The readmission risk flag: Using the electronic health record to automatically identify patients at risk for 30-day readmission

This article outlines the efforts of the University of Pennsylvania Health System in incorporating an automated tool into their electronic medical record (EMR) to flag likely hospital readmissions. Following review of the existing readmissions literature and analysis of their current readmissions data, the team identified one variable that best predicted future readmission: past readmission two or more times within 12 months. Using these data, the team implemented the flagging tool as part of the EMR. During the year-long prospective study of the new program, patients who triggered the alert had readmission rates of 31 percent while those who did not trigger the alert were only readmitted 11 percent of the time.

The article abstract is free. The Penn Medicine press release regarding this study is available at https://www.pennmedicine.org/news/news-releases/2013/november/penn-study-shows-automated-pre.