PPG Derived Respiratory Rate Estimation in Daily living Conditions

The use of successive systolic differences in photoplethysmographic (PPG) signals for respiratory rate estimation

Most PPG-based methods for extracting the respiratory rate (RR) rely on changes in the PPG signal's amplitude, baseline, or frequency. However, several other parameters may provide more valuable information for accurate RR computation. In this study, we explored the capabilities of the respiratory-induced variations in successive systolic differences (RISSDV) of PPG signals to estimate RR. We partitioned fifty-three publicly available recordings into eight 1-min segments and identified peaks and troughs of the PPG signals to quantify respiratory-induced variations in amplitude (RIAV), baseline (RIIV), frequency (RIFV), and peak-to-peak amplitude differences (RISSDV). RR values were extracted by determining the peak frequency of the power spectral density of the four variations and the reference respiratory signal. We assessed each feature's performance by computing the root-mean-squared (RMSE) and mean absolute errors (MAE). RISSDV errors were significantly lower than those of RIAV (RMSE and MAE: p < 0.001), RIIV (RMSE: p < 0.01; MAE p < 0.05), and RIFV (RMSE and MAE: p < 0.001), and it appeared less sensitive to absent or missed PPG pulses than respiratory-induced frequency variations. Further research is necessary to extrapolate these findings to subjects under ambulatory rather than stationary conditions, including pediatric and neonatal populations.

Machine Learning-Based Respiration Rate and Blood Oxygen Saturation Estimation Using Photoplethysmogram Signals

The continuous monitoring of respiratory rate (RR) and oxygen saturation (SpO2) is crucial for patients with cardiac, pulmonary, and surgical conditions. RR and SpO2 are used to assess the effectiveness of lung medications and ventilator support. In recent studies, the use of a photoplethysmogram (PPG) has been recommended for evaluating RR and SpO2. This research presents a novel method of estimating RR and SpO2 using machine learning models that incorporate PPG signal features. A number of established methods are used to extract meaningful features from PPG. A feature selection approach was used to reduce the computational complexity and the possibility of overfitting. There were 19 models trained for both RR and SpO2 separately, from which the most appropriate regression model was selected. The Gaussian process regression model outperformed all the other models for both RR and SpO2 estimation. The mean absolute error (MAE) for RR was 0.89, while the root-mean-squared error (RMSE) was 1.41. For SpO2, the model had an RMSE of 0.98 and an MAE of 0.57. The proposed system is a state-of-the-art approach for estimating RR and SpO2 reliably from PPG. If RR and SpO2 can be consistently and effectively derived from the PPG signal, patients can monitor their RR and SpO2 at a cheaper cost and with less hassle.

Lightweight End-to-End Deep Learning Solution for Estimating the Respiration Rate from Photoplethysmogram Signal

Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients.