Welcome to Health Care POV | sign in | join
ADVANCE Perspective: HIM

It's Not Data Mining, It's Predictive Modeling

Published October 2, 2012 4:23 PM by Sharlene George

(Editor's Note: This guest blog was written from AHIMA 2012 by Jill S. Clark, MBA, RHIA, CHDA, who is AHIMA director of HIM solutions.)

Have you ever been contacted by a credit card company inquiring about a recent large purchase and/or frequency of purchases?  If so, you are the product of a predictive model. 

Predictive modeling applies statistical techniques to determine the likelihood of certain events occurring together. Statistical methods are applied to historical data to "learn" the patterns in data.  In the credit card example, a bank's billing system may suspend the second or third of many large dollar transactions if the spending is not routine.

On Tuesday afternoon at AHIMA's 84th annual Convention and Exhibit in Chicago, Susan E. White, PhD, CHDA was one of many leading professionals to share their knowledge in the Data Analytics track. Dr. White described two sides of predictive modeling use in healthcare - the payer and the provider. Dr. White explained that the Centers for Medicare and Medicaid Services recently has used predictive modeling to identify fraudulent claims prior to payment. On the provider side, predictive modeling can identify potential documentation issues prior to a bill drop. 

While data mining and predictive modeling often use the same data sources, data mining looks for patterns in the data, while predictive modeling uses data mining as a basis and the historical data to predict future behavior. Dr. White illustrated how predictive modeling can be created with decision trees and regression models, and she encouraged HIM professionals to become familiar with the theory behind predictive modeling. 

Dr. White is clear that HIM professionals do not need to be experts in predictive modeling; however, a key takeaway was that a familiarity with the basics is important knowledge for HIM professionals. It will give HIM professionals the ability to go beyond simply responding to requests for health records and to proactively look to the past to better predict the future and identify opportunities for improvement in their organizations.  

2 comments

Magnificent goods from you, man. Lecture Slides: Decision Support Systems and Intelligent Systems, Seventh Edition : Maichel Latupeirissa I have understand your stuff prviuoes to and you're just too great. I actually like what you have acquired here, really like what you are saying and the way in which you say it. You make it enjoyable and you still care for to keep it wise. I cant wait to read much more from you. This is really a tremendous Lecture Slides: Decision Support Systems and Intelligent Systems, Seventh Edition : Maichel Latupeirissa informations.[WORDPRESS HASHCASH] The poster sent us '1892147968 which is not a hashcash value.

Jose Jose, pjkJTvgHRp - GlJnUbrimLiEsBNvP, KrMXDxgAHzoyTrZXT October 24, 2012 1:35 AM
qdSoiGdDBwkVvwOqjFs CO

Here are a few points I would like to discuss.

First, nobody is the "product of a predictive model". This is the kind of sentence that is misleading and gives a bad connotation to data mining. A predictive model is built using past data and allow predicting future situations (generalization principle). If you are contacted by the credit card company, it's marketing. The process behind your selection may be due, among others, to predictive modelling.

Second, data mining is about making sense of data whether it is for prediction (supervised learning) or description (unsupervised learning). So predictive modelling is part of data mining.

Hope this helps.

Sandro October 14, 2012 4:46 PM

leave a comment



To prevent comment spam, please type the code you see below into the code field before submitting your comment. If you cannot read the numbers in the image, reload the page to generate a new one.

Captcha
Enter the security code below:
 

Search

About this Blog

Keep Me Updated