Robust detection of atrial fibrillation from short-term electrocardiogram using convolutional neural networks

Nurmaini, Siti; Tondas, Alexander Edo; Darmawahyuni, Annisa; Rachmatullah, Muhammad Naufal; Partan, Radiyati Umi; Firdaus, Firdaus; Tutuko, Bambang; Pratiwi, Ferlita; Juliano, Andre Herviant; Khoirani, Rahmi

doi:10.1016/j.future.2020.07.021

Cited by 75 publications

(74 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• ECG noise removal using discrete wavelet transform (DWT). This step decompose the ECG signals into the specific wavelet levels (8 levels) with Sym5 [13]. The signal frequency is divided by two in DWT because it passes through the high pass and low pass filters.…”

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

“…The feature reduce from 2700 nodes in layer-1 becomes 78 nodes in layer-13 with maxpooling-5, and the selected feature that use as input in fully connected layer to classify the normal and AF feature. • Each ECG signal episodes of 2700 nodes was trained using the 1D-CNNs classifier model was proposed by Nurmaini et al [13]. The structure model has 13 hidden layers with an activation function rectified linear unit (ReLU) in the hidden layers and tanh-sigmoid in the output layers [13].…”

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

“…• Each ECG signal episodes of 2700 nodes was trained using the 1D-CNNs classifier model was proposed by Nurmaini et al [13]. The structure model has 13 hidden layers with an activation function rectified linear unit (ReLU) in the hidden layers and tanh-sigmoid in the output layers [13]. The hyperparameters utilize a 0.0001 learning rate, 16 batch size, and 100 epochs.…”

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

“…However, by considering signals as 1-dimensional (1D) data, studies have shown promising results using convolutions for signal processing [20][23][24] [25]. 1D-CNNs show superiority in AF signal processing and have outperformed both recurrent neural networks (RNNs) and deep neural networks (DNNs) [13].…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have shown that 1D-CNNs can successfully provide fast and accurate classification of long-term ECG records. They can analyze the morphological characteristics and learn the slit variation of an input signal during a short-term ECG [13]. The 1D-CNNs model is developed for patient-specific ECG classification [26].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

AFibNet: An Implementation of Atrial Fibrillation Detection With Convolutional Neural Network

Tutuko

Nurmaini

Tondas³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R-R intervals to determine the Heart Rate Variability (HRV). An accurate HRV is the gold standard for predicting the AF condition. Hence, we propose a DL approach to analyze massive amounts of ECG raw data in a broad range of devices to overcome a current challenge.Results: This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8,232 records based on three datasets and tested with 3,610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity. When tested with unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity in 0.02 seconds for one instance when processed in theDL-Cloud System.Conclusions: These findings demonstrate that the proposed model approach can used in a broad range of devices and validated to unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment.

show abstract

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

Section: Implementation Of Atrial Fibrillation Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

AFibNet: An Implementation of Atrial Fibrillation Detection With Convolutional Neural Network

Tutuko

Nurmaini

Tondas³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Detection of atrial fibrillation using variable length genetic algorithm and convolutional neural network

Qaraghuli

Sheibani

Tabatabaee

2021

Concurrency and Computation

View full text Add to dashboard Cite

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia and it is considered as one of the most important risk factor for death, stroke, hospitalization, and heart failure. It is possible to detect AF by analyzing electrocardiogram (ECG) of patients. To work on clean signals and reduce errors resulted from noise, we have used Butterworth filter. The short-term Fourier transform was used to analyze ECG segments to obtain ECG spectrogram images. Convolutional neural network (CNN) models have been proposed for improving automatic detection of AF. The number of convolutional layers varies in different CNN models, and as the model become deeper, more hyper parameters are added. So in this article, variable length genetic algorithm was used in order to optimize hyper parameters of CNN. The results of experiments that performed onthe MIT-BIH AF database showed that the proposed method achieved 100%, 98.90%, and 99.95% for the sensitivity, specificity, and accuracy, respectively, so the proposed method outperforms the deep CNNs. Hence, the proposed method is an accurate and efficient method for detection of AF.

show abstract

Automatic Diagnosis of Cardiovascular Diseases Using Electrocardiogram Data and Artificial Intelligence Algorithms: A Systematic Review

Vega

Hurtado

Aceves-Fernández

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Robust detection of atrial fibrillation from short-term electrocardiogram using convolutional neural networks

Cited by 75 publications

References 43 publications

AFibNet: An Implementation of Atrial Fibrillation Detection With Convolutional Neural Network

AFibNet: An Implementation of Atrial Fibrillation Detection With Convolutional Neural Network

Detection of atrial fibrillation using variable length genetic algorithm and convolutional neural network

Automatic Diagnosis of Cardiovascular Diseases Using Electrocardiogram Data and Artificial Intelligence Algorithms: A Systematic Review

Contact Info

Product

Resources

About