Estimating SpO2 via Time-Efficient High-Resolution Harmonics Analysis and Maximum Likelihood Tracking.

The accuracy of noninvasive oxygen saturation (SpO2), which is defined by the measurements based on photoplethysmographic (PPG) signals, is intensively affected by motion artifacts (MAs) and low perfusion. This study introduces a novel approach called ESPRIT-MLT to measure SpO2 when such interferences are present. In contrast to previous studies, the work focuses on the harmonic model of the PPG signal and the probability model of results from harmonic analysis. The optimized parametric ESPRIT method is applied to improve the accuracy of harmonic power estimation, and the maximum likelihood SpO2 tracking (MLT) technique is proposed to track the most probable uncontaminated harmonic of heart rate frequency. We construct an evaluation platform for testing the proposed method via generated signals and subject tests. Compared with the nonparametric periodogram method, the probability of correct harmonics being found is improved by 18.7% or 19.7%, when the signal is contaminated by motion artifacts or affected by low perfusion, respectively. In comparison with the reference methods, the proposed ESPRIT-MLT method exhibits a lower average root mean square error (RMSE) (1.17%) in the simulation using an MA-contaminated PPG signal, and a lower RMSE (2.70%) in the simulation using an extremely low (0.05%) perfusion index. A comprehensive subject test that consists of 4 activities and 20 subjects shows an average RMSE of 0.84% ( 0.44%). Furthermore, the time-efficiency is optimized to be adaptable with wearable devices. Therefore, the proposed method has potential in enhancing the performance of clinical pulse oximetry and wearable SpO2 measurement devices for daily use.

A motion-tolerant approach for monitoring SpO2 and heart rate using photoplethysmography signal with dual frame length processing and multi-classifier fusion.

Monitoring pulse oxygen saturation (SpO2) and heart rate (HR) using photoplethysmography (PPG) signal contaminated by a motion artifact (MA) remains a difficult problem, especially when the oximeter is not equipped with a 3-axis accelerometer for adaptive noise cancellation. In this paper, we report a pioneering investigation on the impact of altering the frame length of Molgedey and Schuster independent component analysis (ICAMS) on performance, design a multi-classifier fusion strategy for selecting the PPG correlated signal component, and propose a novel approach to extract SpO2 and HR readings from PPG signal contaminated by strong MA interference. The algorithm comprises multiple stages, including dual frame length ICAMS, a multi-classifier-based PPG correlated component selector, line spectral analysis, tree-based HR monitoring, and post-processing. Our approach is evaluated by multi-subject tests. The root mean square error (RMSE) is calculated for each trial. Three statistical metrics are selected as performance evaluation criteria: mean RMSE, median RMSE and the standard deviation (SD) of RMSE. The experimental results demonstrate that a shorter ICAMS analysis window probably results in better performance in SpO2 estimation. Notably, the designed multi-classifier signal component selector achieved satisfactory performance. The subject tests indicate that our algorithm outperforms other baseline methods regarding accuracy under most criteria. The proposed work can contribute to improving the performance of current pulse oximetry and personal wearable monitoring devices.