BERN MEDICAL
  • Home
  • Solutions
    • Radiology
    • About Data Visualization
    • Other Services

Big Data in Healthcare

9/20/2011

 
Picture
A visualization of thousands of Wikipedia edits that were made by a single software bot. Each color corresponds to a different page. Image: Fernanda B. Viégas, Martin Wattenberg, and Kate Hollenbach
What is Big Data? Big data are datasets that grow so large that they become awkward to work with using on-hand database management tools. Difficulties include capture, storage, search, sharing, analytics, and visualizing. This trend continues because of the benefits of working with larger and larger datasets allowing analysts to "spot business trends, prevent diseases, combat crime.
 McKinsey addresses the benefits and risks of using big data. 
"If US health care were to use big data creatively and effectively to drive efficiency and quality, the sector could create more than $300 billion in value every year. Two-thirds of that would be in the form of reducing US health care expenditure by about 8 percent."

I think the interesting thing here is that it enables the long tail to start to have an impact. Or, I should say a larger impact. You can sample from a large data set and understand what is going on, generally. But outliers and long tails can get ignored. This is a great place to focus when you think about the concepts of Quality Improvement, Six Sigma, and other improvement movements. 

Being able to impact what is occurring on the fringe can have a great impact. Look at Itunes and Amazon for commercial examples of being able to deliver the Long Tail. Chris Anderson wrote a book a few years ago about the Long Tail. With Bern we operate in the Long Tail. When we analyze a radiology group to discover under-billings we are looking for exceptions. Most groups and I think healthcare providers are good with billing. We are looking for 98% accuracy. But, this still leaves an average of 2% error rate for us to discover. Since these are the long tail types of errors, it is a little more difficult to completely eliminate from happening. Not impossible, but a little more difficult.

So we search for trends in the data, to help explain and understand some of the causes. Perhaps there is a trend in the facility, modality, or scheduler. It may not be cost effective to eliminate some of the errors, provide a daily reconciliation of small dollar items. Some times we get close enough and that is good enough. And maybe that is ok. Because Bern could come in and provide a reconciliation (audit) of a batch of data (quarterly or annually) and be able to recover some of the money and do so in a much cost effective manner.

Comments are closed.

    BERN BLOG

    Blog written by:
    David Fuhriman, CEO
    Contact Me

    Other Useful blogs

    Occam's Razor
    Six Pixels
    Junk Charts
    Kaizen Analytics
    Zoom Metrix

    Archives

    June 2013
    May 2013
    April 2013
    March 2013
    February 2013
    January 2013
    December 2012
    November 2012
    October 2012
    September 2012
    August 2012
    July 2012
    June 2012
    May 2012
    April 2012
    March 2012
    February 2012
    January 2012
    December 2011
    November 2011
    October 2011
    September 2011
    August 2011

    Springboard
Powered by Create your own unique website with customizable templates.