Electrocardiogram signal classification for automated delineation using bidirectional long short-term memory

Nurmaini, Siti; Tondas, Alexander Edo; Darmawahyuni, Annisa; Rachmatullah, Muhammad Naufal; Effendi, Jannes; Firdaus, Firdaus; Tutuko, Bambang

doi:10.1016/j.imu.2020.100507

Cited by 26 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We achieved a good performance with an average accuracy, sensitivity, and F1score of 99.64%, 98.74%, and 98.78%, respectively. However, to achieve greater generalization than we stated in our previous study [23], we had to add automatic feature extraction.…”

Section: Resultsmentioning

confidence: 98%

“…Different to them, we added the isoelectric line from Tend -Pstart2. In our previous work [23], we conducted a BiLSTM model for P-wave, QRS complex, T-wave, and isoelectric lines. We achieved a good performance with an average accuracy, sensitivity, and F1score of 99.64%, 98.74%, and 98.78%, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…They achieved the performance of the proposed DENS-ECG model in raw and filtered signals above 76.80% and 96.53% sensitivity, respectively. Finally, in our previous work [23], we implemented BiLSTM for P-wave, QRS complex, T-wave, and isoelectric line classification. The proposed method outperformed a unidirectional LSTM with an overall average of 99.64% accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…For the experiments, this study generated the stacked ConvBiLSTM models for ECG waveform classification in two cases: (1) four-class classification comprised P-wave (Pstart -Pend), QRS complex (QRSstart -QRSend), T-wave (Tstart -Tend) and No-wave classification, and (2) seven-class classification. We compared the experiment of the ECG delineation in our previous work [23], which limited to three main ECG waveform (P-wave, QRS-complex, T-wave and other waveforms belong to No-wave class) to this current study. The current study is not only focus to delineate the start and end of three main ECG waveforms points, but also the ECG segments, e.g., Pend -QRSstart (PR-segment), QRSend -Tstart (ST-segment), and Tend -Pstart.…”

Section: Stacked Convbilstmmentioning

confidence: 99%

“…The ECG waveform is dynamically changed every time depending on the frequency setting and the signal length. However, the BiLSTM technique lacks of feature extraction to recognize the dynamic ECG waveform [23]. Due to this problem, the aim of this study to improve the BiLSTM architecture stacked with a convolutional neural networks (CNNs) architecture as feature extraction to increase the classifier performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Beat-to-Beat Electrocardiogram Waveform Classification Based on a Stacked Convolutional and Bidirectional Long Short-Term Memory

et al. 2021

Self Cite

View full text Add to dashboard Cite

Delineating the electrocardiogram (ECG) waveform is an important step with high significance in cardiology diagnosis. It refers to extract the ECG morphology in start, peak, end points of waveform. Due to various shapes and abnormalities presented in ECG signals, several conventional computer algorithms always fail to extract the essential feature of heart information. Thus, it is critical to investigate an automated ECG signal delineation with its result accuracy. In this study, we propose the delineation process by using bidirectional long short-term memory (BiLSTM) classifier. Such process was conducted as one beat to the next (beat-to-beat), that means the ECG waveform classification is start of P-wave1 to start of P-wave2. However, such classifier lack of feature extraction process, reducing the classification accuracy result. To improve the classifier performance, convolutional layers as facture extraction are stacked with BiLSTM named ConvBiLSTM. We conducted the experimental based on seven-class ECG waveform using a publicly available QT Database with annotation of the main waveforms to produce high accurate classifier, i.e., P start -Pend, Pend -QRSstart, QRSstart -Rpeak, Rpeak -QRSend, QRSend -Tstart, Tstart -Tend, and Tend -Pstart. It was found that the proposed model showed remarkable results with overall average performances of 99.83% accuracy, 98.82% sensitivity, 99.90% specificity, 98.86% precision, and 98.84% F1 score. Based on these promising results, the efficacy of the proposed stacked ConvBiLSTM model in classifying ECG waveform provides a great opportunity to help cardiologists in diagnosis decision-making for faster assessment.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Stacked Convbilstmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Beat-to-Beat Electrocardiogram Waveform Classification Based on a Stacked Convolutional and Bidirectional Long Short-Term Memory

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

Towards Automated Optimization of Residual Convolutional Neural Networks for Electrocardiogram Classification

2023

View full text Add to dashboard Cite

Accurate Fetal QRS-Complex Classification from Abdominal Electrocardiogram Using Deep Learning

Darmawahyuni,

Tutuko,

Nurmaini

et al. 2023

Int J Comput Intell Syst

View full text Add to dashboard Cite

Fetal heart monitoring during pregnancy plays a critical role in diagnosing congenital heart disease (CHD). A noninvasive fetal electrocardiogram (fECG) provides additional clinical information for fetal heart monitoring. To date, the analysis of noninvasive fECG is challenging due to the cancellation of maternal QRS-complexes, despite significant advances in electrocardiography. Fetal QRS-complex is highly considered to measure fetal heart rate to detect some fetal abnormalities such as arrhythmia. In this study, we proposed a deep learning (DL) framework that stacked a convolutional layer and bidirectional long short-term memory for fetal QRS-complexes classification. The fECG signals are first preprocessed using discrete wavelet transform (DWT) to remove the noise or inferences. The following step beats and QRS-complex segmentation. The last step is fetal QRS-complex classification based on DL. In the experiment of Physionet/Computing in Cardiology Challenge 2013, this study achieved 100% accuracy, sensitivity, specificity, precision, and F1-score. A stacked DL model demonstrates an effective tool for fetal QRS-complex classification and contributes to clinical applications for long-term maternal and fetal monitoring.

show abstract

Electrocardiogram signal classification for automated delineation using bidirectional long short-term memory

Cited by 26 publications

References 32 publications

Beat-to-Beat Electrocardiogram Waveform Classification Based on a Stacked Convolutional and Bidirectional Long Short-Term Memory

Beat-to-Beat Electrocardiogram Waveform Classification Based on a Stacked Convolutional and Bidirectional Long Short-Term Memory

Towards Automated Optimization of Residual Convolutional Neural Networks for Electrocardiogram Classification

Accurate Fetal QRS-Complex Classification from Abdominal Electrocardiogram Using Deep Learning

Contact Info

Product

Resources

About