Predictive Modeling Key in Reducing Readmissions

In an effort to reduce readmissions, many hospitals around the country are turning to their own technological models.  One of the most innovative models can be found at the University of Pittsburgh Medical Center (UPMC), where officials use a variety of modeling tools to identify patients who are “high utilizers” of their services.  Representatives from UPMC say that most patients do get better and that the secret it finding the 20% of patients who won’t but will respond to intensive, coordinated care.  UPMC relies on a questionnaire they administer at the time the patient checks in. They say a certain combination of answers signal that the patient could be 300% more expensive than a patient who did not hit that combination.

Predictive modeling is considered an on-going, continuously learning system; the aim for providers is to keep searching until they find a model that works for them.  Similarly to UPMC, Penn Medicine analyzes internal data for predictive modeling.

Both providers say that they are typically unimpressed with the technology new vendors have to offer because they believe internal efforts fare much better.  According to them, internal efforts by an entire team made up of highly trained specialists help make predictive modeling successful.

Click here to read more


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s