Journal of Occupational Rehabilitation

, Volume 29, Issue 4, pp 740–753 | Cite as

Predictors of Return to Work for Occupational Rehabilitation Users in Work-Related Injury Insurance Claims: Insights from Mental Health

  • Hadi Akbarzadeh KhorshidiEmail author
  • Miriam Marembo
  • Uwe Aickelin


Purpose This study evaluates the Occupational Rehabilitation (OR) initiatives regarding return to work (RTW) and sustaining at work following work-related injuries. This study also identifies the predictors and predicts the likelihoods of RTW and sustainability for OR users. Methods The study is conducted on the compensation claim data for people who are injured at work in the state of Victoria, Australia. The claims which commenced OR services between the first of July 2012 and the end of June 2015 are included. The claims which used original employer services (OES) have been separated from claims which used new employer services (NES). We investigated a range of predictors categorised into four groups as claimant, injury, and employment characteristics and claim management. The RTW and sustaining at work are outcomes of interest. To evaluate the predictors, we use Chi-squared test and logistic regression modelling. Also, we prioritized the predictors using Akaike Information Criterion (AIC) measure and Cross-validation error. Four predictive models are developed using significant predictors for OES and NES users to predict RTW and sustainability. We examined the multicollinearity of the developed models using Variance Inflation Factor (VIF). Results About 75% and 60% of OES users achieved RTW and have been sustained at work respectively, whilst just approximately 30% of NES users have been placed at a new employer and 25% of them have been sustained at work. The predictors which have the most association with OES and NES outcomes are the use of psychiatric services and age groups respectively. We found that having mental conditions is as an important indicator to allocate injured workers into OES or NES initiatives. Our study shows that injured workers with mental issues do not always have lower RTW rate. They just need special consideration. Conclusion Understanding the predictors of RTW and sustainability helps to develop interventions to ensure sustained RTW. This study will assist decision makers to improve design and implementation of OR services and tailor services according to clients’ needs.


Occupational rehabilitation Return to work Mental health Workers’ compensation Injuries 



ISCRR is a joint initiative of WorkSafe Victoria, the Transport Accident Commission (TAC) and Monash University.


This study is funded by WorkSafe Victoria (WSV) through the Institute of Safety, Compensation and Recovery Research (ISCRR).

Compliance with Ethical Standards

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.

Informed Consent

Statement not required. This study was performed using a de-identified administrative dataset, with ethics approval granted by Monash University Human Research Ethics Committee (CF09/3150—2009001727).


  1. 1.
    Berecki-Gisolf J, Collie A, McClure RJ. Determinants of physical therapy use by compensated workers with musculoskeletal disorders. J Occup Rehabil. 2013;23(1):63–73.PubMedCrossRefGoogle Scholar
  2. 2.
    Pransky G, Gatchel R, Linton SJ, Loisel P. Improving return to work research. J Occup Rehabil. 2005;15(4):453–457.PubMedCrossRefGoogle Scholar
  3. 3.
    Brouwer S, Franche RL, Hogg-Johnson S, Lee H, Krause N, Shaw WS. Return-to-work self-efficacy: development and validation of a scale in claimants with musculoskeletal disorders. J Occup Rehabil. 2011;21(2):244–258.PubMedCrossRefGoogle Scholar
  4. 4.
    Park J, Roberts MR, Esmail S, Rayani F, Norris CM, Gross DP. Validation of the readiness for return-to-work scale in outpatient occupational rehabilitation in Canada. J Occup Rehabil. 2018;28(2):332–345.PubMedCrossRefGoogle Scholar
  5. 5.
    Franche RL, Krause N. Readiness for return to work following injury or illness: conceptualizing the interpersonal impact of health care, workplace, and insurance factors. J Occup Rehabil. 2002;12(4):233–256.PubMedCrossRefGoogle Scholar
  6. 6.
    Awang H, Mansor N. Predicting employment status of injured workers following a case management intervention. Saf Health Work. 2018;9(3):347–351PubMedPubMedCentralCrossRefGoogle Scholar
  7. 7.
    Berecki-Gisolf J, Clay FJ, Collie A, McClure RJ. Predictors of sustained return to work after work-related injury or disease: Insights from workers’ compensation claims records. J Occup Rehabil. 2012;22(3):283–291.PubMedCrossRefGoogle Scholar
  8. 8.
    Gray SE, Hassani-Mahmooei B, Cameron ID, Kendall E, Kenardy J, Collie A. Patterns and predictors of failed and sustained return-to-work in transport injury insurance claimants. J Occup Rehabil. 2018:28(4):1–9.CrossRefGoogle Scholar
  9. 9.
    Prang KH, Hassani-Mahmooei B, Collie A. Compensation research database: population-based injury data for surveillance, linkage and mining. BMC Res Notes. 2016;9(1):1–11.CrossRefGoogle Scholar
  10. 10.
    Hou WH, Chi CC, Lo HL, Chou YY, Kuo KN, Chuang HY. Vocational rehabilitation for enhancing return-to-work in workers with traumatic upper limb injuries. Cochrane Database Syst Rev. 2017. Scholar
  11. 11.
    Athanasou JA. A vocational rehabilitation index and return to work after compensable occupational injuries in Australia. Aust J Rehabil Couns. 2017;23(2):69–78.CrossRefGoogle Scholar
  12. 12.
    Lingard H, Saunders A. Occupational rehabilitation in the construction industry of Victoria. Constr Manag Econ. 2004;22(10):1091–1101.CrossRefGoogle Scholar
  13. 13.
    Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement. BMC Med. 2015;13(1):1–10.PubMedPubMedCentralCrossRefGoogle Scholar
  14. 14.
    Gray SE, Hassani-Mahmooei B, Kendall E, Cameron ID, Kenardy J, Collie A. Factors associated with graduated return to work following injury in a road traffic crash. J Transp Health. 2018;10:167–177.CrossRefGoogle Scholar
  15. 15.
    Steyerberg EW, Harrell FE, Borsboom GJJM, Eijkemans MJC, Vergouwe Y, Habbema JDF. Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. J Clin Epidemiol. 2001;54(8):774–781.PubMedCrossRefGoogle Scholar
  16. 16.
    Delen D, Fuller C, McCann C, Ray D. Analysis of healthcare coverage: a data mining approach. Expert Syst Appl. 2009;36(2 PART 1):995–1003.CrossRefGoogle Scholar
  17. 17.
    James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning: with applications in R. New York: Springer; 2013.CrossRefGoogle Scholar
  18. 18.
    Frijters P, Johnston DW, Shields MA. The effect of mental health on employment: evidence from Australian panel data. Health Econ. 2014;23(9):1058–1071.PubMedCrossRefGoogle Scholar
  19. 19.
    Brijnath B, Mazza D, Singh N, Kosny A, Ruseckaite R, Collie A. Mental health claims management and return to work: Qualitative insights from Melbourne, Australia. J Occup Rehabil. 2014;24(4):766–776.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Computing and Information SystemsThe University of MelbourneMelbourneAustralia
  2. 2.Institute for Safety Compensation and Recovery ResearchMonash UniversityMelbourneAustralia
  3. 3.University Planning and StatisticsMonash UniversityMelbourneAustralia

Personalised recommendations