BIG DATA FOR HEALTHCARE

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 1

FACTS BASED ON REPORT 2020: CHALLENGES IN HEALTHCARE
▪With the 2019 global population of 7.7 billion expected to reach 8.5 billion by 2030,4 meeting health
needs won’t be easy

▪Over 2019–23, however, health spending is expected to rise at a more robust compound annual growth
rate (CAGR) of 5 percent, up from 2.7 percent in 2014–18.

▪Overall life expectancy is projected to increase from an estimated 73.7 years in 2018 to 74.7 years by
2023.6 The number of people aged over 65 will be more than 686 million, or 11.8 percent of the total
population

▪Lifestyle-related factors including smoking, poor diet, hypertension, obesity, and lack of physical activity
contribute to many of the top 10 global causes of death

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 2

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 3
 DRIVERS
India unveiled an
ambitious National
Health Protection
Scheme (NHPS) in
February 2018, which it
claimed would be the
world’s largest
government-funded
health care program. It
is expected to
implement the program
despite funding
pressures.

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 4

 SOURCES OF DATA
▪Health Care Data
▪Genomic Data
▪Clinical Data and Clinical Notes: About 80% of this type data are unstructured
documents, images and clinical or transcribed notes (Yang et al., 2014)
▪Behavior Data and Patient Sentiment Data
▪Health Publication and Clinical Reference Data
▪Administrative, Business and External Data (Insurance claims and related financial
data, billing and scheduling , Biometric data)
▪Other Important Data (machine , device data)

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 5

 BIG DATA CHALLENGES IN HEALTHCARE HEALTHCARE

▪Inferring knowledge from complex heterogeneous patient sources. Leveraging the patient/data
correlations in longitudinal records

▪Understanding unstructured clinical notes in the right context.

▪Efficiently handling large volumes of medical imaging data and extracting potentially useful information
and biomarkers.

▪Analyzing genomic data is a computationally intensive task and combining with standard clinical data
adds additional layers of complexity.

▪Capturing the patient’s behavioral data through several sensors; their various social interactions and
communications.
FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 6
OTHER CHALLENGES IN HEALTHCARE
Demographics: aging populations, more chronic conditions, increasingly intense and expensive end-
of-life care

● Technology: advanced high-tech medicine is more expensive to deliver, cost overheads, supply
demand lags

● Quality of care: uncoordinated care, inefficient workflows, medical errors, readmissions, hospital-
acquired infections, nurse and physician shortages

● Structural issues: institutional inefficiencies, fraud, waste, market distortions (third-party payers,
reimbursement regimes), regulatory overhead, defensive medicine

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 7

 BENEFITS OF BIG DATA IN MEDICAL APPLICATIONS AND HEALTH CARE

Research & development:

(1) lower attrition and produce a leaner, faster, more targeted R&D pipeline in drugs and devices with the help of
predictive modeling;
(2) improve clinical trial design, thus reducing trial failures and speeding new treatments to market; and
(3) identify following indications and discover adverse effects before products reach the market

Public health:
(1) analyze disease patterns and track disease outbreaks and transmission to improve public health surveillance and
speed response;
(2) faster develop more accurately targeted vaccines and
(3) turn large amounts of data into actionable information

Clinical operations: Determine more clinically relevant and cost-effective ways to diagnose and treat patients

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 8

CURRENT DIGITAL TECHNOLOGIES USES IN HEALTHCARE
Cloud computing solutions
Fifth-generation (5G) technology
Radical interoperability and open platforms
Artificial intelligence (AI)
Natural language processing (NLP) that generates detailed, accurate medical notes through spoken or written sentences
Big data analytics that can examine large, unstructured data sets to uncover patient patterns or correlations; data visualization
that presents data in the most efficient and effective way to ensure findings that drive strategy and decision -making. Already,
computer algorithms can interpret a range of digital images more accurately than clinicians.
Data as a Platform (DaaP) that extracts insights from patient data which can support several opportunity areas
Blockchain systems that use a digital record of transactions to help life sciences and health care organizations monitor and track
medical products in the supply chain; share data generated by clinical trials; pull together transactions from multiple health
systems, pharmacies, and health plans for patient and/or EMR use; and streamline insurance claims reviews
Robotics that help physicians perform complex procedures with more precision and flexibility; augmented reality that gives
surgeons easy access to digital images and data so that they don’t need to look away from the patient to gather information.
Sensors on wearables that monitor patient health and develop algorithms to determine treatment recommendations; machine
learning that helps recognize and flag abnormalities without bias; 3-D holograms that bring the delivery of care closer and more
comprehensively to the patient.
Internet of Medical Things (IoMT), a connected infrastructure of medical devices, software applications, and health systems and
services that brings together people (patients, caregivers, and clinicians), data (patient or performance data), processes (c are
delivery and patient support), and enablers (sensors and connected medical devices) to deliver improved patient outcomes more
efficiently

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 9

DAAP (DATA AS A
PLATFORM

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 10

CASE 1:
Over $30 billion was spent on unnecessary hospital admissions.
Goals:
▪ Identify patients at high-risk and ensure they get the treatment they need.
▪ Develop algorithms to predict the number of days a patient will spend in a hospital in the next
year.
Outcomes:
▪ Health care providers can develop new strategies to care for patients before its too late reduces
the number of unnecessary hospitalizations.
▪ Improving the health of patients while decreasing the costs of care.
▪ Winning solutions use a combination of several predictive models.

