Noninvasive Classification of Blood Pressure Based on Photoplethysmography Signals Using Bidirectional Long Short-Term Memory and Time-Frequency Analysis

The photoplethysmography (PPG) method for continuous noninvasive measurements of blood pressure (BP) offers a more comfortable solution than conventional methods. The main challenge in using the PPG method is that its accuracy is greatly influenced by motion artifacts. In addition, the characteristics of PPG vary depending on physiological conditions; hence, the system must be calibrated to adjust for such changes. We attempt to address these limitations and propose a novel method for the classification of BP using a bidirectional long short-term memory (BLSTM) network with time-frequency (TF) analysis based on PPG signals. The TF analysis extracts information from PPG signals using a short-time Fourier transform (STFT) in the time domain to produce two features, namely, the instantaneous frequency and spectral entropy. Training the BLSTM network using TF features significantly improves the classification performance and decreases the training time. We classify 900 PPG waveform segment samples from 219 adult subjects into three classification levels: normotension (NT), prehypertension (PHT) and hypertension (HT). The results show that the proposed method is successful in the classification of BP with accuracy, sensitivity, and speciticity values of 97.33%, 100%, and 94.87%, respectively. The F1 scores of three BP classifications were 97.29%, 97.39%, and 93.93%, respectively. A comparison of current and previous approaches to the classification of BP is accomplished. Our proposed method achieves a higher accuracy than convolutional neural networks (CNNs), k-nearest neighbors (KNN), bagged tree, logistic regression, and AdaBoost tree methods.

[1]  Yong Lian,et al.  Towards a Continuous Non-Invasive Cuffless Blood Pressure Monitoring System Using PPG: Systems and Circuits Review , 2018, IEEE Circuits and Systems Magazine.

[2]  J. Talts,et al.  Continuous recording of the oscillometric mean arterial pressure by the differential servo system with two photoplethysmographic sensors , 2008, 2008 8th IEEE International Conference on BioInformatics and BioEngineering.

[3]  Xuan Zeng,et al.  A Machine Learning-Empowered System for Long-Term Motion-Tolerant Wearable Monitoring of Blood Pressure and Heart Rate With Ear-ECG/PPG , 2017, IEEE Access.

[4]  G. Youssef,et al.  Familial history of hypertension as a predictor of increased arterial stiffness in normotensive offspring , 2016, The Egyptian heart journal : (EHJ) : official bulletin of the Egyptian Society of Cardiology.

[5]  K H Blomqvist,et al.  Differential photoplethysmogram sensor with an optical notch filter shows potential for reducing motion artifact signals , 2018 .

[6]  Mostefa Mesbah,et al.  Heart Rate Variability Characterization Using a Time-Frequency Based Instantaneous Frequency Estimation Technique , 2007 .

[7]  Anh Dinh,et al.  Blood Pressure Measurement Using Finger ECG and Photoplethysmogram for IoT , 2017 .

[8]  Rabab Ward,et al.  An optimal filter for short photoplethysmogram signals , 2018, Scientific Data.

[9]  Tapio Taipalus,et al.  Comparison of photoplethysmogram measured from wrist and finger and the effect of measurement location on pulse arrival time , 2018, Physiological measurement.

[10]  Temel Kayikçioglu,et al.  An EEG-based stereoscopic research of the PSD differences in pre and post 2D&3D movies watching , 2020, Biomed. Signal Process. Control..

[11]  M. Omair Ahmad,et al.  A spectral entropy-based measure for performance evaluation of a first-order differential microphone array , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[12]  Zhiyong Cui,et al.  Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2018, ArXiv.

[13]  Mohamed Elgendi,et al.  Optimal Signal Quality Index for Photoplethysmogram Signals , 2016, Bioengineering.

[14]  U. Rajendra Acharya,et al.  A new approach for arrhythmia classification using deep coded features and LSTM networks , 2019, Comput. Methods Programs Biomed..

[15]  A. Al-Zaben,et al.  Detection of premature ventricular beats from arterial blood pressure signal , 2018, 2018 IEEE 4th Middle East Conference on Biomedical Engineering (MECBME).

[16]  Y. Ohno,et al.  A study on estimating blood pressure during body postural change based on pulse transit time , 2014, 2014 IEEE Healthcare Innovation Conference (HIC).

[17]  Einly Lim,et al.  Adaptive template matching of photoplethysmogram pulses to detect motion artefact , 2018, Physiological measurement.

[18]  Mohamed Elgendi,et al.  Descriptor : A new , short-recorded photoplethysmogram dataset for blood pressure monitoring in China , 2018 .

[19]  Gang Liu,et al.  Bidirectional LSTM with attention mechanism and convolutional layer for text classification , 2019, Neurocomputing.

[20]  Athipong Ngamjarurojana,et al.  Construction of Blood Pressure Monitor Using Photoplethysmography Calibrating with Upper-arm Blood Pressure Monitor , 2018 .

