Separating arterial and venous-related components of photoplethysmographic signals for accurate extraction of oxygen saturation and respiratory rate

A Review of Deep Learning-Based Contactless Heart Rate Measurement Methods

The interest in contactless or remote heart rate measurement has been steadily growing in healthcare and sports applications. Contactless methods involve the utilization of a video camera and image processing algorithms. Recently, deep learning methods have been used to improve the performance of conventional contactless methods for heart rate measurement. After providing a review of the related literature, a comparison of the deep learning methods whose codes are publicly available is conducted in this paper. The public domain UBFC dataset is used to compare the performance of these deep learning methods for heart rate measurement. The results obtained show that the deep learning method PhysNet generates the best heart rate measurement outcome among these methods, with a mean absolute error value of 2.57 beats per minute and a mean square error value of 7.56 beats per minute.

Perfusion Changes at the Forehead Measured by Photoplethysmography during a Head-Down Tilt Protocol

Photoplethysmography (PPG) signals from the forehead can be used in pulse oximetry as they are less affected by vasoconstriction compared to fingers. However, the increase in venous blood caused by the positioning of the patient can deteriorate the signals and cause erroneous estimations of the arterial oxygen saturation. To date, there is no method to measure this venous presence under the PPG sensor. This study investigates the feasibility of using PPG signals from the forehead in an effort to estimate relative changes in haemoglobin concentrations that could reveal these posture-induced changes. Two identical reflectance PPG sensors were placed on two different positions on the forehead (above the eyebrow and on top of a large vein) in 16 healthy volunteers during a head-down tilt protocol. Relative changes in oxygenated (ΔHbO2), reduced (ΔHHb) and total (ΔtHb) haemoglobin were estimated from the PPG signals and the trends were compared with reference Near Infrared Spectroscopy (NIRS) measurements. Also, the signals from the two PPG sensors were analysed in order to reveal any difference due to the positioning of the sensor. ΔHbO2, ΔHHb and ΔtHb estimated from the forehead PPGs trended well with the same parameters from the reference NIRS. However, placing the sensor over a large vasculature reduces trending against NIRS, introduces biases as well as increases the variability of the changes in ΔHHb. Forehead PPG signals can be used to measure perfusion changes to reveal venous pooling induced by the positioning of the subject. Placing the sensor above the eyebrow and away from large vasculature avoids biases and large variability in the measurements.

Design and Implementation of Respiration Rate Measurement System Using an Information Filter on an Embedded Device

In this work, an algorithm was developed to measure respiration rate for an embedded device that can be used by a field robot for relief operations. With this algorithm, the rate measurement was calculated based on direct influences of respiratory-induced intensity variation (RIIV) on blood flow in cardiovascular pathways. For this, a photoplethysmogram (PPG) sensor was used to determine changes in heartbeat frequencies. The PPG sensor readings were filtered using an Information Filter and a fast Fourier transform (FFT) to determine the state of RIIV. With a relatively light initialization, the information filter can estimate unknown variables based on a series of measurements containing noise and other inaccuracies. Therefore, this filter is suitable for application in an embedded device. For faster calculation time in the implementation, the FFT analysis was calculated only for a major peak in frequency domain. Test and measurement of respiration rate was conducted based on the device algorithm and spirometer. Heartbeat measurements were also evaluated by comparing the heartbeat data of the PPG sensor and pulse-oximeter. Based on the test, the implemented algorithm can measure the respiration rate with approximately 80% accuracy compared with the spirometer.

A Portable, Wireless Photoplethysomography Sensor for Assessing Health of Arteriovenous Fistula Using Class-Weighted Support Vector Machine

A portable, wireless photoplethysomography (PPG) sensor for assessing arteriovenous fistula (AVF) by using class-weighted support vector machines (SVM) was presented in this study. Nowadays, in hospital, AVF are assessed by ultrasound Doppler machines, which are bulky, expensive, complicated-to-operate, and time-consuming. In this study, new PPG sensors were proposed and developed successfully to provide portable and inexpensive solutions for AVF assessments. To develop the sensor, at first, by combining the dimensionless number analysis and the optical Beer Lambert’s law, five input features were derived for the SVM classifier. In the next step, to increase the signal-noise ratio (SNR) of PPG signals, the front-end readout circuitries were designed to fully use the dynamic range of analog-digital converter (ADC) by controlling the circuitries gain and the light intensity of light emitted diode (LED). Digital signal processing algorithms were proposed next to check and fix signal anomalies. Finally, the class-weighted SVM classifiers employed five different kernel functions to assess AVF quality. The assessment results were provided to doctors for diagonosis and detemining ensuing proper treatments. The experimental results showed that the proposed PPG sensors successfully achieved an accuracy of 89.11% in assessing health of AVF and with a type II error of only 9.59%.

Breathing Rate Estimation From the Electrocardiogram and Photoplethysmogram: A Review

Breathing rate (BR) is a key physiological parameter used in a range of clinical settings. Despite its diagnostic and prognostic value, it is still widely measured by counting breaths manually. A plethora of algorithms have been proposed to estimate BR from the electrocardiogram (ECG) and pulse oximetry (photoplethysmogram, PPG) signals. These BR algorithms provide opportunity for automated, electronic, and unobtrusive measurement of BR in both healthcare and fitness monitoring. This paper presents a review of the literature on BR estimation from the ECG and PPG. First, the structure of BR algorithms and the mathematical techniques used at each stage are described. Second, the experimental methodologies that have been used to assess the performance of BR algorithms are reviewed, and a methodological framework for the assessment of BR algorithms is presented. Third, we outline the most pressing directions for future research, including the steps required to use BR algorithms in wearable sensors, remote video monitoring, and clinical practice.

Estimation of instantaneous venous blood saturation using the photoplethysmograph waveform

Non-invasive estimation of regional venous saturation (SxvO2) using a conventional pulse oximeter could provide a means of obtaining clinically relevant information. This study was carried out in order to investigate the hypothesis that SxvO2 could be estimated by utilising the modulations created by positive pressure ventilation in the photoplethysmograph (PPG) signals. The modulations caused by the mechanical ventilator were extracted from oesophageal PPG signals obtained from 12 patients undergoing cardiothoracic surgery. The signals analysed in this work were acquired in a previous study. For the purpose of this analysis the raw PPG signal was considered to have three major components, ac PPG signal (cardiac related component), a static component or dc PPG signal (created mostly by the absorption of light by surrounding tissue) and the ventilator modulation component. These components were then used to estimate instantaneous arterial blood oxygen saturation (SpO2) and SxvO2 by utilising time-frequency analysis technique of smoothed-pseudo Wigner-Ville distribution (SPWVD). The results showed that there was no significant difference in the traditionally-derived (time-domain) arterial saturation and the instantaneous arterial saturation. However, the instantaneous venous saturation was found to be significantly lower than the estimated time-domain and instantaneous arterial saturation (P   =  < 0.001, n = 12).