Personalized Blood Pressure Estimation Using Photoplethysmography: A Transfer Learning Approach

Advances in Cuffless Continuous Blood Pressure Monitoring Technology Based on PPG Signals

“…First, the poor signals can be removed by some empirical values, such as limiting systolic blood pressure (SBP) and diastolic blood pressure (DBP) to 80-180 mmHg and 60-130 mmHg, respectively [ 26 , 27 ], deleting the PPG signals with heart rate below 60 beats per minute [ 28 ], and rejecting outliers by using quartile [ 29 ] or 3-sigma criterion [ 30 ]. Moreover, considering the periodicity of PPG, some researches adopted autocorrelation between PPG periodic signals [ 31 ], dynamic time warping [ 32 ], or high-order statistics, such as skewness and kurtosis [ 33 , 34 ], to further standardize the quality of PPG signals…”

“…The proposed model was tested on 39 subjects in MIMIC I and achieved an MAE of 1.10 mmHg for SBP and 0.58 mmHg for DBP. Besides, the network proposed by Leitner et al [ 31 ] adopted a gated recurrent unit (GRU) instead of the LSTM on the basis of the CNN-LSTM framework, because GRU has similar functions and slightly different parameters with LSTM. The proposed model was validated on long-term data of 100 subjects in the MIMIC dataset, combined with transfer learning-based calibration techniques, and resulted in an MAE of 3.52 and 2.20 mmHg for SBP and DBP, respectively.…”

“…First, the poor signals can be removed by some empirical values, such as limiting systolic blood pressure (SBP) and diastolic blood pressure (DBP) to 80-180 mmHg and 60-130 mmHg, respectively [26,27], deleting the PPG signals with heart rate below 60 beats per minute [28], and rejecting outliers by using quartile [29] or 3-sigma criterion [30]. Moreover, considering the periodicity of PPG, some researches adopted autocorrelation between PPG periodic signals [31], dynamic time warping [32], or high-order statistics, such as skewness and kurtosis [33,34], to further standardize the quality of PPG signals (4) Normalization: converting the amplitude of the PPG signal to the range of [0-1] can simplify and enhance the analysis process of the PPG signal and ensure that the extracted values are meaningful and fair to the subsequent characterization process. The normalization methods of these studies are relatively uniform, with some using the method in formula (5) to convert the amplitude of the PPG signal to 0-1 [35] and others normalizing the PPG signal to have a mean of 0 and a variance of 1 [21]: where x i ′ refers to the amplitude of the sample after conversion, x i refers to the original amplitude of the sample, and min ðxÞ and max ðxÞ are the minimum and the maximum amplitude in the set of samples, respectively 3.2.…”

Photoplethysmogram Recording Length: Defining Minimal Length Requirement from Dynamical Characteristics

“…Additionally, in many practical cases, lower-sampling-rate PPG data are used [ 45 , 46 , 47 ]. To broaden the applicability of this study, collected PPG recordings were two- and four-times subsampled to generate sparse PPG time series.…”

“…Examples of the resulting time series obtained using the original (𝜃 = 0) and noisy (𝜃 = 0.25) x time series are shown in Figure 3, where the addition of dynamical noise affected the amplitude of the time series and created additional fluctuations compared to the original time series. Additionally, in many practical cases, lower-sampling-rate PPG data are used [45][46][47].…”