Predictive Analytics and Business Processes

Came across an article from a year ago on Predictive Analytics in Clinical Healthcare by Scott Wanless, published March 22, 2005. The byline is: "The Value of Predicting Your Next Patient Encounter."

You analysts and enterprise architects out there -- what's been happening in the field in the intervening year? Who's pushed back the frontiers?

The major focus in health IT these days seems to be the electronic medical record (EMR) and, accordingly, networking or information exchange systems to locate and distribute the EMR. Analysts tout the cost savings and increase in quality of care as being critical factors in adopting EMR and networking technology.

But the businesses processes that drive healthcare and that must be supported effectively and efficiently by health IT are every bit as important a focus. Here, for example, is an excerpt from the article above describing the value of predictive analysis:

A patient encounter isn't just a simple event like buying a pack of gum. Rather, it entails many details spanning a number of dimensions such as who, what, when, where and why. Prediction of this encounter, therefore, is a complex undertaking. But it is also rich in possibilities for improving both operational and strategic decisions within the organization. Here are just a few of the elements of a patient encounter.

• Who the patient is as well as his or her health history.
• What healthcare conditions or changes to those conditions caused the encounter.
• Where the patient encounter took place.
• When the encounter took place. This includes the time of day and, more importantly, at what point in time during the patient’s health history.
• Why the patient had the encounter (emergency, routine visit, hospital admission, etc.)
• How the encounter took place. Increasingly, remote care such as phone or e-mail is used in place of an in-person encounter.
• Who provided the care and;
• How much revenue the encounter produced, who paid for it, what it cost, namely, the inescapable financial questions.

The information suggested in that example is typical of information managed in a data warehouse, and the answers to the questions posed are typical of those addressed by predictive analytics. Such information is not only of interest to healthcare providers to improve the quality of service delivery but is also critical to payers who are seeking to optimize the value (costs and profits) of that delivery across patient populations. The more information available, and the broader the range of analytics using that information, the better for all concerned.