Big Data Healthcare Industry

Published on June 2016 | Categories: Types, Presentations | Downloads: 50 | Comments: 0 | Views: 379
of 5
Download PDF   Embed   Report

Big data use cases in the healthcare industry



Use of Big data Analytics in the Healthcare Industry
Marutish Varanasi
Big Data Market Consultant
Executive summary:
Big-data initiatives have the potential to transform health care value chain and help patients achieve
better outcomes. But the fruits of these initiatives will be available only to companies who are
committed to looking beyond the current day to day work and are eager to commit resources and build
their capabilities. Only companies committed to this new line of thinking and are focusing on innovation
will be the first to reap the rewards of big data.
Healthcare industry – Transforming
The healthcare industry is undergoing a significant change and transformation in view of the changes
due to the penetration of IT and use of data in the society at large. This change is resulting in a host of
new challenges that can change customer experiences, impact care quality and also the bottom line of
the healthcare providers. With increasing demands from consumers for enhanced healthcare quality
and increased value, healthcare providers and payers are under pressure to deliver better outcomes.
Further the cost dynamics of healthcare are changing, driven by people living longer, the pervasiveness
of chronic illnesses and infectious diseases, and defensive medicine practices. Analytics provide the
mechanism to sort through this torrent of complexity and data, and help healthcare organizations
deliver on these demands.
Healthcare Delivery is getting Complex
The global healthcare industry is experiencing fundamental transformation as it moves from a volumebased business to a value-based business. New market entrants and new approaches to healthcare
delivery are increasing complexity and competition. But with the availability of big data analytics, the
service providers can move to data-driven healthcare that generates insights to the organization which
significantly improves the operational efficiency, quality of care, and profitability.
Market Forces Driving Health Care Transformation

Increasing competition for the healthcare consumer
Health monitors and gene sequencing offering new opportunities
New engagement models
Increased regulatory requirements and reduced reimbursements
Customers are empowered by information, mobility and choice

Why analytics now?
Evidence continues to mount that healthcare is increasingly challenged by entrenched inefficiencies.
These inefficiencies can be attributed to several factors, including the ineffective gathering, sharing and
use of information. The increasing regulatory presence of government places additional focus on

accountability, governance and oversight on the industry. Market dynamics and competitive pressures
require enhanced understanding of underlying trends and a path to differentiation.
Top performers in the healthcare industry use analytics to differentiate, see the future and drive
revenue growth. Beyond the general application of analytics to business goals, the development and use
of analytics among top performers is geared towards achieving specific objectives and priorities.
Analytics can be focused in a variety of ways to improve clinical quality of care, reduce costs and
increase efficiency, and increase revenue and return on investment (ROI.
Objectives of implementing Big Data Analytics?
Big data analytics is the key to unlocking the insights from the data – structured and unstructured. It
empowers the healthcare providers to combine, integrate and analyze all data at once – regardless of
source, type, size, or format – to generate the insights needed to:
Improve Patient Experiences and Outcomes

New regulations and technologies are giving patients more control over their own care, as well
as the freedom to choose innovative providers who can deliver consistent, high-quality,
personalized service. To compete and win, healthcare providers need the ability to monitor
customer experiences in real time, minimize medical errors, and empower people working in
the organizations to make the most of each customer interaction at every touch point.

Analyze structured and unstructured data together at once and quickly

The insights of analyzing structured and unstructured data together at once and quickly can
provide help practitioners provide an exceptional healthcare experience because they can
monitor, analyze and improve their services in totally new ways. At the same time, big data
analytics can help improve patient care quality and safety, by giving healthcare providers
immediate access to consolidated diagnostic information and reducing opportunities for medical

Increase Operational Efficiency for Higher Profitability

With Big Data Analytics companies can identify hidden opportunities to reduce operational costs
and gain efficiencies that directly impact the quality of patient experiences – and the bottom
line. Taking action to improve processes like these can tangibly enhance patient experiences and
boost the organization’s reputation in the marketplace – all while reducing the cost of providing

Benefits and uses of Big Data Analytics?
With Big data healthcare providers get deeper insights about patients which help improve health
outcomes in the following specific areas
 Population Management : understand patients at risk across the population groups
 Intervention : Getting into real time patient intervention using data
 Health Economics : evidence that demonstrates a lower total cost of care and better

