Tens of millions of archived patient records are reviewed using supercomputers
with data including health history, symptomology, treatment response, imaging,
neurobiology, and detailed virtual models.
A major goal of outcomes-based healthcare is
identifying highly effective treatments in near real
time—while the patient is still in the office—by
comparing an individual’s genetic makeup, health
history, and symptomology against tens of millions
of archived patient records.
10 June 2016 www.HPCSource.com
burgeoning government regulations and
coverage mandates.
Third-party payers have long maintained
that better healthcare quality and cost control
can go hand in hand. Wellness and other
preventive medicine programs have shown
that this counterintuitive principle can work
in practice. But far larger benefits for quality
and cost will come from the multiyear
transition to personalized, outcomes-based
healthcare (sometimes called precision
medicine.) It’s here where high-performance
data analysis (HPDA)—using high performance computing (HPC) for advanced
analytics—is beginning to make a difference.
What’s the goal?
A major goal of outcomes-based healthcare is
identifying highly effective treatments in near
real time—while the patient is still in the
office—by comparing an individual’s genetic
makeup, health history, and symptomology
against tens of millions of archived patient
records. Today, a high-performance computer
is needed to process all this data and generate
efficacy ratings for a range of treatment
options in short order. When this capability
matures, it will likely serve as a decision-support tool of unprecedented utility for the
global healthcare community.
Where do things stand?
Early outcomes-based initiatives involving
HPC are well underway. Consider the evolu-
tion of IBM’s famous Watson supercomputer:
• In 2011, the IBM Watson supercomputer
stunned a huge American television
audience by defeating two human former
champions of the Jeopardy! game show
in a competition match. Not much later,
IBM said 14 U.S. cancer treatment cen-
ters had signed on to receive personalized
treatment plans selected by a Watson
supercomputer. Watson will parse the
DNA of each patient’s cancer and recom-
mend the optimal medical treatment.
Watson is not the only supercomputer
battling cancer and other diseases. Other
initiatives are finding success using standard
HPC clusters:
• The Center for Pediatric Genomic
Medicine at Children’s Mercy Hospital in
Kansas City, Missouri has been using
supercomputer power to help save the