© 2014 IBM Corporation 1
IBM – Big Data for Healthcare Using Data, Analytics and Insight to Improve Health
John Crawford, Healthcare Industry Leader, IBM Europe
6 May 2014
© 2014 IBM Corporation 2
What is Big Data and why is it important?
Characteristics of Big Data
Source: IBM Institute for Business Value, 2012
© 2014 IBM Corporation 3
Foundational
• What happened?
• When and where?
• How much?
Advanced, Predictive
• What will happen?
• What will be the impact?
• Dashboards
• Clinical data repositories
Data integration
Data warehouse
• Basic reporting
• Spreadsheets
Transaction
reporting
• Enterprise analytics
• Evidence-based medicine
• Outcomes analytics
Decision support
analytics
• Personalised healthcare
• Population risk models
• Optimising care systems
Predictive
analytics
Prescriptive
• What are potential scenarios?
• What is the best course?
• How can we pre-empt and
mitigate the crisis?
How is Big Data changing Analytics?
© 2014 IBM Corporation 4
Exploiting Big Data to support Personalised Medicine and Public Health
Capturing and using data enables new insights into populations and individualized care
Analytics innovations
Advanced analytics apply Natural Language Processing and
Artificial Intelligence to complement tools that surface
patterns and anomalies
New platforms Collaborative and mobile technology platforms facilitate a holistic view of the individual and enable new ways to coordinate care delivery
New and numerous
data sources Transactional,
application, mobile, social, care provider,
publications, research, and individual
information
of the world’s data was generated in just
the last two years
90%
expected compound annual growth rate
(CAGR) in the big data marketplace by 2016*
31.7%
*IDC Worldwide Big Data Technology and Services 2012-2016 Forecast, doc #238746, Dec 2012
© 2014 IBM Corporation 5
Big Data & Analytics
5
The State University of New
York (SUNY) Buffalo gains
insights from Big Data to
slow progression of multiple
sclerosis
5
Need
• Researchers needed to quickly build models
using a range of variable types and run them
on a high-performing environment on huge
data sets spanning more than 2,000 genetic
and environmental factors that may contribute
to multiple sclerosis (MS) symptoms
Benefits
• Able to reduce the time required to conduct
analysis from 27.2 hours to 11.7 minutes
• Researchers are empowered to look for
potential factors contributing to the risk of
developing MS
© 2014 IBM Corporation 6
Big Data & Analytics University of Ontario
Institute of Technology
(UOIT) uses Big Data to
improve quality of care for
neonatal babies
Need
• Performing real-time analytics using
physiological data from neonatal babies
• Continuously correlates data from medical
monitors to detect subtle changes and alert
hospital staff sooner
• Early warning gives caregivers the ability to
proactively deal with complications
Benefits
• Detecting life threatening conditions 24
hours sooner than symptoms exhibited
• Lower morbidity and improved patient care
6 6
© 2014 IBM Corporation 7
Big Data & Analytics
7
EuResist GEIE Network
uses Big Data to predict
response of HIV patients to
treatment based on viral
genomics
7
Need
• Predicting best treatment strategy for HIV
sufferers from a cocktail of drugs, comparing
new cases with a database of over 61,000
previous cases, over 150,000 therapy options
and nearly 700,000 viral loads
Benefits
• Using decision support delivers 78% accuracy
in treatment plans
• EuResist prediction engine outperformed 9 out
of 10 human experts in predicting outcome
© 2014 IBM Corporation 8
What is Watson?