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.

收缩压高会引起许多问题，包括中风，脑部发作等。因此，检查血压并在适当的时间发现与血压有关的问题可以帮助防止出现健康问题。如今，基于健康的数据通过利用实时患者的数据来早期检测收缩压（SBP），为医疗保健带来了新的领域。此外，通常与智能和实时数据处理相关的技术可在医疗保健领域增加价值，包括人工智能，数据分析技术和流处理技术。因此，本文介绍了一种可实时预测SBP的收缩期血压预测系统，从而可以避免因突然的高血压而引起的健康问题。拟议的系统通过两个组件工作，即开发离线模型和在线预测管道。开发离线模型模块的目的是通过研究不同的深度学习模型来开发模型，以实现最小的均方根误差。它是使用递归神经网络（RNN），长期短期记忆（LSTM），双向短期记忆（BI-LSTM），门控循环单位（GRU）模型和重症监护医疗信息中心（MIMC II）SBP开发的时间序列数据集。在线预测管道模块使用Apache Kafka和Apache Spark通过最佳的深度学习模型和SBP流时间序列数据实时预测SBP的不久的将来。实验结果表明，BI-LSTM模型使用三个隐藏层获得了最佳性能，