Project Details - Ended
- Grant Number:R21 HS022578
- Funding Mechanism:
- AHRQ Funded Amount:$299,803
- Principal Investigator:
- Project Dates:9/30/2013 to 9/29/2015
- Care Setting:
- Type of Care:
- Health Care Theme:
Preventing avoidable hospital readmissions is one way to reduce waste and costs in health care. Targeting interventions to those at risk is one strategy to reduce those readmissions. To identify those individuals at risk, readmission risk prediction models (RRPMs) have been developed that use data from health data plans and hospital administrative databases. Incorporating data from health information exchanges (HIEs) into these models allows the models to execute in real time and to predict readmissions both to a given hospital as well as across hospitals. This use of HIE data has the potential to significantly contribute to preventable hospital readmissions within a community.
This project developed a 30-day RRPM that incorporated data from an HIE and validated the new model by comparing it to an existing predication model.
The specific aim of this project was as follows:
- Derive and validate a 30-day hospital RRPM based on Admission Discharge and Transmission (ADT) messages transacted by HIE entities.
The investigators conducted a systematic literature review to identify significant readmission variables. These readmission variables were then mapped with the ADT message segments. A RRPM library of predictive models for readmission was then developed and compared to existing readmission prediction models. It was found that the RRPMs have acceptable predictive power to detect potential preventable readmissions. The investigators concluded that readmission prediction models can be developed based on transactional HIE data, with more work needed to ensure higher accuracy and increased generalizability.