UPMC puts power of analytics to work

$100M invested to improve decision-making to transform care

PITTSBURGH  -  With a $100 million investment, UPMC has joined the ranks of an increasing number of medical and research centers across the country aiming to mine and analyze its data in order to provide more precise care.

At UPMC, it's a five-year initiative that employs sophisticated enterprise analytics with technology from Oracle, IBM, Informatica and dbMotion.

UPMC will break down its data silos and create what officials call a best-in-class data warehouse to bring together clinical, financial, administrative, genomic and other information that today is difficult to integrate and analyze.

Advanced analytic and predictive modeling applications for clinical and financial decision-making are expected to produce better patient outcomes and research capabilities across UPMC. At the same time, executives expect to improve quality across the enterprise and to reduce cost.

 "Every patient is different; every patient has a unique story," said Steven D. Shapiro, MD, chief medical and scientific officer at UPMC. "This comprehensive analytics approach will enable us to treat each patient in a personalized way to produce the best possible results."

UPMC, a $10 billion global enterprise, employs more than 55,000 people and operates more than 20 hospitals, 400 doctors' offices and outpatient sites, a health insurance services division, and international and commercial services. The organization has been at the forefront of investing in electronic health records, interoperability and financial management systems.

"As one of the largest and most technologically sophisticated healthcare systems in the world, we are perfectly positioned to leverage our vast stores of data to innovate the way that patient care is delivered," said Lisa Khorey, vice president of enterprise systems and data management at UPMC.

In preparation, Khorey said, UPMC worked with the Carnegie Mellon Software Engineering Institute to methodically study best practices in analytics both inside and outside of healthcare.

The explosion of data  -  now totaling more than 3.2 petabytes at UPMC alone  -  "is moving faster than our ability to transform that information into intelligence and improved decision-making at the point of care," said Shapiro.

Also, with the rapidly decreasing cost of sequencing genes, huge amounts of genomic information will be added to that database in the future, he noted.

Over the next two years, UPMC will install the hardware and software needed to create a comprehensive data warehouse that will bring together data from more than 200 sources of information across UPMC, UPMC Health Plan and outside entities, including labs and pharmacies.

Clinicians, researchers and administrators will have secure, real-time access to data and analytic tools that fit their particular interests and needs.

"UPMC's analytics initiative is one of the most ambitious and comprehensive efforts of its kind in healthcare," said Neil de Crescenzo, senior vice president and general manager, Oracle Health Sciences. "Given the size, scope and influence of this leading academic medical center, the discoveries made here are likely to transform the practice of medicine far beyond the walls of UPMC."

Early analytics projects are expected to improve quality reporting and measurement across UPMC hospitals and physician offices; provide insight into the effectiveness of treatments and the cost of variations in care; and offer predictive alerts that will improve disease prevention.