Non-Invasive Hemodynamics Monitoring System Based on Electrocardiography via Deep Convolutional Autoencoder

This study evaluates cardiovascular and cerebral hemodynamics systems by only using non-invasive electrocardiography (ECG) signals. The Massachusetts General Hospital/Marquette Foundation (MGH/MF) and Cerebral Hemodynamic Autoregulatory Information System Database (CHARIS DB) from the PhysioNet database are used for cardiovascular and cerebral hemodynamics, respectively. For cardiovascular hemodynamics, the ECG is used for generating the arterial blood pressure (ABP), central venous pressure (CVP), and pulmonary arterial pressure (PAP). Meanwhile, for cerebral hemodynamics, the ECG is utilized for the intracranial pressure (ICP) generator. A deep convolutional autoencoder system is applied for this study. The cross-validation method with Pearson’s linear correlation (R), root mean squared error (RMSE), and mean absolute error (MAE) are measured for the evaluations. Initially, the ECG is used to generate the cardiovascular waveform. For the ABP system—the systolic blood pressure (SBP) and diastolic blood pressures (DBP)—the R evaluations are 0.894 ± 0.004 and 0.881 ± 0.005, respectively. The MAE evaluations for SBP and DBP are, respectively, 6.645 ± 0.353 mmHg and 3.210 ± 0.104 mmHg. Furthermore, for the PAP system—the systolic and diastolic pressures—the R evaluations are 0.864 ± 0.003 mmHg and 0.817 ± 0.006 mmHg, respectively. The MAE evaluations for systolic and diastolic pressures are, respectively, 3.847 ± 0.136 mmHg and 2.964 ± 0.181 mmHg. Meanwhile, the mean CVP evaluations are 0.916 ± 0.001, 2.220 ± 0.039 mmHg, and 1.329 ± 0.036 mmHg, respectively, for R, RMSE, and MAE. For the mean ICP evaluation in cerebral hemodynamics, the R and MAE evaluations are 0.914 ± 0.003 and 2.404 ± 0.043 mmHg, respectively. This study, as a proof of concept, concludes that the non-invasive cardiovascular and cerebral hemodynamics systems can be potentially investigated by only using the ECG signal.

[1]  Jiann-Shing Shieh,et al.  Genetic Deep Convolutional Autoencoder Applied for Generative Continuous Arterial Blood Pressure via Photoplethysmography , 2020, Sensors.

[2]  B. Gerber,et al.  Electrocardiographic changes after head trauma. , 2005, Journal of Electrocardiology.

[3]  P. Podolec,et al.  ECG Markers of Hemodynamic Improvement in Patients with Pulmonary Hypertension , 2018, BioMed research international.

[4]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[5]  Xiaomao Fan,et al.  An Adaptive Weight Learning-Based Multitask Deep Network for Continuous Blood Pressure Estimation Using Electrocardiogram Signals , 2021, Sensors.

[6]  J. Thiran,et al.  Non-invasive pulmonary artery pressure estimation by electrical impedance tomography in a controlled hypoxemia study in healthy subjects , 2020, Scientific Reports.

[7]  S. Meek,et al.  Introduction. I—Leads, rate, rhythm, and cardiac axis , 2002, BMJ : British Medical Journal.

[8]  Maysam F. Abbod,et al.  Computational Depth of Anesthesia via Multiple Vital Signs Based on Artificial Neural Networks , 2015, BioMed research international.

[9]  Thomas Heldt,et al.  Pseudo-Bayesian Model-Based Noninvasive Intracranial Pressure Estimation and Tracking , 2020, IEEE Transactions on Biomedical Engineering.

[10]  Bob D. de Vos,et al.  State-of-the-Art Deep Learning in Cardiovascular Image Analysis. , 2019, JACC. Cardiovascular imaging.

[11]  E. Frohlich,et al.  Electrocardiographic Changes Reflecting Left Atrial Abnormality in Hypertension , 1966, Circulation.

[12]  R. Kalbag,et al.  Electrocardiographic abnormalities associated with raised intracranial pressure. , 1975, British medical journal.

[13]  Md. Kamrul Hasan,et al.  Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network , 2018, Biomed. Signal Process. Control..

[14]  Zhong Ji,et al.  Non-Invasive Continuous Blood-Pressure Monitoring Models Based on Photoplethysmography and Electrocardiography , 2019, Sensors.

[15]  S. L. Miller,et al.  Traumatic Subarachnoid Hemorrhage and QTc Prolongation , 2004, Journal of neurosurgical anesthesiology.

[16]  W. Craelius,et al.  Trending autoregulatory indices during treatment for traumatic brain injury , 2016, Journal of Clinical Monitoring and Computing.

[17]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[18]  F Golliot,et al.  Complications of femoral and subclavian venous catheterization in critically ill patients: a randomized controlled trial. , 2001, JAMA.

[19]  Majid Sarrafzadeh,et al.  Building Continuous Arterial Blood Pressure Prediction Models Using Recurrent Networks , 2016, 2016 IEEE International Conference on Smart Computing (SMARTCOMP).

[20]  Thomas Heldt,et al.  A Spectral Approach to Model-Based Noninvasive Intracranial Pressure Estimation , 2019, IEEE Journal of Biomedical and Health Informatics.

