What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular monitoring (ECG reconstruction) (n=12000). Intervention: HA-CNN-BiLSTM deep learning network vs. ConvBiLSTM and other hybrid DNN models. Primary outcome: Root Mean Square Error (RMSE) of reconstructed ECG signal.

November 5, 2024EURASIP Journal on Advances in Signal Processing9 citationsOpen Access

ECG signal reconstruction from PPG using a hybrid attention-based deep learning network

AEAhmed A. EzzatHigher Institute of Engineering OOOsama A. OmerAswan University USUsama SayedNanjing Forestry University

Key Result

The proposed HA-CNN-BiLSTM deep learning network reconstructed ECG signals from PPG signals with a superior root mean square error of 0.031 using the SGDM optimizer.

Structured PICO

Does a hybrid attention-based CNN and BiLSTM model improve the reconstruction of ECG signals from PPG signals compared to state-of-the-art methods?

Intervention

Hybrid attention-based bidirectional recurrent neural network (Bi-RNN) incorporating a dilated convolutional neural network (HA-CNN-BiLSTM) for reconstructing ECG signals from PPG signals

Comparator

Separate state-of-the-art methods (e.g., standard dilated CNN, ConvBiLSTM, ResNet+Bi-LSTM)

Outcome

Root mean square error (RMSE) of the reconstructed ECG signalsurrogate

The proposed HA-CNN-BiLSTM deep learning model accurately reconstructs ECG signals from PPG signals with a low RMSE of 0.031, potentially enabling continuous, non-invasive cardiac monitoring using simple wearable devices.

Main Result

Absolute Event Rate: 0.031% vs 0.0346%

Limitations

ECG data or beats that display substantial distortion must be excluded from analysis

Abstract

Electrocardiography (ECG) and photoplethysmography (PPG) are non-invasive methods used to quantify signals originating from the cardiovascular system. Although there is a strong correlation between the cycles of the two measures, the correlation between the waveforms has received little attention in research. Measuring the PPG is significantly simpler and more convenient compared to the ECG measure. Recent research has demonstrated that PPG signals can be utilized to rebuild the ECG signals, suggesting that healthcare professionals might acquire a comprehensive comprehension of patients' cardiovascular well-being by only measuring PPG. With the advancement of artificial intelligence, the deep learning model has made significant progress in reconstructing ECG signals from PPG signals. However, the quality of the reconstructed ECG signal is still in need of more enhancement. In order to enhance the quality of the reconstructed ECG signal, we propose an innovative hybrid attention-based bidirectional recurrent neural network (Bi-RNN) that incorporates a dilated convolutional neural network technique for the purpose of reconstructing ECG signals from PPG signals. This addresses issues that occur when standard dilated CNN (DCNN) models neglect the link between circumstances and dispersion of gradients. The suggested approach maximizes the utilization of the DCNN and Bi-RNN unit design to provide fusion features. In order to ensure the model's resilience to deformation, it is imperative to initially extract spatial properties utilizing convolutional neural networks (CNNs). Once we have obtained geographic data, we employ BiLSTM to extract temporal features. The proposed model is so-called hybrid attention-based CNN and BiLSTM (HA-CNN-BiLSTM). BiLSTM mitigates the issues of gradient vanishing and exploding while maintaining accuracy. To showcase the advantages of the suggested model, we conduct a comparison between HA-CNN-BiLSTM and each separate state-of-the-art method. The simulation results indicated that the proposed method yielded superior root mean square error (RMSE) when reconstructing the ECG signal across different optimizers. The results also demonstrated that the proposed method results in the lowest RMSE with SGDM optimizer which is 0.031.

Ask AI

Helpful

Bookmark

View Full Paper