A Community Health Information Exchange-based Hospital Readmission Risk Prediction & Notification System
Project Final Report (PDF, 250.21 KB) Disclaimer
The findings and conclusions in this document are those of the author(s), who are responsible for its content, and do not necessarily represent the views of AHRQ. No statement in this report should be construed as an official position of AHRQ or of the U.S. Department of Health and Human Services.
Disclaimer
Disclaimer details
Project Details -
Completed
-
Grant NumberR21 HS022578
-
AHRQ Funded Amount$299,803
-
Principal Investigator(s)
-
Organization
-
LocationBaltimoreMaryland
-
Project Dates09/30/2013 - 09/29/2015
-
Technology
-
Care Setting
-
Population
-
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.
Citation: Kharrazi, H. A Community Health Information Exchange-based Hospital Readmission Risk Prediction & Notification System - Final Report. (Prepared by Johns Hopkins University under Grant No. R21 HS022578). Rockville, MD: Agency for Healthcare Research and Quality, 2015.
Link:
r21hs022578-kharrazi-final-report-2015.pdf
(250.21 KB)
The findings and conclusions in this document are those of the author(s), who are responsible for its content, and do not necessarily represent the views of AHRQ. No statement in this report should be construed as an official position of AHRQ or of the U.S. Department of Health and Human Services.
Principal Investigator: Kharrazi, Hadi
Project Name: A Community Health Information Exchange-based Hospital Readmission Risk Prediction & Notification System
Document Type: Report
Technology: Health Information Exchange
Population: Researcher
Citation: Swain MJ, Kharrazi H. Feasibility of 30-day hospital readmission prediction modeling based on health information exchange data. Int J Med Inform 2015;84(12):1048–56. PMID: 26412010.
Principal Investigator: Kharrazi, Hadi
Project Name: A Community Health Information Exchange-based Hospital Readmission Risk Prediction & Notification System
Document Type: Journal Publication
Research Method: Quantitative, Systematic Review
Technology: Health Information Exchange
Disclaimer
Disclaimer details