Use of Electronic Health Record Metadata to Assess Hospital Discharge Planning for Post-Acute Transitions

Transitions in care are often poorly coordinated and disruptive to those who transition from hospitalization to post-acute care services. Discharge planning is critical to these transitions in care--summary of pending results, changes in medication and therapy needs, post-discharge care plans--must be completed and transmitted to the patient’s destination. Incomplete discharge planning puts patients at increased risk of care disruption, complications, and adverse health events, resulting in nearly one in four patients being readmitted. Health systems need actionable data to assess where discharge planning breaks down to identify possible improvements in transitional care practices.

Analyzing electronic health record (EHR) metadata may provide these actionable data, but new approaches for using metadata are needed in order to capture, characterize, and evaluate clinician behaviors in this specific workflow. Researchers from the University Minnesota will develop and test novel approaches for using metadata to characterize and evaluate hospital discharge planning practices, with the long-term goal of providing tools to monitor and strengthen specific behaviors within discharge workflows that optimize post-acute transitions of care.

The specific aims of the research are as follows:

• Characterize task and workflow variation as clinicians prepare information for patient hospital discharge.
• Identify measures of the discharge planning process that are associated with patient outcomes.

Using a sample of patients with high-volume, high-readmission risk conditions such as heart failure and pneumonia, the research team will define, measure, and assess the extent of variation in key discharge planning tasks and workflows. They will then descriptively analyze key patient and contextual factors that drive this variation and use generalized linear models to assess which discharge planning tasks and workflows are associated with process (e.g., timely discharge and followup care) and outcome-based (e.g., readmissions) measures of transitional care quality.

The findings will highlight specific ways in which EHR metadata can be used to identify inconsistencies and identify best practices in preparing patients for discharge, powering cycles of learning and improvement that can be scaled and adapted to address other priority health system challenges.