Big Data

Application in
Industry
Healthcare
Big Data in Healthcare
 Big data in healthcare is used for reducing
cost overhead, curing diseases, improving
profits, predicting epidemics and
enhancing the quality of human life by
preventing deaths.
 Scientific research labs, hospitals and
other medical institutions are leveraging
big data analytics to reduce healthcare
costs by changing the models of treatment
delivery.
Big Data in Healthcare
 The New York based research and consulting firm,
Institute for Health Technology Transformation estimates
that in 2011, the US Healthcare industry generated 150
billion gigabytes (150 Exabytes) of data.
 This data was mostly generated by various regulatory
requirements, record keeping, compliance and patient
care.
 Since then, there has been an exponential increase in
data which has lead to an expenditure of $1.2 trillion
towards healthcare data solutions in the Healthcare
industry. McKinsey projects that the use of Big Data in
healthcare can reduce the healthcare data management
expenses by $300 billion -$500 billion.
Big Data in Healthcare
 Big Data in healthcare originates from the large
electronic health datasets – these datasets are very
difficult to manage with the conventional hardware
and software.
 The use of legacy data management methods and
tools also makes it impossible to usefully leverage
all this data.
 Big Data in healthcare is an overpowering concept
not just because of the volume of data but also due
to the different data types and the pace at which
healthcare data management needs to be
managed.
Big Data in Healthcare
 The sum total of data related to the patient and
their well-being constitutes the “Big Data”
problem in the healthcare industry.
 Big Data Analytics has actually become an on
the rise and crucial problem in healthcare
informatics as well.
 Healthcare informatics also contributes to the
development of Big Data analytic technology by
posing novel challenges in terms of data
knowledge representation, database design,
data querying and clinical decision support.
Big Data in Healthcare
 Big Data in healthcare industry promises to support a
diverse range of healthcare data management
functions such as population health management,
clinical decision support and disease surveillance.
 The Healthcare industry is still in the early stages of
getting its feet wet in the large scale integration and
analysis of big data.
 With 80% of the healthcare data being unstructured,
it is a challenge for the healthcare industry to make
sense of all this data and leverage it effectively for
Clinical operations, Medical research, and Treatment
courses.
Healthcare as Big Data
Repository
 Healthcare is a multi-dimensional system
established with the sole aim for :
 prevention
 diagnosis
 treatment of health-related issues or
impairments in human beings.
Healthcare as Big Data
Repository
 The major components of a healthcare system
are:
 health professionals (physicians or nurses)
 health facilities (clinics, hospitals for
delivering medicines
 other diagnosis or treatment technologies)
 financing institution
Healthcare as Big Data
Repository
 With the advent of computer systems and its potential,
the digitization of all clinical exams and medical
records in the healthcare systems has become a
standard and widely adopted practice nowadays
 Electronic health records (EHR) as defined by Murphy,
Hanken and Waters as:
 computerized medical records for patients any information
relating to the past, present or future physical/mental
health or condition of an individual which resides in
electronic system(s) used to capture, transmit, receive,
store, retrieve, link and manipulate multimedia data for
the primary purpose of providing healthcare and health-
related services”
Healthcare as Big Data
Repository
 Electronic health records (EHR) advantages
 healthcare professionals have an improved access
to the entire medical history of a patient
 The information includes medical diagnoses,
prescriptions, data related to known allergies,
demographics, clinical narratives, and the results
obtained from various laboratory tests
 significant decrease in the redundant and
additional examinations, lost orders and
ambiguities caused by illegible handwriting, and
an improved care coordination between multiple
healthcare providers
Healthcare as Big Data
Repository
 Electronic health records (EHR) advantages
 Overcoming such logistical errors has led to
reduction in the number of drug allergies by
reducing errors in medication dose and
frequency.
 Finally, EHRs can reduce or absolutely
eliminate delays and confusion in the billing
and claims management area.
 The EHRs and internet together help provide
access to millions of health-related medical
information critical for patient life.
Healthcare as Big Data
Repository
 Electronic health records (EHR) advantages
 Overcoming such logistical errors has led to
reduction in the number of drug allergies by
reducing errors in medication dose and
frequency.
 Finally, EHRs can reduce or absolutely
eliminate delays and confusion in the billing
and claims management area.
 The EHRs and internet together help provide
access to millions of health-related medical
information critical for patient life.
Healthcare as Big Data
Repository
 The big data in health- care includes the healthcare payer-
provider data (such as EMRs, pharmacy prescription, and
insurance records) along with the genomics-driven
experiments (such as genotyping, gene expression data) and
other data acquired from the smart web of internet of things
(IoT)
 The management and usage of such healthcare data has been
increasingly dependent on information technology.
 The development and usage of wellness monitoring devices
and related software that can generate alerts and share the
health related data of a patient with the respective health
care providers has gained momentum, especially in
establishing a real-time biomedical and health monitoring
system.
Healthcare as Big Data
Repository
 These devices are generating a huge amount of
data that can be analyzed to provide real-time
clinical or medical care.