 Patient Engagement : Managing customer feedback and reviews
 Care Management : Reduce readmission rates with customized care
 Customer management : Understand customer or patient needs in real time using Big data
analytics and social media
The following healthcare providers use big data analytics to improve the patient outcomes across
various segments of the healthcare market. We look at few cases, were companies are effectively using
Big data analytics and technology to provide real value to customers.
Specific Use cases
3.1 Solving the big data problem at ICU and neonatal units of Children Hospitals
Challenges for Hospitals
Hospitals' intensive care units (ICUs) have bedside monitors that continuously collect data streams on
patient vitals such as respiration, heart rate, and blood pressure. The amount of information is vast,
leading healthcare facilities to take hourly snapshots and then discard the data after several days.
What the neonatal or ICU unit of Children Hospital needs to undertake
If the neonatal or ICU unit of Children Hospital at any of its centers continuously collect's patients
data(neo-natal or infants), there will be a benefit to the hospital from both the short term & long term
data storage and analysis.
Solving a specific problem
For instance, if the neonatal or ICU unit of Children Hospital wants to know how environmental factors,
such as ambient light and noise, impact the quality of care and patient outcomes of infants in the
neonatal ICU; as these patients are perhaps the most sensitive to factors of their environment, but least
capable of communicating what they’re experiencing.
Big Data Platform - tomorrow's competitive advantage
For neonatal or ICU unit of Children Hospital’s these could be a first step towards getting on to a big
data platform to better understand its patients, their conditions, and the quality of care they receive in
support of its mission: to make kids better today and healthier tomorrow
3.2 Using predictive analytics for epileptic seizures
Significant amount of research is being done by global majors to harness the power of analytics to help
healthcare providers deliver more highly personalized care to people living with epilepsy. The goals of
various companies is to deliver an interactive system that translates massive amounts of patient data
and scientific literature into insights that healthcare providers can consult at the point of care to inform
their treatment decisions.
The identification of epileptic seizures significantly relies on monitoring and visual analysis of large
amounts of multi-channel electroencephalographic (EEG) signals. With a goal of automating this timeconsuming and subjective task, companies have developed a patient-speech seizure recognition model
for multi-channel scalp EEG signals. The differentiation between seizure and non-seizure periods is
shown by representing multi-channel EEG signals using a set of features from both time and frequency
domains with visualization features from the data
3.3 Using big data to target preventable readmissions
At Texas Health Harris Methodist Hospital Hurst-Euless-Bedford since fall 2012, more than 14,000
patients admitted to one Texas hospital have had a computer program analyze their medical records to
help clinicians predict what type of care would improve their outcomes. The software used at 213-bed

Texas Health Harris Methodist Hospital Hurst-Euless-Bedford scans each patient's electronic health
record within 24 hours of admission, looking at multiple data elements such as blood-pressure readings
and blood-glucose levels. “It takes all these pieces of data from the EHR, and it has an algorithm, and
tells which patient is at higher risk for heart failure. Armed with 30-day readmission risk scores for heart
failure, the hospital is better able to target intensive follow-up care to those patients who need it most.
Interventions include prompt callbacks, a follow-up consultation with a cardiologist, and a talk with a
social worker and the provision of educational materials.
3.4 How hospitals are using Predictive Analytics to Improve Sepsis Outcomes
The problem
 20,000 deaths per day worldwide
 800,000+/year contract sepsis in the U.S.;
 250K-300K sepsis deaths/year
 $20+ billion annual cost to global healthcare providers
 Mortality rate for septic shock exceeds 50%... and,
 untreated, grows 7.6% per hour
Early identification is critical and difficult
 Evidence unwaveringly suggests that early administration of appropriate antibiotics reduces
 Lack of early recognition is a major obstacle to sepsis bundle initiation
Benchmarking Candidate EHR Rules
EHR triggers may be proposed to aid early sepsis identification. For example, the traditional 4 SIRS
criteria require vitals & labs:
 Heart rate
 Respiratory rate
 Temperature
 White blood cell count, Bands percentage
Benchmark prior to deployment to estimate clinical impact
 Using retrospective EHR data
 Logging results from a live trial implementation
Typical example of 500-bed U.S. hospital
 Proposed EHR alert requires at least 2 out of 4 SIRS criteria
 Benchmark to estimate alert volume and clinical workload
 Results of running proposed alert on 4 months of real-time data
 13142 patients receive the proposed alert
 Over 100 alerts per day on average
 Significant burden: alerts require clinical evaluation for infection & sepsis
 Most alerts are false positives
 Many hospitals end up ignoring or turning off SIRS alerts due to high workload
 Though it can yield results with continuous training & feedback:
Clinical Results
 Alerts precede clinician’s standard of care order of antibiotics by > 12 hours for > 45% of
alertable sepsis patients, substantially improving upon results already achieved by conventional
sepsis initiatives.
 High alerting accuracy (specificity > 99%). Average1-3 alerts per clinical shift for a 500 bed
hospital. Important for avoiding alarm fatigue.

Finally, with the escalating costs of healthcare for citizens across the world, the healthcare industry is
addressing systemic inefficiencies by improving data sharing and collaboration and applying analytics to
improve operations across the value chain, with a final objective to improve and change the patient
outcomes for better.

Sources :

The big-data revolution in US health care Accelerating value and innovation – Mckinsey & Co – Jan 2013 –


National Children's Hospital Applies Enriched Data Analysis to Improve Pediatric Care & Outcomes
Using big data to target preventable readmissions - Joseph Conn | August 2, 2014


Using Predictive Analytics to Improve Sepsis Outcomes - Apr 23, 2014 - UC Davis at HIMSS 2014. Case
Study: SIRS –

Modeling and Detection of Epileptic Seizures using Multi-modal Data Construction and Analysis


Datameer – Using Big Data Analytics in Healthcare


Analytics-Driven Healthcare: Improving Care, Compliance and Cost – Cognizant – February 2013


The value of analytics in healthcare: From insights to outcomes - IBM


Big Data in Healthcare Transformation - Making Better Health Care Decisions – April 2013$file/Sri

Sponsor Documents

Or use your account on


Forgot your password?

Or register your new account on


Lost your password? Please enter your email address. You will receive a link to create a new password.

Back to log-in