Source: IBM
11 report
FOR ACADEMIC PURPOSE (DR PREETI KHANNA)
 CASE 2:
VIRTUAL CARE
Virtual health uses
telecommunication and networked
technologies to connect clinicians
with patients (and with other
clinicians and stakeholders) to
remotely deliver health care services
and support well-being. Virtual
health appears to have the capacity
to inform, personalize, accelerate,
and augment people’s ability to care
for one another.

Source: Deloitte report, 2020

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 12
CASE 3: CLINICAL ANALYTICS
▪Client is a leading diagnostic services provider that assists patients and physicians in making
better healthcare decisions to improve patient outcomes.
▪In order to enhance the quality of its analytics and decision support systems, client wanted to
replace their legacy data warehousing solution with a data lake that could manage high
volumes of data (5-10 million messages per day) and provide deeper interactive
visualizations (historical and longitudinal reporting, trend analysis, etc.) and analytical
queries on massive healthcare datasets.

Solutions Used:
▪CitiusTech was selected by the client to develop the infrastructure, given its strong expertise
across healthcare workflows, data mining and standardization, big data processing and
advanced analytics use cases in healthcare.
FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 13
 Benefits:
▪Leverage CitiusTech’s expertise on
Hadoop and big data technology to
build a configurable data model that
processes high volumes of data
efficiently
▪Reduce the dependency on the
legacy system and build a data
repository with standardized, cleansed
and filtered data that is used for
downstream consumption
▪Leverage BI and analytics to provide
powerful reports with rich
visualizations to providers
▪Drive key big data processing and
advanced analytics use cases such as
point of care decision support,
population health reporting, etc.
FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 14
 4. WATSON PHYSICIANS’ DIAGNOSIS AND TREATMENT ASSISTANT
SUPERCHARGED WITH BIG DATA AND ANALYTICS
Watson, a compilation of 21 supercomputer subsystems, is the first of a new class of industry-specific analytical
platforms and decision support systems that use deep content analysis, evidence-based reasoning and natural
language processing to support faster and more precise diagnostics and clinical decision making.

● Watson is the most advanced natural language processor on the planet, as demonstrated by its
performance on Jeopardy.
● With 16 terabytes of memory, twice the amount in the Library of Congress, Watson can store
huge amounts of data, ranging from patient health records to the latest publications about
cutting-edge treatments.
● A doctor typically spends about 10 hours a week reading the latest advances in medical
journals, but Watson can read 200 million pages of text in three seconds and remember every
word.
● Watson takes in data from patient history, family history, symptoms and test findings and
produces a list of disease suggestions ranked by confidence, to assist the physician in diagnosis
and treatment.
● WellPoint is working on a Watson project with Cedars-Sinai Medical Center in Los Angeles to
build decision-making tools for oncologists treating breast, colon and lung cancer.
FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 15
 5. THE INSTITUTE FOR HEALTH METRICS
AND EVALUATION (IHME)
The Institute for Health Metrics and Evaluation (IHME) is gathering a large number of data sets globally
for data analysis and health measurement that can guide policy decisions to improve population health.
● This independent global research center at the University of Washington, funded by the Bill and Melinda
Gates Foundation and the State of Washington, has a mission to answer three questions in global health:
 What are the world’s major health problems?
 How well is society addressing these problems?
 How do we best dedicate resources to maximize health improvement?

● Analyzes data from disparate sources including censuses, surveys, vital statistics, disease registries, hospital
records and others to create evidence for policy and decision making.
● Collaborates with and provides information for inter-governmental agencies, governments, and other
public and global health organizations.
● Currently finishing one of their major research projects, The Global Burden of Disease.

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 16

 6. SICKWEATHER LLC
Sickweather LLC scans social media (Facebook,
Twitter) to track outbreaks of disease, offering
forecasts to users, similar to weather forecasting.
● Offers real time sickness forecasting services to
keep individuals aware of outbreaks in their area.
● Allows individuals to be members and input
information about what is happening in their
area.
● Supported by advertising links to low-cost
medications.
● Currently works in English-speaking countries
with future plans to expand globally.

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 17

 7. ASTHMAPOLIS
Asthmapolis collects data from patients and
provides them with feedback which helps them
better manage their asthma.

● A mobile sensor tracking device attaches to

asthma inhalers to monitor the time and location
of events, plus triggers and symptoms through
an iOS/Android app.
● Helps patients control their asthma, helps
providers and payers identify at-risk patients
● Aggregates real-time data for research and
public health use.

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 18

QUESTIONS NEED TO BE ANSWERED:
How can our organization deliver cost-effective, high-quality health care today and prepare for the
future?

How can we strengthen consumer engagement, improve the patient experience, and
optimize where and how health care is delivered?

How well prepared is our health care system to undertake digital transformation? What needs to
happen to equip our clinical workforce and patients to embrace technology-enabled care?

How do we attract, develop, and retain skilled health care professionals? How do we make
our workforce more efficient and help them feel more fulfilled and satisfied?

FOR ACADEMIC PURPOSE (DR PREETI KHANNA) 19