 The use of big data from healthcare shows
promise for improving health outcomes and
controlling costs.
Patients Predictions For
Improved Staffing
 A white paper by Intel details how four
hospitals that are part of the Assistance
Publique-Hôpitaux de Paris have been using
data from a variety of sources to come up
with daily and hourly predictions of how many
patients are expected to be at each hospital.
 One of the key data sets is 10 years’ worth of
hospital admissions records, which data
scientists crunched using “time series
analysis” techniques.
Patients Predictions For
Improved Staffing
 These analyses allowed the researchers to see
relevant patterns in admission rates. Then, they
could use machine learning to find the most
accurate algorithms that predicted future
admissions trends.
 Summing up the product of all this work, the
data science team developed a web-based user
interface that forecasts patient loads and helps
in planning resource allocation by utilizing online
data visualization that reaches the goal of
improving the overall patients' care.
Patients Predictions For
Improved Staffing
Real-Time Alerting
 Other examples of data analytics in healthcare
share one crucial functionality – real-time alerting.
 In hospitals, Clinical Decision Support (CDS)
software analyzes medical data on the spot,
providing health practitioners with advice as they
make prescriptive decisions.
 For example, if a patient’s blood pressure
increases alarmingly, the system will send an
alert in real-time to the doctor who will then take
action to reach the patient and administer
measures to lower the pressure.
Real-Time Alerting
 Another example is that of Asthmapolis,
which has started to use inhalers with
GPS-enabled trackers in order to identify
asthma trends both on an individual
level and looking at larger populations.
 This data is being used in conjunction
with data from the CDC in order to
develop better treatment plans for
asthmatics.
Real-Time Alerting
Smart Staffing & Personnel
Management
 Without a cohesive, engaged workforce, patient
care will dwindle, service rates will drop, and
mistakes will happen.
 With big data tools in healthcare, it’s possible to
streamline your staff management activities in
a wealth of key areas.
 By working with the right HR analytics, it’s
possible for time-stretched medical institutions
to optimize staffing while forecasting operating
room demands, streamlining patient care as a
result.
Smart Staffing & Personnel
Management
 Too often, there is a significant lack of fluidity
in healthcare institutions, with staff
distributed in the wrong areas at the wrong
time.
 This imbalance of personnel management
could mean a particular department is either
too overcrowded with staff or lacking staff
when it matters most, which can develop risks
of lower motivation for work and increases the
absenteeism rate.
Smart Staffing & Personnel
Management
 Too often, there is a significant lack of fluidity
in healthcare institutions, with staff
distributed in the wrong areas at the wrong
time.
 This imbalance of personnel management
could mean a particular department is either
too overcrowded with staff or lacking staff
when it matters most, which can develop risks
of lower motivation for work and increases the
absenteeism rate.
Smart Staffing & Personnel
Management
 Though data-driven analytics, it’s possible
to predict when you might need staff in
particular departments at peak times
while distributing skilled personnel to
other areas within the institution during
quieter periods.
Big Data In Healthcare Applied
On A Hospital Dashboard
 You can see here the most important metrics
concerning various aspects: the number of patients
that were welcomed in your facility, how long they
stayed and where, how much it cost to treat them,
and the average waiting time in emergency rooms.
 Such a holistic view helps top-management identify
potential bottlenecks, spot trends, and patterns over
time, and in general assess the situation.
 This is key in order to make better-informed decisions
that will improve the overall operations performance,
with the goal of treating patients better and having
the right staffing resources.
Big Data In Healthcare Applied
On A Hospital Dashboard
 You can see here the most important metrics
concerning various aspects: the number of patients
that were welcomed in your facility, how long they
stayed and where, how much it cost to treat them,
and the average waiting time in emergency rooms.
 Such a holistic view helps top-management identify
potential bottlenecks, spot trends, and patterns over
time, and in general assess the situation.
 This is key in order to make better-informed decisions
that will improve the overall operations performance,
with the goal of treating patients better and having
the right staffing resources.
Big Data In Healthcare Applied
On A Hospital Dashboard
 You can see here the most important metrics
concerning various aspects: the number of patients
that were welcomed in your facility, how long they
stayed and where, how much it cost to treat them,
and the average waiting time in emergency rooms.
 Such a holistic view helps top-management identify
potential bottlenecks, spot trends, and patterns over
time, and in general assess the situation.
 This is key in order to make better-informed decisions
that will improve the overall operations performance,
with the goal of treating patients better and having
the right staffing resources.
Hadoop technology in Cancer
Treatments and Genomics
 There are about 3 billion base pairs that constitute the human
DNA and it is necessary for such large amounts of data to be
organized in an effective manner if we have to fight cancer.
 The biggest reason why cancer has not been cured yet is
because of the fact that cancer mutates in different patterns
and reacts in different ways based on the genetic makeup of
an individual.
 Hence, oncology researchers have come up with a solution
that in order to cure cancer, patients will need to be given
personalized treatment based on the type of cancer the
individual patient’s genetics make up.
