Health Research and Policy

Abstract

DATE: February 13, 2014
TIME: 1:15 - 3:00 pm
LOCATION: Medical School Office Building, Rm x303
TITLE: A Prospectively Validated Case Finding Algorithm to Estimate the Risk of Future Emergency Department Visits in the state of Maine
SPEAKER: Bruce Ling, PhD
Principal Investigator, Translational Medicine Program,
Dept of Surgery, Stanford

Context: Estimating risk of future emergency department (ED) visits can guide the allocation of resources to better manage high-risk patient populations and thereby reduce unnecessary ED utilization.

Objective: To develop an active case finding (ACF) algorithm that estimates the impending 6-month ED visit risk.

Design, Setting, and Patients: Electronic Medical Record (EMR) episode data from HealthInfoNet (HIN), Maine’s Health Information Exchange (HIE), was used to develop and validate an ACF algorithm for subsequent 6 month ED visit. A retrospective cohort of 831,319 patients with complete clinical histories from January 1, 2012 to December 31, 2012 was utilized for model building and then tested on a prospective cohort of 878,233 patients from July 1, 2012 to June 30, 2013.

Main Outcome Measure: Risk profile of patient population of Maine ED visit in a defined 6-month interval.

Results: The ACF identified 101 variables predictive of future defined 6-month risk of ED visit: age groups (4), history of different encounter types (8), history of primary (17) and secondary (8) diagnosis (Dx), specific chronic diseases (8), laboratory test results (28), history of radiographic tests (3), and history of outpatient prescriptions (25). The c-statistics for the retrospective and prospective cohorts were 0.739 and 0.732 respectively. Cluster analysis identified discrete subpopulations of ACF derived high-risk patients, suggesting the need for diversified care management strategies.

Conclusion: Integration of the ACF into the HIN secure statewide data system in real time prospectively validated its performance. This promises to provide increased opportunity for targeted care intervention to reduce ED utilization and overall healthcare costs, and improve outcomes.

Suggested readings:
Taubman SL, Allen HL, Wright BJ, Baicker K, Finkelstein AN. Medicaid Increases Emergency-Department Use: Evidence from Oregon's Health Insurance Experiment. Science 17. Jan 2, 2014: 343 (6168), pp 263-268.

Billings J, Dixon J, Mijanovich T, Wennberg D. Case finding for patients at risk of readmission to hospital: development of algorithm to identify high risk patients. BMJ. Aug 1,2 2006; 333(7563):327.

Kansagara D, Englander H, Salanitro A, et al. Risk prediction models for hospital readmission: a systematic review. JAMA : the journal of the American Medical Association. Oct 19 2011; 306(15):1688-1698.

Stanford Medicine Resources:

Footer Links: