocardiogram (ECG) and can generally provide high-output diagnostic accuracy if subjected to robust training and optimization on large datasets at high computational cost. So far, limited research and optimization of DNNs in shock advisory systems is found on large ECG arrhythmia databases from out-of-hospital cardiac arrests (OHCA). The objective of this study is to optimize the hyperparameters (HPs) of deep convolutional neural networks (CNN) for detection of shockable (Sh) and nonshockable (NSh) rhythms, and to validate the best HP settings for short and long analysis durations (2–10 s). Large numbers of (Sh + NSh) ECG samples were used for training (720 + 3170) and validation (739 + 5921) from Holters and defibrillators in OHCA. An end-to-end deep CNN architecture was implemented with one-lead raw ECG input layer (5 s, 125 Hz, 2.5 uV/LSB), configurable number of 5 to 23 hidden layers and output layer with diagnostic probability p ∈ [0: Sh,1: NSh]. The hidden layers contain N convolutional blocks × 3 layers (Conv1D (filters = Fi, kernel size = Ki), max-pooling (pool size = 2), dropout (rate = 0.3)), one global max-pooling and one dense layer. Random search optimization of HPs = {N, Fi, Ki}, i = 1, … N in a large grid of N = [1, 2, … 7], Fi = [5;50], Ki = [5;100] was performed. During training, the model with maximal balanced accuracy BAC = (Sensitivity + Specificity)/2 over 400 epochs was stored. The optimization principle is based on finding the common HPs space of a few top-ranked models and prediction of a robust HP setting by their median value. The optimal models for 1–7 CNN layers were trained with different learning rates LR = [10−5; 10−2] and the best model was finally validated on 2–10 s analysis durations. A number of 4216 random search models were trained. The optimal models with more than three convolutional layers did not exhibit substantial differences in performance BAC = (99.31–99.5%). Among them, the best model was found with {N = 5, Fi = {20, 15, 15, 10, 5}, Ki = {10, 10, 10, 10, 10}, 7521 trainable parameters} with maximal validation performance for 5-s analysis (BAC = 99.5%, Se = 99.6%, Sp = 99.4%) and tolerable drop in performance (<2% points) for very short 2-s analysis (BAC = 98.2%, Se = 97.6%, Sp = 98.7%). DNN application in future-generation shock advisory systems can improve the detection performance of Sh and NSh rhythms and can considerably shorten the analysis duration complying with resuscitation guidelines for minimal hands-off pauses.

show abstract

Section: Introductionmentioning

confidence: 99%

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms

Krasteva

Ménétré

Didon

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

Relating the spectrum of cardiac signals to the spatiotemporal dynamics of cardiac sources

Requena‐Carrión

Beltran-Molina

Marqués

2013

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

An increasing number of studies use the spectrum of cardiac signals for analyzing the spatiotemporal dynamics of complex cardiac arrhythmias. However, the relationship between the spectrum of cardiac signals and the spatiotemporal dynamics of the underlying cardiac sources remains to date unclear. In this paper, we derive a mathematical expression relating the spectrum of cardiac signals to the spatiotemporal dynamics of cardiac sources and the measurement characteristics of the lead systems. Then, by using analytical methods and computer simulations we analyze the spectrum of cardiac signals measured by idealized lead systems during correlated and uncorrelated spatiotemporal dynamics. Our results show that lead systems can have distorting effects on the spectral envelope of cardiac signals, which depend on the spatial resolution of the lead systems and on the degree of spatiotemporal correlation of the underlying cardiac sources. In addition to this, our results indicate that the spectral features that do not depend on the spectral envelope, such as the dominant frequency, behave robustly against different choices of lead systems.

show abstract

Detection of shockable ventricular cardiac arrhythmias from ECG signals using FFREWT filter-bank and deep convolutional neural network

Panda

Jain

Tripathy

et al. 2020

Computers in Biology and Medicine

View full text Add to dashboard Cite

Analysis of the robustness of spectral indices during ventricular fibrillation

Cited by 4 publications

References 30 publications

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms

Relating the spectrum of cardiac signals to the spatiotemporal dynamics of cardiac sources

Detection of shockable ventricular cardiac arrhythmias from ECG signals using FFREWT filter-bank and deep convolutional neural network

Contact Info

Product

Resources

About