Reconstruction of gastric slow wave from finger photoplethysmographic signal using radial basis function neural network

Abstract

Extraction of extra-cardiac information from photoplethysmography (PPG) signal is a challenging research problem with significant clinical applications. In this study, radial basis function neural network (RBFNN) is used to reconstruct the gastric myoelectric activity (GMA) slow wave from finger PPG signal. Finger PPG and GMA (measured using Electrogastrogram, EGG) signals were acquired simultaneously at the sampling rate of 100 Hz from ten healthy subjects. Discrete wavelet transform (DWT) was used to extract slow wave (0-0.1953 Hz) component from the finger PPG signal; this slow wave PPG was used to reconstruct EGG. A RBFNN is trained on signals obtained from six subjects in both fasting and postprandial conditions. The trained network is tested on data obtained from the remaining four subjects. In the earlier study, we have shown the presence of GMA information in finger PPG signal using DWT and cross-correlation method. In this study, we explicitly reconstruct gastric slow wave from finger PPG signal by the proposed RBFNN-based method. It was found that the network-reconstructed slow wave provided significantly higher (P < 0.0001) correlation (≥ 0.9) with the subject's EGG slow wave than the correlation obtained (≈0.7) between the PPG slow wave from DWT and the EEG slow wave. Our results showed that a simple finger PPG signal can be used to reconstruct gastric slow wave using RBFNN method.

Low Frequency Systemic Hemodynamic “Noise” in Resting State BOLD fMRI: Characteristics, Causes, Implications, Mitigation Strategies, and Applications

“…This finding is in good agreement with previous work by Yacin et al (2011) which showed a strong relationship between gastric activity and systemic LFOs in the periphery. Yacin was able to reconstruct the gastric slow wave signal from a fingertip photoplethysmogram, using a deep learning approach.…”

Assessment of the macrovascular contribution to resting-state fMRI functional connectivity at 3 Tesla

“…An earlier review article proposed the concept of systematic low-frequency oscillations (sLFOs), which are defined as a vasogenic low-frequency BOLD signal travelling through the brain (Tong et al, 2015). It appears that the oscillation originated outside the brain (Frederick and Tong, n.d.; Li et al, 2018; Tong and Frederick, 2010) and could be caused by vasomotion (Hundley et al, 1988; Mayhew et al, 1996; Rivadulla et al, 2011), heart-rate variability (Thayer et al, 2012), respiratory volume variability (Birn et al, 2006; Chang et al, 2009), gastric oscillations (Mohamed Yacin et al, 2011; Rebollo et al, 2018) and variations in carbon dioxide levels (Sassaroli et al, 2012; Wise et al, 2004). Furthermore, previous studies using near-infrared spectroscopy have shown that such oscillations travel through the vasculature, and that strong and vascular-specific spatial structures can be captured in the macrovasculature by regressing finger-tip oxygenation time courses with the whole-brain BOLD signal (Frederick et al, 2013; Tong et al, 2015, 2014, 2011a, 2011b, 2011c; Tong and Frederick, 2014, 2012).…”

“…These sLFOs permeate the brain volume, being particularly pronounced in the vasculature. The most commonly referenced contributors to the sLFOs would be vasomotion (Hundley et al, 1988; Mayhew et al, 1996; Rivadulla et al, 2011), heart rate (Thayer et al, 2012), respiratory volume variability (Birn et al, 2006; Chang et al, 2009), gastric oscillations (Mohamed Yacin et al, 2011; Rebollo et al, 2018) and variations in carbon dioxide levels (Sassaroli et al, 2012; Wise et al, 2004). Notably, previous observations of robust anti-correlations between arterial and venous BOLD signals in the low-frequency range (Tong et al, 2019b) demonstrated the contribution of arterial BOLD to the rs-fMRI correlational structure, overturning the long-held belief that arterial BOLD effects are negligible.…”

Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients

“…Neural networks are more and more widely used in medical sciences [ 37 , 42 , 45 , 54 , 60 ]. In cardiology, they are used, inter alia, to assess the status of cardiovascular system [ 43 ], to predict the risk of coronary heart disease [ 35 ] in ECG analysis [ 36 , 56 ] or echocardiography [ 59 ].…”