Health IT Pulse

Mar 22 2013   12:09PM GMT

Report says EHRs can be springboarded to clinical data analytics

EmilyHuizenga Profile: EmilyHuizenga

Big Data
CDS and data analytics
Data Mining
EHR implementation
EHR systems

Coupling EHRs with new analytics tools and normalizing best big data practices will be key to effectively utilizing big data in the health care industry, an Institute for Health Technology Transformation (iHT2) report concludes.

And those best-practices are needed, stat. The report, “Transforming Health Care through Big Data,” cites an Oracle poll indicating health care organizations are accumulating 85% more data than they did two years ago. In that poll, 77% of health care executives grade their organizations at a “C” or below for data management – with none giving their organizations an “A.” But the report, among others, also shows the opportunity: Citing 2011 McKinsey data, iHT2 estimates the health care sector could potentially realize $300 billion in annual value by successfully leveraging big data

Providers must couple EHRs with new analytics tools to reap the benefits big data has to offer, the report says. Despite the high priority they place on EHRs, health care leaders say their organizations are struggling to properly implement them: while 34% reported being able to capture data from EHRs to help patients, 43% said they were unable to collect sufficient data to improve care.

One solution is electronic sensors, which use real-time analysis to monitor critical biochemical markers and stream data from individual patients to secure analysis systems. The information can then be used meaningfully to alert providers of potentially adverse events like side effects to medications or early development of infection and allergic reactions. One example: The report cites a Kaiser Permanente dataset that led to the discovery of adverse side effects, and ultimately the removal of the drug Vioxx from the market.

Providers should also use big data to drive their clinical decision support (CDS) systems. . Some CDS modules can analyze images in clinical databases for pre-diagnosis help, or mine medical literature to create a medical expertise database capable of suggesting treatment options based on patients’ medical records.

What’s more, doubling EHRs as data sources opens the door for mining de-identified information, which researchers can use statistically to examine trends, identify care gaps, measure outcomes and ultimately pinpoint costly procedures, waste and delays.

To do this, providers must make an effort to streamline their big data efforts in the form of outcomes-based research, also known as comparative effectiveness research. The report cites studies that reveal wide variations in health care data practices, outcomes and costs among providers. For example, researchers at the Dartmouth Atlas project have documented that some primary care physicians order more than twice as many CT scans as their colleagues in the same practice.

To normalize data management and move toward a culture of best practices, the report suggests providers implement a data governance framework, engage providers, foster competition and transparency, bake analytics into training, provide for flexibility in information transference and when possible, choose in-house solutions over vendor-generate solutions.

 Comment on this Post

There was an error processing your information. Please try again later.
Thanks. We'll let you know when a new response is added.
Send me notifications when other members comment.

Forgot Password

No problem! Submit your e-mail address below. We'll send you an e-mail containing your password.

Your password has been sent to:

Share this item with your network: