April 4, 2012

Fixing Healthcare with Big Data

Robert Gelber

Yesterday, Roger Foster, the Senior Director for DRC’s technologies group, discussed the immense expenses of the U.S. healthcare system.  The 2.6 trillion dollar market is ripe for new efficiencies reducing overall costs and improving public health.  He believes these enhancements can be achieved with the help of big data.

With over 20 years of leadership experience in tech management and operations support for government agencies and commercial businesses, Foster has tackled big data problems from astrophysics to healthcare. His experience has delivered insights into the healthcare system’s current state as well as what modifications could extend its viability.

A Thompson Reuters report estimated that $600-$850 billion are wasted in healthcare costs that fail to improve patient outcomes. The source of these costs come from medical errors, criminal fraud, un-warranted use of health services, lack of preventative care and administrative inefficiencies to name a few.

To combat these issues, healthcare providers ingest massive data sets of biomediacal information. Hospitals storing petascale datasets are becoming more commonplace.

A report by Graham Hughes, CMO of the SAS Center for Health Analytics and Insights, estimated that US healthcare data sets reached 150 exabytes in 2011. However, the will likely continue as more data is being generated. The petascale systems healthcare providers implement today, will evolve into exascale, zetascale and yottascale systems in the future.

Having massive data stores alone is just one piece of this puzzle. Proper modeling and sharing of healthcare data can drive efficiencies while improving patient outcomes. One study from the McKinsey Global Health Institute estimated a cost reduction of $200-300 billion through the use of big data analytics in healthcare.

The government has a strong influence in healthcare through investments in insurance for Medicare / Medicaid recipients and its own employees. Roughly 40 percent of all healthcare expenditures are paid by the government. By improving data management techniques, the government has the potential to boost patient outcomes and reduce costs in the system.  

Foster set forth a six-part approach aimed at reducing costs and improving patient outcomes using big data.

Unwarranted use

Many healthcare providers focus on a fee-for-service model, which promotes recurring medical visits at higher rates. Instead, big data analytics could help generate a model that implements a performance-based payment method.

Fraud waste & abuse

Criminal organizations defraud Centers for Medicare and Medicaid Services (CMS) by charging for services never rendered. Using big data analytics, these individuals could be tracked much faster through the employment of outlier algorithms

Administrative costs

The departments of Veterans Affairs (VA), Military Heath System (MHS) and others suffer high costs due to administrative inefficiencies in billing and medical records management. By updating billing systems and employing big data records management, facilities could spend less time working on bookkeeping and more time providing accurate information to doctors and physicians assistants.

Provider inefficiencies

A wide implementation of clinical decision systems could reduce errors and increase congruency among various healthcare providers. Such systems could also predict risks based on population data.

Lack of coordinated care

The process of sharing medical data across institutions has become cumbersome resulting in redundant information and added costs. Improved sharing of information would open systems up to predictive modeling and also allow patients to view their history. This would allow the patient to have greater control in their treatment.

Preventable conditions

Government agencies like the Centers for Disease Control (CDC), the Food and Drug Administration (FDA) and the National Institutes of Health (NIH) study data to help prevent disease outbreaks and survey new drugs on the market. Through the use of big data, healthcare providers can track the change in behavior of patients after treatment. Using this data, medical professionals can better educate patients of the resulting effects from their behavior.

Foster is confident that big data will answer pressing issues in the healthcare as long as solutions are deployed properly.

Related Stories

New Platform Caters to Cancer Research

Predictive Modeling Meets Patient Behavior

Missing Opportunities in Healthcare Data