Predictive Analysis of Health Care Data using SPARK
Vengamamba Pachava
Computer Information Systems
University of Houston – Clear Lake
Houston, Texas
Pachavav2901@uhcl.edu
Abstract—the main objective of this research is to provide a thorough review on how to handle the rapid growth of health care data using Apache Spark framework. Healthcare data is not very structured and unique. This data is more diversified and complex and using linear analysis techniques on it is not helpful.
Keywords—component; formatting; style; styling; insert (key words)
I. INTRODUCTION
In recent years, Internet has changed the way of life. New generation of health care data has evolved which includes Electronic Health Records (EHR’s), Electronic Patient Records (EPR’s). With this large-scale growth of structured and unstructured data, it has become difficult to store, manage, retrieve and distribute data. This research mainly concentrates on reviewing the recent developments in “Predictive Analysis of Health Care Data using SPARK”. With the increase in importance of public health surveillance, it is essential to consider an effective, scalable and secure framework. [1] The modern health care systems produce a vast amount of electronically stored data. Analyzing such data will create a great potential that improve patient care and health outcomes. There are different sources of healthcare data which makes it unique: A. Multiple Places: Healthcare data comes from different sources like Electronic Health Record (EHR) or Electronic Medical Record (EMR) which includes range of data such as demographics, laboratory results, personal statistics, medication etc. Healthcare data also occurs in different formats like digital, pictures, text, numeric, paper, multimedia and today’s EMR’s can hold numerous textual and numeric data. Also, there are few complex formats of heath data such as a patient’s broken arm might be an image in medical record but appears as a Diagnosis code in the claims data. [1] B. Structured and Unstructured data: One of the most important clinical fact is that health data is captured in whatever way is most convenient giving least priority on how to analyze and aggregate the data. As users become trained to …show more content…
Managing such an amalgam o of data and turning it into usable information requires more advanced set of tools. [4]
II. V’S OF BIG DATA
• Volume: Big data implies enormous volumes of data. It used to be employees created data. Now that data is generated by machines, networks and human interaction on systems like social media the volume of data to be analyzed is massive. Yet, the volume of data is not as much the problem as other V’s like veracity.
• Variety: Variety refers to the many sources and types of data both structured and unstructured. We used to store data from sources like spreadsheets and databases. Now data comes in the form of emails, photos, videos, monitoring devices, PDFs, audio, etc. This variety of unstructured data creates problems for storage, mining and analyzing data.
• Velocity: Big Data Velocity deals with the pace at which data flows in from sources like business processes, machines, networks and human interaction with things like social media sites, mobile devices, etc. The flow of data is massive and continuous. This real-time data can help researchers and businesses make valuable decisions that provide strategic competitive advantages and ROI if you are able to handle the velocity. Professionals suggest that sampling data can help deal with issues like volume and
Vengamamba Pachava
Computer Information Systems
University of Houston – Clear Lake
Houston, Texas
Pachavav2901@uhcl.edu
Abstract—the main objective of this research is to provide a thorough review on how to handle the rapid growth of health care data using Apache Spark framework. Healthcare data is not very structured and unique. This data is more diversified and complex and using linear analysis techniques on it is not helpful.
Keywords—component; formatting; style; styling; insert (key words)
I. INTRODUCTION
In recent years, Internet has changed the way of life. New generation of health care data has evolved which includes Electronic Health Records (EHR’s), Electronic Patient Records (EPR’s). With this large-scale growth of structured and unstructured data, it has become difficult to store, manage, retrieve and distribute data. This research mainly concentrates on reviewing the recent developments in “Predictive Analysis of Health Care Data using SPARK”. With the increase in importance of public health surveillance, it is essential to consider an effective, scalable and secure framework. [1] The modern health care systems produce a vast amount of electronically stored data. Analyzing such data will create a great potential that improve patient care and health outcomes. There are different sources of healthcare data which makes it unique: A. Multiple Places: Healthcare data comes from different sources like Electronic Health Record (EHR) or Electronic Medical Record (EMR) which includes range of data such as demographics, laboratory results, personal statistics, medication etc. Healthcare data also occurs in different formats like digital, pictures, text, numeric, paper, multimedia and today’s EMR’s can hold numerous textual and numeric data. Also, there are few complex formats of heath data such as a patient’s broken arm might be an image in medical record but appears as a Diagnosis code in the claims data. [1] B. Structured and Unstructured data: One of the most important clinical fact is that health data is captured in whatever way is most convenient giving least priority on how to analyze and aggregate the data. As users become trained to …show more content…
Managing such an amalgam o of data and turning it into usable information requires more advanced set of tools. [4]
II. V’S OF BIG DATA
• Volume: Big data implies enormous volumes of data. It used to be employees created data. Now that data is generated by machines, networks and human interaction on systems like social media the volume of data to be analyzed is massive. Yet, the volume of data is not as much the problem as other V’s like veracity.
• Variety: Variety refers to the many sources and types of data both structured and unstructured. We used to store data from sources like spreadsheets and databases. Now data comes in the form of emails, photos, videos, monitoring devices, PDFs, audio, etc. This variety of unstructured data creates problems for storage, mining and analyzing data.
• Velocity: Big Data Velocity deals with the pace at which data flows in from sources like business processes, machines, networks and human interaction with things like social media sites, mobile devices, etc. The flow of data is massive and continuous. This real-time data can help researchers and businesses make valuable decisions that provide strategic competitive advantages and ROI if you are able to handle the velocity. Professionals suggest that sampling data can help deal with issues like volume and