Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool
Unplanned hospital readmissions represent a significant health care value problem with high costs and poor quality of care. A significant percentage of readmissions could be prevented if clinical inpatient teams were better able to predict which patients were at higher risk for readmission. Many of...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/10/3/103 |
| _version_ | 1797555531557109760 |
|---|---|
| author | David Gallagher Congwen Zhao Amanda Brucker Jennifer Massengill Patricia Kramer Eric G. Poon Benjamin A. Goldstein |
| author_facet | David Gallagher Congwen Zhao Amanda Brucker Jennifer Massengill Patricia Kramer Eric G. Poon Benjamin A. Goldstein |
| author_sort | David Gallagher |
| collection | DOAJ |
| description | Unplanned hospital readmissions represent a significant health care value problem with high costs and poor quality of care. A significant percentage of readmissions could be prevented if clinical inpatient teams were better able to predict which patients were at higher risk for readmission. Many of the current clinical decision support models that predict readmissions are not configured to integrate closely with the electronic health record or alert providers in real-time prior to discharge about a patient’s risk for readmission. We report on the implementation and monitoring of the Epic electronic health record—“Unplanned readmission model version 1”—over 2 years from 1/1/2018–12/31/2019. For patients discharged during this time, the predictive capability to discern high risk discharges was reflected in an AUC/C-statistic at our three hospitals of 0.716–0.760 for all patients and 0.676–0.695 for general medicine patients. The model had a positive predictive value ranging from 0.217–0.248 for all patients. We also present our methods in monitoring the model over time for trend changes, as well as common readmissions reduction strategies triggered by the score. |
| first_indexed | 2024-03-10T16:48:50Z |
| format | Article |
| id | doaj.art-7a71d229e1064c1db7a7d487ac00b547 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T16:48:50Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-7a71d229e1064c1db7a7d487ac00b5472023-11-20T11:23:34ZengMDPI AGJournal of Personalized Medicine2075-44262020-08-0110310310.3390/jpm10030103Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support ToolDavid Gallagher0Congwen Zhao1Amanda Brucker2Jennifer Massengill3Patricia Kramer4Eric G. Poon5Benjamin A. Goldstein6Hospital Medicine Programs, Division of General Internal Medicine, Duke University, DUMC 100800, Durham, NC 27710, USADepartment of Biostatistics and Bioinformatics, Duke University Medical Center, 2424 Erwin Road Suite 1102 Hock Plaza (Box 2721), Durham, NC 27710, USACenter for Predictive Medicine, Duke Clinical Research Institute, Duke University, 200 Morris Street, Durham, NC 27701, USAPerformance Services, Duke University Health System, 615 Douglas St Suite 600, Durham, NC 27705, USACase Management, Duke University Health System, Dept 946, Durham, NC 27710, USADivision of General Internal Medicine, Duke University, 2424 Erwin Road, Durham, NC 27705, USADepartment of Biostatistics and Bioinformatics, Duke University Medical Center, 2424 Erwin Road Suite 1102 Hock Plaza (Box 2721), Durham, NC 27710, USAUnplanned hospital readmissions represent a significant health care value problem with high costs and poor quality of care. A significant percentage of readmissions could be prevented if clinical inpatient teams were better able to predict which patients were at higher risk for readmission. Many of the current clinical decision support models that predict readmissions are not configured to integrate closely with the electronic health record or alert providers in real-time prior to discharge about a patient’s risk for readmission. We report on the implementation and monitoring of the Epic electronic health record—“Unplanned readmission model version 1”—over 2 years from 1/1/2018–12/31/2019. For patients discharged during this time, the predictive capability to discern high risk discharges was reflected in an AUC/C-statistic at our three hospitals of 0.716–0.760 for all patients and 0.676–0.695 for general medicine patients. The model had a positive predictive value ranging from 0.217–0.248 for all patients. We also present our methods in monitoring the model over time for trend changes, as well as common readmissions reduction strategies triggered by the score.https://www.mdpi.com/2075-4426/10/3/103hospitalizationpatient readmissionclinical decision support systemsreadmission risk modelrisk assessment |
| spellingShingle | David Gallagher Congwen Zhao Amanda Brucker Jennifer Massengill Patricia Kramer Eric G. Poon Benjamin A. Goldstein Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool Journal of Personalized Medicine hospitalization patient readmission clinical decision support systems readmission risk model risk assessment |
| title | Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool |
| title_full | Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool |
| title_fullStr | Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool |
| title_full_unstemmed | Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool |
| title_short | Implementation and Continuous Monitoring of an Electronic Health Record Embedded Readmissions Clinical Decision Support Tool |
| title_sort | implementation and continuous monitoring of an electronic health record embedded readmissions clinical decision support tool |
| topic | hospitalization patient readmission clinical decision support systems readmission risk model risk assessment |
| url | https://www.mdpi.com/2075-4426/10/3/103 |
| work_keys_str_mv | AT davidgallagher implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT congwenzhao implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT amandabrucker implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT jennifermassengill implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT patriciakramer implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT ericgpoon implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool AT benjaminagoldstein implementationandcontinuousmonitoringofanelectronichealthrecordembeddedreadmissionsclinicaldecisionsupporttool |