Published on 29 Jun 2012
"This solution will accelerate our ability to devise, test and publish new computationally intensive algorithms applied to large longitudinal healthcare databases that we hope become the ‘gold standard’ for researchers globally." - Dr. Sebastian Schneeweiss
Customer:
Brigham and Women’s Hospital
Industry:
Education, Healthcare
Deployment country:
United States
Solution:
Big Data, Data Warehouse, Smarter Planet
Smarter Planet:
Smarter Healthcare
Overview
Brigham and Women’s Hospital (BWH) is a 793-bed teaching affiliate of Harvard Medical School located in the Longwood Medical Area in Boston, MA. In addition to its biomedical research laboratories, BWH offers inpatient and outpatient services and clinics, neighborhood primary care health centers and state-of-the art diagnostic and treatment technologies.
Business need:
Traditional methods for analyzing large databases have become inadequate to deliver the potential that the research team at BWH envisioned for its growing trove of information. The institution was seeking an information management solution that would change the game, ultimately developing into a research tool that could learn over time, bringing the very latest drug effectiveness and interaction data right to patients’ bedsides.
Solution:
BWH recognizes the need to advance the complex analytics and computing power it deploys to deliver “high-dimensional” pharmacoepidemiology research results. The BWH information management solution handles massive data volumes and delivers analytics quickly, enabling the research team to conduct multiple drug studies simultaneously, and design, test and apply new algorithms to identify drug risk warning signals. BWH intends to use the solution to automate a process for continuous drug safety monitoring and evolve it into a system that learns from prior results to improve predictive accuracy.
Benefits:
Enables one of the department’s novel algorithms, its high-dimensional propensity scoring, to run 20 to 30 times faster than in its previous relational database environment;
Allows the department to conduct basic analytic processing at two to three times previous speeds, with no change in code;
Enables research studies on larger databases and exploration of previously inconceivable new research avenues
Case Study
Brigham and Women’s Hospital (BWH) is a 793-bed teaching affiliate of Harvard Medical School located in the Longwood Medical Area in Boston, MA. In addition to its biomedical research laboratories, BWH offers inpatient and outpatient services and clinics, neighborhood primary care health centers and state-of-the art diagnostic and treatment technologies.
The Opportunity
Traditional methods for analyzing large databases have become inadequate to deliver the potential that the research team at BWH envisioned for its growing trove of information. The institution was seeking an information management solution that would change the game, ultimately developing into a research tool that could learn over time, bringing the very latest drug effectiveness and interaction data right to patients’ bedsides.
What Makes It Smarter
Drug risk awareness saves lives, which is why BWH recognizes the need to advance the complex analytics and computing power it deploys to help deliver “high-dimensional” pharmacoepidemiology research results. BWH implemented an information management solution that handles massive data volumes with ease and delivers analytics with unprecedented speed. The research team found it could immediately make full use of its large data sets and conduct multiple drug studies simultaneously. The solution is enabling researchers to design, test and apply brand-new algorithms to help identify drug risk warning signals far more quickly. The institution intends to use the solution to automate a process for continuous drug safety monitoring and evolve the solution into a system that learns from prior results to continuously improve its predictive accuracy.
Real Business Results
- Enables one of the department’s novel algorithms, its high-dimensional propensity scoring, to run 20 to 30 times faster than in its previous relational database environment
- Allows the department to conduct basic analytic processing at two to three times previous speeds, with no change in code
- Enables research studies on larger databases and exploration of previously inconceivable new research avenues
Please contact your IBM sales representative or IBM Business Partner.
Visit us at: ibm.com/healthcare
To learn more about Brigham and Women’s Hospital visit:
www.brighamandwomens.org
Components
IBM products and services that were used in this case study.
Software:
IBM Netezza Analytics, IBM Netezza 1000
Legal Information
© Copyright IBM Corporation 2012 IBM Corporation Software Group Route 100 Somers, NY 10589 Produced in the United States June 2012 IBM, the IBM logo and ibm.com are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the Web at “Copyright and trademark information” at ibm.com/legal/copytrade.shtml Netezza® is a trademark or registered trademark of IBM International Group B.V., an IBM Company. This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.