Subject-Independent per Beat PPG to Single-Lead ECG Mapping

Abstract

In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in the training stage entirely, i.e., a subject record appears once either in the training or testing set, but testing beats/signals belong to records that never appear in the training set. The proposed deep learning model is designed for providing efficient feature extraction that attains high reconstruction quality over subject-independent scenarios. The achieved performance is about 0.92 for the correlation coefficient and 0.0086 for the mean square error for the dataset extracted/cleaned from the MIMIC II dataset.

Reconstruction of Missing Electrocardiography Signals from Photoplethysmography Data Using Deep Neural Network

“…The accuracy of these methods depends on the accuracy of the R wave in ECG and contraction seam extraction algorithms in PPG, which can reduce the accuracy of ECG reconstruction. The computational parametric model [8], lightweight neural network [9], deep learning models based on encoder-decoder [10], BiLSTM [11], PPG2ECGps [12], P2E-WGAN [13], CardioGAN [14], Performer [15], transformed attentional neural network [16], and banded kernel ensemble method [17] have been proposed for reconstructing electrocardiograms from PPG based on deep learning methods. In [8], the author proposed a computational parametric model that extracts features from PPG to predict ECG parameters.…”

“…Although their system estimates ECG parameters with over 90% accuracy on benchmark hospital datasets, the need for complete ECG waveform reconstruction is a barrier to the widespread adoption of their system. Two studies [9,10] took the beat-to-beat reconstruction of ECG from PPG as a basis, segmenting beats based on the signal period during preprocessing. However, cycle alignment and segmentation result in loss of temporal information, such as pulse transit time and heart rate variability, which are essential clinical factors.…”

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

“…Consequently, considerable research efforts have been recently conducted on finding comfortable and accurate means for BP self-monitoring constantly in a non-clinical environment [9,10]. In this context, photoplethysmography (PPG) signal [11,12] exhibits an essential role in the non-invasive and continuous monitoring of many vital signs [13] such as heart rate variability [14], respiration rate [15], blood pressure [16,17], electrocardiogram (ECG) reconstruction [18][19][20], hemoglobin level [21], and oxygen saturation level (SpO2) [22]. Motivated by PPG extraction simplicity, many wearable devices [23][24][25][26] are introduced for predicting these physiological vital signs from the PPG signal that represents changes in the volume of the blood inside the arteries due to heart pulsation.…”

UNet-BiLSTM: A Deep Learning Method for Reconstructing Electrocardiography from Photoplethysmography

“…Several studies utilized the discrete cosine transform (DCT) method [9], P2E-WGAN model [14], CardioGAN model [15], scattering wavelet transform (SWT) method [16], and PPG2ECG model [17] to reconstruct ECG signals for group models. The DCT [9] and SWT [16] model used a beat-to-beat method to reconstruct ECG signals.…”