Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we use this parameterization to train NNs with a larger PPG dataset and carry out a systematic evaluation of the predicted blood pressure. The analysis revealed a strong systematic increase of the prediction error towards less frequent BP values across NN architectures. Moreover, we tested different train/test set split configurations which underpin the importance of a careful subject-aware dataset assignment to prevent overly optimistic results. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply different personalization techniques and retrain our NNs with subject-specific data for both the PPG-only and rPPG case. Whilst the particular technique is less important, personalization reduces the prediction errors significantly.

Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning.

Deep generative model with domain adversarial training for predicting arterial blood pressure waveform from photoplethysmogram signal

Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera-based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG-based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we apply this parameterization to a larger PPG dataset and train NNs to predict BP. The resulting prediction errors increase towards less frequent BP values. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply a personalization technique and retrain our NNs with subject-specific data. This slightly reduces the prediction errors.

/pdf/assessment-of-deep-learning-based-blood-pressure-prediction-3csa8oh75a.pdf

Assessment of deep learning based blood pressure prediction from PPG and rPPG signals

Prediction of arterial blood pressure waveforms from photoplethysmogram signals via fully convolutional neural networks.

Recent works on the machine learnings designed for cuffless blood pressure (BP) estimation based on measured photoplethysmogram (PPG) waveforms are reviewed by this study, with future trends of the related technology developments distilled. This review starts with those based on the conventional pulse wave velocity (PWV) theory, by which few equations are derived to calculate BPs based on measured pulse arrival times (PATs) and/or pulse transit time (PTT). Due to the inadequacy of PATs and PPTs to characterize BP, some works were reported to employ more features in PPG waveforms to achieve better accuracy. In these works, varied machine learnings were adopted, such as support vector machine (SVM), regression tree (RT), adaptive boosting (AdaBoost), and artificial neural network (ANN), etc., resulting in satisfactory accuracies based on a large number of data in the databases of Queensland and/or MIMIC II. Most recently, a few studies reported to utilize the deep learning machines like convolution neural network (CNN), recursive neural network (RNN), and long short-term memory (LSTM), etc., to handle feature extraction and establish models integrally, with the aim to cope with the inadequacy of pre-determined (hand-crafted) features to characterize BP and the difficulty of extracting pre-determined features by a designed algorithm. Therefore, the deep learning opens an opportunity of achieving much better BP accuracy by using a single PPG sensor. Favorable accuracies have been resulted by these few studies in comparison with prior works. Finally, future research efforts needed towards successful commercialization of the cuffless BP sensor are distilled.

The Machine Learnings Leading the Cuffless PPG Blood Pressure Sensors Into the Next Stage

Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms (ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works.

https://www.mdpi.com/1424-8220/20/19/5668/pdf

Yan Cheng Hsu

Papers

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only.