EMR Analytics Reduce Cardiac Readmissions

Posted on August 6, 2013 I Written By

Anne Zieger is veteran healthcare editor and analyst with 25 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A new study has concluded that EMRs can help reduce hospital readmissions of high-risk heart failure patients, according to a report in Modern Healthcare.

The study, which appeared in BMJ Quality & Safety, looked at more than 1,700 adult inpatients who had been diagnosed with heart failure, myocardial infarction and pneumonia over a two-year period at Dallas-based Parkland Memorial Hospital.

Researchers first used an EMR-based software package to sort high-risk from low-risk heart failure patients. The EMR analytics software drew on 29 clinical, social and behavioral factors within 24 hours of a patient’s admission for heart failure.

Using this tool, researchers were able to cut readmission rates for the studied patients by from 26.2 percent to 21.2 percent, according to EHR Intelligence. Not only that, hospitals were able to shift resources to patients at highest risk while they were still in the hospital.

As we who work in and around health IT know, reducing readmissions through better data analysis is something of an obvious move.  EMR users may not yet have the predictive analytics in place to make this happen, but I think solutions will be coming to the marketplace, and soon.

That being said, it could be a while before such solutions reach their full potential. After all, predicting patient needs is more likely to work if hospitals and health systems integrated EMRs with community medical practices, and we all know how challenging this is still.

Perhaps the work of building robust predictive analytics systems can begin in earnest in situations where the hospital owns the medical practice and both use the same system. But even in those cases, hospitals will still be treating patients seen by community practices outside of their organization.

Bottom line, this study is an interesting look at the possibilities of mining EMR data for direct patient care improvement. Let’s see how many more projects of this kind hit the news this year.