You are on page 1of 20

Big Data Analytics for Healthcare

Industry:
Impact, Applications, and Tools

1
Abstract
• To discuss the impact of big data in
healthcare, and various tools available in the
Hadoop ecosystem for handling it and also
architecture of big data analytics for
healthcare.
• This involves the data gathering history of
different branches, the genome database,
electronic health records, text/imagery, and
clinical decisions support system.

2
Introduction
• According to a survey conducted in 2012,
healthcare data totaled nearly 550 petabytes
and will reach nearly 26,000 petabytes in
2020.
• The various classes of data in healthcare
applications include Electronic Health Records
(EHR), public records, etc.

3
What is Big Data?
• At The Big Data Institute (TBDI), big data is a
“term applied to voluminous data objects that
are variety in nature – structured, unstructured
or a semi-structured, including sources internal or
external to an organization”.
• The 4 V’s of Big Data in Healthcare:
 Volume
 Veracity
 Variety
 Velocity

4
4 V’s in Health Care Industry

5
Why Big data analytics in Healthcare?
• The various classes of data in healthcare
applications include Electronic Health Records
(EHR), machine generated/sensor data, health
information exchanges, patient registries, portals,
genetic databases, and public records.
• Patient data in electronic health records (EHRs).
• According to a survey conducted in 2012,
healthcare data totaled nearly 550 petabytes and
will reach nearly 26,000 petabytes in 2020.
6
Challenges
• Healthcare Industry is facing many problems in
order to leverage potential benefits of Data
analytics:
Many players – Data sharing is cumbersome. Accurate
analytics is to be done on operational, clinical and
financial.
Resistance to change – Providers are used to make
treatment decisions based on their clinical judgment
instead of relying on protocols based on Big Data
Analytics.
Patient privacy and security.

7
Scenario of Analytics in Indian
Healthcare – A case study
• With Government initiatives under the Digital
India Program (DIP) led by the Prime Minister of
India, Mr. Narendra Modi – healthcare sector is in
the process of undergoing a massive digital make-
over.
• The e- health initiative under this Program allows
integration of the patient’s Electronic Health
Records in a ‘digital locker’, backed by Aadhaar
card which can be shared with doctors of both
public and private establishments.

8
How can we believe that the data is
true in health sectors?

9
User: Apollo Hospitals, Chennai
• Business Case: To immunize the Hospital
against Hospital Acquired Infections (HAI).
• Solution: IT teams provisioned with powerful
big data analytics to enhance their ability to
define both preventive and prescriptive
treatment patterns by applying the solutions
of “RxAnalytics” along with microbiology
information.

10
• Result: Post adoption of this solution has immensely benefitted across the
following parameters:
 Reduction in Analysis Time
 Scalability
 Standardized Approach
 Improved Quality of Healthcare
11
Big Data Analytics in health Informatics
• In 2011, healthcare organizations had produced
more than 150 exabytes of data, all of which
must be efficiently analyzed to be at all useful to
the healthcare system.
• Which could be done with avoidance of Human
intervention.
– Previously Human Beings analyzed patterns by data
mining by prompting a prediction.
– At present, Machine learning evaluates a possible
pattern without Human Intervention.

12
Impact of Big Data on the Healthcare
System

13
Hadoop-Based Applications for Health
Industry
• The collection of software utilities known as the Hadoop ecosystem
can help the healthcare sector to manage this vast amount of data.
• The various applications of the Hadoop ecosystem in the healthcare
sector are as follows:
 Treatment of Cancer and Genomics : mapping of three billion DNA
base pairs.
 Monitoring of Patient Vitals : Hadoop Distributed File System (HDFS)
 Hospital Network : NoSQL database to collect and manage their huge
amounts of real-time data
 Healthcare Intelligence : Hadoop ecosystem’s Pig, Hive, and
MapReduce technologies process large datasets
 Prevention and Detection of Frauds : NoSQL database is also helpful in
preventing fraud

14
Why Hadoop?
• It is the latest technology available in the
market
• Many technologies like SAP, CEPH, BigQuery,
etc are used but they have some
dependencies:
a. Data Storage is costly
b. No efficient means to process data
c. MapReduce and HDFS are the main reasons

15
Hadoop’s Tools and Techniques for Big
Data
• Apache Hadoop
• HDFS
• MapReduce
• Apache Hive
• Apache Pig
• Apache Oozie
• Apache Hbase
• Apache Avro
• ZooKeeper MapReduce procedure

16
17
Conclusion
• Analytics in Healthcare in India is still at a very
nascent stage, however the application of well-
defined and well-integrated analytics throughout
the healthcare value chain can be transformative.
The combination of big data and healthcare
• Analytics can lead to treatments that are effective
for specific patients by providing the ability to
prescribe appropriate medications for each
individual, rather than those that work for most
people.

18
References
• https://www.researchgate.net/publication/322713448
_Scenario_of_Analytics_in_Indian_Healthcare.
• https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumbe
r=8486794.
• A. Gandomi and M. Haider, Beyond the hype: Big data
concepts, methods and analytics, International Journal
of Information Management, vol. 35, no. 2, pp. 137–
144, 2015.
• A. O’Driscoll, J. Daugelaite, and R. D. Sleator, “Big
Data”, Hadoop and cloud computing in genomics,
Journal of Biomedical Informatics, vol. 46, no. 5, pp.
774–781, 2013.

19
THANK YOU..

20

You might also like