Abstract
Abstract Heart rate variability (HRV) is a powerful measure to gain information on the activation of the central nervous system and is thus a strong indicator for the overall health and emotional state of a person. Currently, the gold standard for HRV analysis is the examination of R-peaks in electrocardiograms (ECG), which requires a placement of electrodes on the torso. This is often impracticable, especially for the use in daily routines or 24/7 measurements. Photoplethysmograms (PPG) are an alternative to ECG assessment and are easier to acquire, e.g. by using fitness trackers or smart watches. Nevertheless, PPG data is more susceptible to motion artifacts. Hence, goal of this work is to develop and evaluate an artificial neural network (ANN) approach to estimate the R-peak locations in complex PPG signals. Public data collections were used as benchmark to compare our ANN-based approach to state-of-the-art methods. Results show that ANNs can improve HRV estimation during motion. HRV estimations from baseline methods (decision-tree based and automatic multiscalebased peak detection) were compared with the best performing neural network (3L-GRU) using the TROIKA dataset with respect to reference parameters obtained from a manual selection of the peaks in ECG data. In most cases, the neural network based HRV estimation was closer to the reference HRV compared to baseline methods (lower μ and σ ) Also, σ is smaller for the best performing ANN approach across most HRV parameters. Inclusion of another PPG or acceleration channel did not affect HRV estimation. Although, the neural network learning approach outperforms conventional methods, the examined PPG-based HRV estimation has still accuracy limitations. Nonetheless, the proposed estimation approach opens up new directions for further improvement.
Highlights
Heart rate variability (HRV) is considered as an important parameter when it comes to the estimation of stress level or fitness state [1]
We evaluate complex Artificial Neural Networks (ANNs) for R-peak estimation and HRV approximation, explicitly excluding any pre-processing steps
The neural network based HRV estimation was closer to the reference HRV compared to baseline methods
Summary
Heart rate variability (HRV) is considered as an important parameter when it comes to the estimation of stress level or fitness state [1]. PPG signals are susceptible to motion artifacts. Employing PPGs, the change in blood volume can be detected by sending light using a LED through the skin and measuring the intensity of the light that is either reflected or transmitted over time. PPG waveforms can be used to observe respiratory rate, blood pressure and oxygen saturation in blood and may give further insight into diagnostic of cardiac diseases along with ECG [3,4]. An HRV can be determined considering the peak-to-peak (R-R) intervals in a PPG signal alone. Motion artifacts (yielding electrode displacements) and the complex physio-mechanical processes between the heart and the observed skin act as a strong filter, making the HRV estimation from PPG difficult. The goal of this work is to investigate to which extent PPG data can be used as a surrogate to ECG data in order to
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
