Predicting Systolic Blood Pressure in Real-Time Using Streaming Data and Deep Learning

High systolic blood pressure causes many problems, including stroke, brain attack, and others. Therefore, examining blood pressure and discovering issues related to it at the right time can help prevent the occurrence of health problems. Nowadays, health-based data brings a new dimension to healthcare by exploiting the real-time patients’ data to early detect systolic blood pressure (SBP). Furthermore, technologies typically associated with smart and real-time data processing add value in the healthcaredomain, including artificial intelligence, data analytic technologies, and stream processing technologies. Thus, this paper introduces a systolic blood pressure prediction system that can predict SBP in real-time and, therefore, can avoid health problems that may stem from sudden high blood pressure. The proposed system works through two components, namely, developing an offline model and an online prediction pipeline. The aim of developing an offline model module is to develop the model using investigate different deep learning models to achieve the smallest root mean square error. It has been developed using Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional Short-Term Memory (BI-LSTM), Gated Recurrent Units (GRU) models andMedical Information Mart for Intensive Care (MIMC II) SBP time-series dataset. The online prediction pipeline module is using Apache Kafka and Apache Spark to predict the near future of SBP in real-time using the best deep learning model and SBP streaming time-series data. The experimental results indicate that the BI-LSTM model has achieved the best performance using three hidden layers, and it is used to predict the near future of SBP in real-time.

[1]  J Lee,et al.  A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series , 2010, 2010 Computing in Cardiology.

[2]  Xi Deng,et al.  A novel short-term blood pressure prediction model based on LSTM , 2019 .

[3]  José Neves,et al.  Evolving Time Series Forecasting ARMA Models , 2004, J. Heuristics.

[4]  Bharadwaj Veeravalli,et al.  Real-Time, Personalized Anomaly Detection in Streaming Data for Wearable Healthcare Devices , 2017, Handbook of Large-Scale Distributed Computing in Smart Healthcare.

[5]  Ying Liu,et al.  Investigation of Machine Learning Techniques in Forecasting of Blood Pressure Time Series Data , 2019, SGAI Conf..

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[8]  Keqin Li,et al.  A task-level adaptive MapReduce framework for real-time streaming data in healthcare applications , 2015, Future Gener. Comput. Syst..

[9]  D. Ogoina,et al.  Prevalence of hypertension and associated factors in a rural community in Bayelsa State , 2018 .

[10]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[11]  Nilanjan Ray,et al.  Continuous blood pressure prediction from pulse transit time using ECG and PPG signals , 2016, 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT).

[12]  R G Mark,et al.  MIMIC II: a massive temporal ICU patient database to support research in intelligent patient monitoring , 2002, Computers in Cardiology.

[13]  Joon Lee,et al.  Accessing the public MIMIC-II intensive care relational database for clinical research , 2013, BMC Medical Informatics and Decision Making.

[14]  Liang Wang,et al.  Blood Pressure Prediction via Recurrent Models with Contextual Layer , 2017, WWW.

[15]  M. Saeed,et al.  Estimating cardiac output from arterial blood pressurewaveforms: a critical evaluation using the MIMIC II database , 2005, Computers in Cardiology, 2005.

[16]  M. Gunasekaran,et al.  Effective Big Data Retrieval Using Deep Learning Modified Neural Networks , 2019, Mob. Networks Appl..

[17]  Deepak Gupta,et al.  Artificial plant optimization algorithm to detect heart rate & presence of heart disease using machine learning , 2020, Artif. Intell. Medicine.

[18]  Deepak Gupta,et al.  Artificial plant optimization algorithm to detect infected leaves using machine learning , 2020, Expert Syst. J. Knowl. Eng..

[19]  Ryosuke Kojima,et al.  Prediction of blood pressure variability using deep neural networks , 2020, Int. J. Medical Informatics.

[20]  Abdeltawab M. Hendawi,et al.  Heart disease identification from patients' social posts, machine learning solution on Spark , 2020, Future Gener. Comput. Syst..

[21]  Yu Cao,et al.  An integrated machine learning approach to stroke prediction , 2010, KDD.

[22]  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).

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[24]  Sujit Dey,et al.  Personalized Effect of Health Behavior on Blood Pressure: Machine Learning Based Prediction and Recommendation , 2018, 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom).

[25]  Wei Shi,et al.  Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification , 2016, ACL.

[26]  Farhad Kaffashi,et al.  Data Collection and Analysis in the ICU , 2019, Neurocritical Care Informatics.

[27]  Colleen M. Ennett,et al.  Prediction of extubation failure for neonates with respiratory distress syndrome using the MIMIC-II clinical database , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  Peter Szolovits,et al.  Abstract 448: Predicting Blood Pressure Response to Fluid Bolus Therapy Using Neural Networks with Clinical Interpretability , 2019, Circulation Research.

[29]  G. Mitchell,et al.  Arterial stiffness and hypertension. , 2014, Hypertension.

[30]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[31]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.