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

Authors

  • Charles A. Baillie MD,

    1. Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Christine VanZandbergen PA-C, MPH,

    1. Office of the Chief Medical Information Officer, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Gordon Tait BS,

    1. Information Services, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Asaf Hanish MPH,

    1. Department of Clinical Effectiveness and Quality Improvement, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Brian Leas MS, MA,

    1. Center for Evidence-based Practice, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Benjamin French PhD,

    1. Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    2. Department of Biostatistics and Epidemiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    Search for more papers by this author
  • C. William Hanson MD,

    1. Office of the Chief Medical Information Officer, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Maryam Behta PharmD,

    1. Department of Clinical Effectiveness and Quality Improvement, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    Search for more papers by this author
  • Craig A. Umscheid MD, MSCE, FACP

    Corresponding author
    1. Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    2. Center for Evidence-based Practice, University of Pennsylvania Health System, Philadelphia, Pennsylvania
    3. Department of Biostatistics and Epidemiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    4. Section of Hospital Medicine, Division of General Internal Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
    • Address for correspondence and reprint requests: Craig A. Umscheid, MD, Penn Medicine, 3535 Market Street, Mezzanine, Suite 50, Philadelphia, PA 19104; Telephone: 215-349-8098; Fax: 215-349-5829; E-mail: craig.umscheid@uphs.upenn.edu

    Search for more papers by this author

Abstract

BACKGROUND

Identification of patients at high risk for readmission is a crucial step toward improving care and reducing readmissions. The adoption of electronic health records (EHR) may prove important to strategies designed to risk stratify patients and introduce targeted interventions.

OBJECTIVE

To develop and implement an automated prediction model integrated into our health system's EHR that identifies on admission patients at high risk for readmission within 30 days of discharge.

DESIGN

Retrospective and prospective cohort.

SETTING

Healthcare system consisting of 3 hospitals.

PATIENTS

All adult patients admitted from August 2009 to September 2012.

INTERVENTIONS

An automated readmission risk flag integrated into the EHR.

MEASURES

Thirty-day all-cause and 7-day unplanned healthcare system readmissions.

RESULTS

Using retrospective data, a single risk factor, ≥2 inpatient admissions in the past 12 months, was found to have the best balance of sensitivity (40%), positive predictive value (31%), and proportion of patients flagged (18%), with a C statistic of 0.62. Sensitivity (39%), positive predictive value (30%), proportion of patients flagged (18%), and C statistic (0.61) during the 12-month period after implementation of the risk flag were similar. There was no evidence for an effect of the intervention on 30-day all-cause and 7-day unplanned readmission rates in the 12-month period after implementation.

CONCLUSIONS

An automated prediction model was effectively integrated into an existing EHR and identified patients on admission who were at risk for readmission within 30 days of discharge. Journal of Hospital Medicine 2013;8:689–695. © 2013 Society of Hospital Medicine

Ancillary