PPG-Based Systolic Blood Pressure Estimation Method Using PLS and Level-Crossing Feature

Abstract

This paper proposes a cuff-less systolic blood pressure (SBP) estimation method using partial least-squares (PLS) regression. Level-crossing features (LCFs) were used in this method, which were extracted from the contour lines arbitrarily drawn on the second-derivative photoplethysmography waveform. Unlike conventional height ratio features (HRFs), which are extracted on the basis of the peaks in the waveform, LCFs can be reliably extracted even if there are missing peaks in the waveform. However, the features extracted from adjacent contour lines show similar trends; thus, there is a strong correlation between the features, which leads to multicollinearity when conventional multiple regression analysis (MRA) is used. Hence, we developed a multivariate estimation method based on PLS regression to address this issue and estimate the SBP on the basis of the LCFs. Two-hundred-and-sixty-five subjects (95 males and 170 females [(Mean ± Standard Deviation) SBP: 133.1 ± 18.4 mmHg; age: 62.8 ± 16.8 years] participated in the experiments. Of the total number of subjects, 180 were considered as learning data, while 85 were considered as testing data. The values of the correlation coefficient between the measured and estimated values were found to be 0.78 for the proposed method (LCFs + PLS), 0.58 for comparison method 1 (HRFs + MRA), and 0.62 for comparison method 2 (HRFs + MRA). The proposed method was therefore found to demonstrate the highest accuracy among the three methods being compared.

Portable Sensor System for Registration, Processing and Mathematical Analysis of PPG Signals

“…In the study [27], the authors analyze PPG data that were obtained from the right forefinger of healthy people and propose a method for improving the accuracy of blood pressure measurement.…”

Blood pressure prediction by exploiting informative features from ICU patients’ ECG and PPG signals under a heterogeneous ensemble learning framework

“…Feature extraction plays significant role in traditional ML, extracting valid and informative features that are most relevant to the prediction task is crucial for training an accurate prediction model. Therefore, features [22], [24], [27], [37], [55] were systematically extract from PPG and ECG signals.…”

“…S et al [21] used Kmeans singular value decomposition (K-SVD) as an alternative method of feature extraction to learn the sparse representation of the signal from PPG and then use the learned sparse representation as features to train a prediction model. Fujita et al [22] extracted level-crossing features (LCFs) from the second derivative waveform of PPG, and then these LCFs were used to train a partial least-squares regression model. The results exhibited that this model is superior to multiple regression analysis).…”

“…Slapnicar et al [33] designed a complex convolution network with raw PPG signal and its first and second derivatives as inputs, in an attempt to train the prediction model using a large database-MIMICIII. According to the signals used, above works can be grouped into three types of PPG based [10], [13], [15], [21,22], [28], [33], ECG based [14], [23] and PPG and ECG based [12], [16], [19,20], [24], [27], [30], [32]. ECG contains abundant electronic activities and can assist PPG to better predict BP.…”

Evaluation of the Possible Use of PPG Waveform Features Measured at Low Sampling Rate

“…Research into arterial stiffness has reported on age, vasoactive drugs, diseases such as arteriosclerosis and diabetes, and changes in PPG waveforms [18]. Moreover, substantial research is being conducted on cuff-less blood pressure estimation using PPG waveform features [2], [19], [20]. To obtain detailed features from PPG waveforms, these research efforts used a dedicated sensor at a comparatively high sampling rate for PPG measurement.…”