[21]  Yuhan Zhang,et al.  Acoustic Scene Classification Using Deep Audio Feature and BLSTM Network , 2018, 2018 International Conference on Audio, Language and Image Processing (ICALIP).

[23]  Haruki Kawanaka,et al.  Features Extraction for Cuffless Blood Pressure Estimation by Autoencoder from Photoplethysmography , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Anita Agrawal,et al.  Time-frequency based feature extraction for the analysis of vibroarthographic signals , 2018, Comput. Electr. Eng..

[25]  M. Elgendi,et al.  Photoplethysmography and Deep Learning: Enhancing Hypertension Risk Stratification , 2018, Biosensors.

[26]  N. Sriraam,et al.  Detection of alcoholic impact on visual event related potentials using beta band spectral entropy, repeated measures ANOVA and k-NN classifier , 2016, 2016 International Conference on Circuits, Controls, Communications and Computing (I4C).

[27]  R. Romulus.  A comparison between instantaneous frequency estimation methods of frequency modulated signals covered with Gaussian noise , 2012, 2012 10th International Symposium on Electronics and Telecommunications.

[28]  Yong Lian,et al.  Machine Learning Methods for Real-Time Blood Pressure Measurement Based on Photoplethysmography , 2018, 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP).

[29]  Sun K. Yoo,et al.  A Deep Neural Network-Based Pain Classifier Using a Photoplethysmography Signal , 2019, Sensors.

[30]  Se Dong Min,et al.  Feasibility study for the non-invasive blood pressure estimation based on ppg morphology: normotensive subject study , 2017, BioMedical Engineering OnLine.

[31]  Aniruddha Sinha,et al.  Blood pressure estimation from photoplethysmogram using latent parameters , 2016, 2016 IEEE International Conference on Communications (ICC).

[32]  Norbert Noury,et al.  A review of methods for non-invasive and continuous blood pressure monitoring: Pulse transit time method is promising? , 2014 .

[33]  Mahdi Shabany,et al.  Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring , 2017, IEEE Transactions on Biomedical Engineering.

[34]  Toshiyo Tamura,et al.  Current progress of photoplethysmography and SPO2 for health monitoring , 2019, Biomedical Engineering Letters.

[35]  Horacio Sanson,et al.  Non-invasive blood pressure estimation from photoplethysmography signals using artificial neural networks , 2018, 2018 20th International Conference on Advanced Communication Technology (ICACT).

[36]  Bo Wen,et al.  Multi-Sensor Fusion Approach for Cuff-Less Blood Pressure Measurement , 2020, IEEE Journal of Biomedical and Health Informatics.

[37]  Saso Koceski,et al.  Continuous Blood Pressure Monitoring as a Basis for Ambient Assisted Living (AAL) – Review of Methodologies and Devices , 2019, Journal of Medical Systems.

[38]  Yuan-Ting Zhang,et al.  Long-term blood pressure prediction with deep recurrent neural networks , 2017, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[39]  T. Penzel,et al.  Continuous non-invasive determination of nocturnal blood pressure variation using photoplethysmographic pulse wave signals: comparison of pulse propagation time, pulse transit time and RR-interval , 2019, Physiological measurement.

[40]  Mohamad Ivan Fanany,et al.  Combining deep belief networks and bidirectional long short-term memory: Case study: Sleep stage classification , 2017, 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI).

[41]  Sheng-Chieh Huang,et al.  A New Image Blood Pressure Sensor Based on PPG, RRT, BPTT, and Harmonic Balancing , 2014, IEEE Sensors Journal.

[43]  Ronald M. Aarts,et al.  Estimating blood pressure trends and the nocturnal dip from photoplethysmography , 2018, Physiological measurement.

[44]  Aniruddha Sinha,et al.  Estimating blood pressure using Windkessel model on photoplethysmogram , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[45]  Jiyu Cheng,et al.  Continuous systolic and diastolic blood pressure estimation utilizing long short-term memory network , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[46]  Mohamed Elgendi,et al.  Hypertension Assessment via ECG and PPG Signals: An Evaluation Using MIMIC Database , 2018, Diagnostics.

[47]  Po-Wei Huang,et al.  A Feature Selection Method for Vision-Based Blood Pressure Measurement , 2018, 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[48]  Zhan Zhao,et al.  Continuous blood pressure estimation based on multiple parameters from eletrocardiogram and photoplethysmogram by Back-propagation neural network , 2017, Comput. Ind..

[49]  Anagha Savkar,et al.  Study on Techniques Involved in Tourniqueteless Blood Pressure Measurement Using PPG , 2018, 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS).

[50]  Aniruddha Sinha,et al.  Smart phone based blood pressure indicator , 2014, MobileHealth '14.

[51]  Haruki Kawanaka,et al.  Separate estimation of long- and short-term systolic blood pressure variability from photoplethysmograph , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[52]  Kalamullah Ramli,et al.  Review of photoplethysmography based non-invasive continuous blood pressure methods , 2017, 2017 15th International Conference on Quality in Research (QiR) : International Symposium on Electrical and Computer Engineering.