Back to search

Virginia Commonwealth University

Development and Validation of a Predictive Model of Return-to-Work Outcomes of Injured Employees in Minnesota

Abstract

dc:description.abstract

In Minnesota’s workers’ compensation system, injured employees at risk for sustaining permanent disability may be eligible for receipt of vocational rehabilitation (VR) services if they are determined to be capable of benefitting from such services. VR services can be a valuable resource to injured employees who need assistance minimizing their work disability and maximizing their residual wage-earning capacity. However, for VR services to be effective at a system level, it is necessary to precisely and accurately identify an injured employee’s rehabilitation potential. Failure to do so is likely to result in the misallocation of a scarce and costly resource. Given recent trends in Minnesota’s workers’ compensation system (e.g., higher VR service costs and lower RTW rates among injured employees with indemnity claims), this study was conducted with the purpose of developing and validating an objective, evidence-based method of predicting the RTW status as of claim closure of injured Minnesota employees who sustained permanent impairment and received VR services. To accomplish this purpose, a closed-claim, retrospective design was implemented. Data for this cross-sectional study was obtained from the Minnesota administrative claims database. There were 15,372 claims that met all eligibility criteria. With guidance from the biopsychosocial disablement models developed by Nagi and the World Health Organization, 15 discrete predictor variables that represented medical, individual, and workplace factors were selected for study inclusion. Descriptive and predictive analyses were used to assess the relationship between this study’s RTW outcome and its set of RTW predictors. Using logistic regression, an optimal RTW model was first developed and then internally validated with a split-dataset approach. The optimal RTW model included four main effects (attorney involvement; severity of permanent impairment; age; job tenure) and three first-order interaction effects (pre-injury average weekly wage X pre-injury industry; attorney involvement X severity of permanent impairment; attorney involvement X job tenure). Though not retained in the optimal RTW model, part of body affected and education also had notable bivariate relationships with the outcome. The optimal RTW model’s performance regarding goodness-of-fit and clinical usefulness suggests it may be of value to those assessing rehabilitation potential within Minnesota’s workers’ compensation system.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Health Related Sciences

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Hankins, A. Bentley
Contributors dc:contributor
  • Christine Reid

Subjects

dc:subject × 6

Rights

dc:rights
Statement dc:rights
  • © The Author

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Virginia Commonwealth University
Base URL
scholarscompass.vcu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Hankins, A. Bentley. Development and Validation of a Predictive Model of Return-to-Work Outcomes of Injured Employees in Minnesota. Dissertation thesis, https://doi.org/10.25772/8YSS-PY39