“Big Data in Healthcare
Management: A Review of
Literature”
By Anastasia Tuta
Introduction
• Change in healthcare from
disease oriented to patients
oriented.
• For this to happen data must
be analyzed. Limitation:
some and a big majority of
data is outdated.
• Another change is that
healthcare nowdays focuses
on predicting diseases based
upon history.
Big Data in
Healthcare
• Took off in 2013 when a big
company McKinsey&Company
published a report regarding
reducing healthcare
spendings.
Big Data - Definition
• “Large volumes of high velocity, complex and variable
data that require advanced technologies to enable the
capture, storage, distribution, management and
analysis of the information”.
• Specifically in healthcare it means collecting from
clinics or foundations to be used for decision
marketing.
6 V’s of Big
Data
• Volume
• Veracity
• Variety
• Variability
• Velocity
• Value
Volume
• In the present we have
exabyte amount of data
(10^18 bytes)
• This in the future will
increase to zettabyte
(10^21 bytes) or to
yottabyte (10^24 bytes).
Veracity
• It is defined as the
correctness and accuracy of
data.
• Big data has a low veracity
and it is never 100%
accurate.
• Therefore it is difficult
to validate.
Velocity
• There is a massive
frequency of during the
time when the current data
is created, supplied and
managed.
• For example, the increase
in the percentage of older
population makes the higher
the number of patients that
healthcare industry has to
deal with. It is estimated
that this increases the
number of patients by 5060% each year.
Variability
• This refers to data
fluctuation from the start
to the end of research
journey.
Value
• This is represented by
extracting big data from
huge data.
Data Aquisition
• Primary data is acquired from clinical decision
support systems.
• Secondary sources are taken from laboratories,
insurance companies
• Electronic health records involve data as EKG, X
Rays.
• Image processing involves data such as CT Scan,
MRI, Pet Scan.
• Social Media : www.patientslikeme.com
• Smart phones: Mood Panda and Diabetics support
apps to measure sugar level.
Data Storage
• Can be big data storage,
relational databases, or it
does not involve SQL
• Big data storage includes
vendors such as Google,
Microsoft, Amazon, IBM and
has components Cloud
Services, Azure S3,
SmartCloud
Data
Managemen
t
Involves organizing,
cleaning, retrieval data
mining and data
governnance
Data
Analysis
There are various
languages for for data
analysis: R, Cytoscape,
Graphiz, IBM Watston
Analysis
Applications of big data in
Healthcare
• Used for fraud detection, epidemic spread
detection, Omics, clinical outcome, medical
device design, insurance industry, personalized
patient care
Challenges of
big data in
healthcare
• Data Privacy
• Data leakage
• Data security
Limitations
• There are limited resources in healthcare
management that must be taken into account.
References
• SA, S. (2018). Big Data in Healthcare
Management: A Review of Literature. American
Journal of Theoretical and Applied Business,
4(2), p.57.