A Review of the Role and Challenges of Big Data in Healthcare Informatics and Analytics

Table 2

Represent a list of several large companies which provide and supply services on big data analysis in the healthcare sector [1].

Data	Software	Description
Data integration or dataset or data source	Kafka, Sqoop	Tiny biosensors are placed on patients’ body for collecting vital signs data in health applications, and the vital signs include blood pressure (BP), systolic and diastolic, respiratory rate (RR), heart rate (HR), oxygen saturation (spo2), and body temperature (BT)
Data decision and data storage	Apache Spark, Hadoop HDFS	That is responsible for storing data and processing it. That layer consists of two main tools, i.e., Hadoop and Apache Spark, also processing two data algorithms, patient archiving, emergency management, and clinical responses
Emergency detection and clinical response algorithm	Early warning score (EWS)	To verify abnormal situations
Patient classification and disease diagnosis	Machine learning algorithm	Machine learning tool and advanced analytics of huge datasets at high speed. Big data workspace tools are stored on Hadoop clusters for pattern insights discovered from massive data. Solutions to big data use cases by predictive analytics through platforms
Data retrieval and visualization	Hive, Spark SQL	Medical staff can access patients’ records using the last platform for storing their data in HDFS and Hadoop. It comprises two data retrieval (spark SQL and hive) and just one graphing tool (Matplotlib). Obtaining data from the Hadoop storage system, which uses a set of criteria defined via queries, is based on the data retrieval tools. The retrieved data is usually stored in a file or displayed on a screen. Using graphics or plots statistically for data visualization is a graphical representation of the retrieved data; in our platform, each tool has been highlighted