[21]  A. V. van Vliet,et al.  Hypertensive crisis-induced electrocardiographic changes: a case series , 2009, Journal of medical case reports.

[22]  Edith Grall-Maës,et al.  Blood Pressure Morphology Assessment from Photoplethysmogram and Demographic Information Using Deep Learning with Attention Mechanism , 2021, Sensors.

[23]  G. Ross EFFECT OF HYPERTENSION ON THE P WAVE OF THE ELECTROCARDIOGRAM , 1963, British heart journal.

[24]  Mitja Lustrek,et al.  Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network , 2019, Sensors.

[25]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[26]  Maysam F. Abbod,et al.  HRV-derived data similarity and distribution index based on ensemble neural network for measuring depth of anaesthesia , 2017, PeerJ.

[27]  S. Chatterjee ECG Changes in Subarachnoid Haemorrhage: A Synopsis , 2011, Netherlands heart journal : monthly journal of the Netherlands Society of Cardiology and the Netherlands Heart Foundation.

[28]  Sabee Molloi,et al.  Detecting Cardiovascular Disease from Mammograms With Deep Learning , 2017, IEEE Transactions on Medical Imaging.

[29]  Mark Butlin,et al.  Arterial blood pressure measurement and pulse wave analysis—their role in enhancing cardiovascular assessment , 2010, Physiological measurement.

[30]  Maysam F. Abbod,et al.  Arrhythmia Evaluation in Wearable ECG Devices , 2017, Sensors.

[31]  Cheolsoo Park,et al.  End-To-End Deep Learning Architecture for Continuous Blood Pressure Estimation Using Attention Mechanism , 2020, Sensors.

[32]  B. Hedblad,et al.  Hypertension and ST segment depression during ambulatory electrocardiographic recording. Results from the prospective population study 'men born in 1914' from Malmö, Sweden. , 1992, Hypertension.

[33]  M. Matucci-Cerinic,et al.  Use of ECG and Other Simple Non-Invasive Tools to Assess Pulmonary Hypertension , 2016, PloS one.

[34]  Maysam F. Abbod,et al.  Intermittent blood pressure prediction via multiscale entropy and ensemble artificial neural networks , 2016, 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[35]  Maysam F. Abbod,et al.  Ensemble Genetic Fuzzy Neuro Model Applied for the Emergency Medical Service via Unbalanced Data Evaluation , 2018, Symmetry.

[36]  J. van der Naalt,et al.  The Association of Early Electrocardiographic Abnormalities With Brain Injury Severity and Outcome in Severe Traumatic Brain Injury , 2021, Frontiers in Neurology.

[37]  Thomas Penzel,et al.  Comparison of detrended fluctuation analysis and spectral analysis for heart rate variability in sleep and sleep apnea , 2003, IEEE Transactions on Biomedical Engineering.

[38]  Sabine Van Huffel,et al.  A Novel Algorithm for the Automatic Detection of Sleep Apnea From Single-Lead ECG , 2015, IEEE Transactions on Biomedical Engineering.

[39]  Ki H. Chon,et al.  A Novel Time-Varying Spectral Filtering Algorithm for Reconstruction of Motion Artifact Corrupted Heart Rate Signals During Intense Physical Activities Using a Wearable Photoplethysmogram Sensor , 2015, Sensors.

[40]  Rong Zhang,et al.  Arterial blood pressure feature estimation using photoplethysmography , 2018, Comput. Biol. Medicine.

[41]  Mohammad Monir Uddin,et al.  Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques , 2020, Sensors.

[42]  T. Penzel,et al.  Dynamics of Heart Rate and Sleep Stages in Normals and Patients with Sleep Apnea , 2003, Neuropsychopharmacology.

[43]  U. Baumann,et al.  Noninvasive central venous pressure measurement by controlled compression sonography at the forearm. , 2007, Journal of the American College of Cardiology.

[44]  Antonello Rizzi,et al.  Cancer Diagnosis Using Deep Learning: A Bibliographic Review , 2019, Cancers.

[45]  J. Gummert,et al.  Non-invasive assessment of central venous pressure in heart failure: a systematic prospective comparison of echocardiography and Swan-Ganz catheter , 2020, The International Journal of Cardiovascular Imaging.

[46]  Maysam F. Abbod,et al.  Ensemble empirical mode decomposition applied for PPG motion artifact , 2016, 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[47]  C. Hersch,et al.  Electrocardiographic Changes in Head Injuries , 1961, Circulation.

[48]  R. Baranowski,et al.  J-wave formation in patients with acute intracranial hypertension. , 2009, Journal of electrocardiology.

[49]  H. Snieder,et al.  Causal Pathways from Blood Pressure to Larger QRS Amplitudes: a Mendelian Randomization Study , 2018, Scientific Reports.

[50]  U. Rajendra Acharya,et al.  Automated detection of severity of hypertension ECG signals using an optimal bi-orthogonal wavelet filter bank , 2020, Comput. Biol. Medicine.

[51]  Lori Shutter,et al.  A trial of intracranial pressure monitoring in traumatic brain injury , 2014, Critical Care.