Photoplethysmography-Based Respiratory Rate Estimation Algorithm for Health Monitoring Applications

Abstract

Purpose Respiratory rate can provide auxiliary information on the physiological changes within the human body, such as physical and emotional stress. In a clinical setup, the abnormal respiratory rate can be indicative of the deterioration of the patient's condition. Most of the existing algorithms for the estimation of respiratory rate using photoplethysmography (PPG) are sensitive to external noise and may require the selection of certain algorithm-specific parameters, through the trial-and-error method. Methods This paper proposes a new algorithm to estimate the respiratory rate using a photoplethysmography sensor signal for health monitoring. The algorithm is resistant to signal loss and can handle low-quality signals from the sensor. It combines selective windowing, preprocessing and signal conditioning, modified Welch filtering and postprocessing to achieve high accuracy and robustness to noise. Results The Mean Absolute Error and the Root Mean Square Error of the proposed algorithm, with the optimal signal window size, are determined to be 2.05 breaths count per minute and 2.47 breaths count per minute, respectively, when tested on a publicly available dataset. These results present a significant improvement in accuracy over previously reported methods. The proposed algorithm achieved comparable results to the existing algorithms in the literature on the BIDMC dataset (containing data of 53 subjects, each recorded for 8 min) for other signal window sizes. Conclusion The results endorse that integration of the proposed algorithm to a commercially available pulse oximetry device would expand its functionality from the measurement of oxygen saturation level and heart rate to the continuous measurement of the respiratory rate with good efficiency at home and in a clinical setting.

Stress Monitoring Using Wearable Sensors: A Pilot Study and Stress-Predict Dataset

“…The created dataset is different from all existing public datasets, as it included information on the estimated RR for each participant. As explained in [ 24 ], the study proposed a novel RR-estimating algorithm that worked on raw PPG signals. As BVP is a filtered form of raw PPG signal, the developed algorithm was able to estimate the RR of the participants during stress, as well as rest/baseline time.…”

“…Peak detection, peak-to-peak interval, error and correction in peak detection, calculation of time-series measurement and estimation of RR were carried out during the signal analysis stage. Usually, the BVP waveform is synchronised with the respiratory cycle [ 24 ]; thus, an amplitude variation is induced in the raw signal. In the post-processing stage, the estimated RR is scaled based on the range (maximum-minimum value) and defined window size of the signal.…”

“…The key contributions of this study are as follows: Collected PPG signals using an Empatica E4 watch (a wrist-worn device) and developed an open-access dataset. Estimated respiratory rate readings from the raw signal using a novel PPG-based respiratory rate estimation algorithm [ 24 ] and included them in the dataset. Performed individual-level statistical analysis using a novel method based on the Bayesian framework and time-efficient approximate Expectation-Maximisation (EM) algorithm [ 25 ].…”

“…Estimated respiratory rate readings from the raw signal using a novel PPG-based respiratory rate estimation algorithm [ 24 ] and included them in the dataset.…”

An Ex Vivo Study of Wireless Linkage Distance between Implantable LC Resonance Sensor and External Readout Coil

“…In addition to these state-of-the-art solutions, various wearable and implantable systems with miniature sensors to monitor the body parameters have been developed to record the heart rate [ 10 ], temperature [ 11 , 12 , 13 ], pH [ 13 , 14 , 15 ], pressure [ 16 , 17 ], blood flow [ 18 ], and respiration rates [ 19 , 20 ]. These solutions are flexible [ 21 ], bendable [ 22 ], stretchable [ 23 , 24 , 25 ], and biocompatible, making them suitable for both wearable and implantable applications [ 26 , 27 , 28 ].…”