 Leveraging Hadoop technology will offer great support for
parallelization and help in mapping the 3 billion DNA base pairs
using MapReduce programs.
Hadoop technology in Cancer
Treatments and Genomics
 CASI pr the Complex Adaptive Systems
Initiative at the Arizona State University
is developing a genomic data lake with
petabytes of genetic data on individuals,
treatments, potentially helping in
identifying the cancer gene and
providing the base to develop life saving
cancer treatments through big data
analysis.
Hadoop technology in
Monitoring Patient Vitals
 CASI pr the Complex Adaptive Systems
Initiative at the Arizona State University
is developing a genomic data lake with
petabytes of genetic data on individuals,
treatments, potentially helping in
identifying the cancer gene and
providing the base to develop life saving
cancer treatments through big data
analysis.
Hadoop technology in
Monitoring Patient Vitals
 Children’s Healthcare of Atlanta treats
over 6,200 children in their ICU units. On
average, the duration of stay in Pediatric
ICU varies from a month to a year.
 Children’s Healthcare of Atlanta used a
sensor beside the bed that helps them
continuously track patient signs such as
blood pressure, heartbeat and the
respiratory rate.
Hadoop technology in
Monitoring Patient Vitals
 These sensors produce large chunks of data,
which using legacy systems cannot be stored
for more than 3 days for analysis.
 The main motive of Children’s Healthcare of
Atlanta was to store and analyze the vital signs.
 If there is any change in pattern, then the
hospital wanted an alert to be generated to a
team of doctors and assistants. All this was
successfully achieved using Hadoop ecosystem
components - Hive, Flume, Sqoop, Spark, and
Impala.
Hadoop technology in the
Hospital Network
 A Cleveland Clinic spinoff company known as
Explorys is making use of Big Data in healthcare to
provide the best clinical support, reduce the cost of
care measurement and manage the population of
at-risk patients.
 Explorys has reportedly built the largest database in
the healthcare industry with over a hundred billion
data points all thanks to Hadoop.
 Explorys uses Hadoop technology to help their
medical experts analyze data bombardments in real
time from diverse sources such as financial data,
payroll data, and electronic health records.
Hadoop technology in the
Hospital Network
 The analytics tool developed by Explorys is
used for data mining so that it helps
clinicians determine the deviations among
patients and the effects treatments have
on their health.
 These insights help the medical
practitioners and health care providers find
out the best treatment plans for a set of
patient populations or for an individual
patient.
Hadoop technology in Fraud
Prevention and Detection
 At least 10% of the Healthcare insurance
payments are attributed to fraudulent
claims.
 Worldwide this is estimated to be a multi
billion dollar problem.
 Fraudulent claims is not a novel problem but
the complexity of the insurance frauds
seems to be increasing exponentially
making it difficult for the healthcare
insurance companies to deal with them.
Hadoop technology in Fraud
Prevention and Detection
 At least 10% of the Healthcare insurance
payments are attributed to fraudulent
claims.
 Worldwide this is estimated to be a multi
billion dollar problem.
 Fraudulent claims is not a novel problem but
the complexity of the insurance frauds
seems to be increasing exponentially
making it difficult for the healthcare
insurance companies to deal with them.
Hadoop technology in Fraud
Prevention and Detection
 Big Data Analytics helps healthcare insurance
companies find different ways to identify and prevent
fraud at an early stage.
 Using Hadoop technology, insurance companies have
been successful in developing predictive models to
identify fraudsters by making use of real-time and
historical data of medical claims, weather data, wages,
voice recordings, demographics, cost of attorneys and
call center notes.
 Hadoop’s capability to store large unstructured data sets
in NoSQL databases and using MapReduce to analyze
this data helps in the analysis and detection of patterns
in the field of Fraud Detection.
Summary
 Big data analytics leverage the gap within structured
and unstructured data sources.
 The shift to an integrated data environment is a well-
known hurdle to overcome.
 Interesting enough, the principle of big data heavily
relies on the idea of the more the information, the
more insights one can gain from this information and
can make predictions for future events.
 It is rightfully projected by various reliable consulting
firms and health care companies that the big data
healthcare market is poised to grow at an exponential
rate.
Summary
 However, in a short span we have witnessed a
spectrum of analytics currently in use that have
shown significant impacts on the decision making
and performance of healthcare industry.
 The exponential growth of medical data from
various domains has forced computational experts
to design innovative strategies to analyze and
interpret such enormous amount of data within a
given timeframe.
 The integration of computational systems for signal
processing from both research and practicing
medical professionals has witnessed growth.
References
 https://www.datapine.com/blog/big-data
-examples-in-healthcare/
 Dash, S., Shakyawar, S.K., Sharma, M.
et al. Big data in healthcare:
management, analysis and future
prospects. J Big Data 6, 54 (2019).
https://doi.org/10.1186/s40537-019-021
7-0
 https://www.dezyre.com/article/5-
healthcare-applications-of-hadoop-and-
big-data/85