Analytics for Human Information: Is 90 percent of your clinical data missing in action?

From the minute a patient checks into a hospital to the time he or she checks out, meticulous records are kept of the patient’s journey through the healthcare system.   In addition to the standard transactional records such as claims, medications, procedures etc., clinical narratives in the form of free text or unstructured data are provided by highly skilled professionals.   

 

These clinical notes represent some of the most valuable data, but are hardly ever systematically harvested for intelligence except for occasional manual chart reviews. According to a JAMA’s (Journal of American Medical Association) publication[i], 90 percent of clinical data is likely in this form of unstructured text!   

 

 Healthcare_Solution_616x254.jpg

 

What can we do with this kind of data? 

Let’s check out a common issue that is plaguing the healthcare industry,—miscoding—where a discrepancy exists between the diagnostic code and the actual diagnosis.  This disparity may be caused by a simple mistake, but the consequences are far from simple.  

 

The consequences of miscoding impact multiple facets of a healthcare operation from billing, to premium determination, to resource planning.  Up until now, healthcare organizations needed to manually review these records to spot discrepancies. Given the enormous amount of data, it is simply unsustainable. Hence, many such discrepancies go unnoticed and continue to stress an already overtaxed system.  


Fortunately, there’s a new way to activate and leverage dormant clinical notes; addressing this common issue in an automated fashion.   This example simply represents one of many use cases of HP Healthcare Analytics

 

 

To learn more about how the data in your organization can start helping you make a positive difference in patient care, cost control and operational efficiency, please visit www.autonomy.com/healthcare.

 

 

#HPAHIB

 



[i] JAMA viewpoint: The inevitable application of Big Data to healthcare, April 3, 2013. 

Leave a Comment

We encourage you to share your comments on this post. Comments are moderated and will be reviewed
and posted as promptly as possible during regular business hours

To ensure your comment is published, be sure to follow the Community Guidelines.

Be sure to enter a unique name. You can't reuse a name that's already in use.
Be sure to enter a unique email address. You can't reuse an email address that's already in use.
Type the characters you see in the picture above.Type the words you hear.
Search
Showing results for 
Search instead for 
Do you mean 
About the Author
Joe has over 13 years of experience in technology marketing and is currently focused on the analytics solution portfolio. Prior to this rol...
Featured


Follow Us
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation.