Abstract

Nowadays, the increasing number of patients accompanied with the emergence of new symptoms and diseases makes heath monitoring and assessment a complicated task for medical staff and hospitals. Indeed, the processing of big and heterogeneous data collected by biomedical sensors along with the need of patients’ classification and disease diagnosis become major challenges for several health-based sensing applications. Thus, the combination between remote sensing devices and the big data technologies have been proven as an efficient and low cost solution for healthcare applications. In this paper, we propose a robust big data analytics platform for real time patient monitoring and decision making to help both hospital and medical staff. The proposed platform relies on big data technologies and data analysis techniques and consists of four layers: real time patient monitoring, real time decision and data storage, patient classification and disease diagnosis, and data retrieval and visualization. To evaluate the performance of our platform, we implemented our platform based on the Hadoop ecosystem and we applied the proposed algorithms over real health data. The obtained results show the effectiveness of our platform in terms of efficiently performing patient classification and disease diagnosis in healthcare applications.

Highlights

  • Today, the world faces an increasing number of diseases and patients

  • Spark is selected among other existing tools due to three major characteristics required in sensing-based healthcare: first, it supports both batch and streaming processing which are necessary to apply various data analytical algorithms; second, it ensures a lower latency level than other tools such as MapReduce, which is strongly required in health applications; and third it guarantees scalability to any number of cluster nodes required for the health application requirements

  • We propose a new version of Kmeans, called SKmeans (Stability-based Kmeans), which is strictly dedicated to sensing-based healthcare applications

Read more

Summary

Introduction

The world faces an increasing number of diseases and patients. In addition, wars, pollution, food-related illness, and human–animal relationships cause the emergence and propagation of new types of diseases and viruses. Smart technologies have opened up a world of applications in disease diagnostic and treatment such as for cancer, glucose monitoring, depression, Parkinson’s disease, connected contact lenses, etc This has been a big motivation for healthcare organizations to heavily invest in big data analytics. Big data collection and storage: Biosensors continuously record vital signs of patients, usually per second, and they send their records toward data storage center. Rapid emergency detection: Usually, a normal health range is defined for each vital sign Records outside this range lead to an abnormal situation which should be quickly detected and reported to the medical staff in order to take suitable actions. To overcome the above challenges, we propose an efficient and robust big data analytical platform for real-time sensing-based healthcare applications.

Related Work
Overview about the Architecture of Our Platform
Layer 1
Data Sources
Layer 2
Apache Spark
Hadoop HDFS
Emergency Detection and Clinical Response Algorithm
Patient Archiving Algorithm
Layer 3
Patient Classification Algorithm
Disease Diagnosis Algorithm
Layer 4
Spark SQL
Matplotlib
System Demonstration and Evaluation
Records Patients Study
SKmeans Study
Iteration Number Study
Clustering Accuracy Study
Vital Signs and Disease Diagnosis Study
Further Discussions
Conclusions and Future Work
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call