A Machine Learning Model of Vocational Rehabilitation Employment Outcomes for Veterans with Psychiatric and/or Substance Use Disorders

Matthew E. Sprong et al.

Rehabilitation Counseling Bulletin2026https://doi.org/10.1177/00343552261416859article
AJG 1
Weight
0.50

What the paper says

Employment has been linked to improved outcomes for individuals with substance use disorders (SUDs) and/or psychiatric disabilities, including successful treatment completion, higher recovery rates, and better quality of life. This study aims to explore employment outcomes for veterans with SUDs and/or schizophrenia and other psychotic disorders enrolled in state-federal vocational rehabilitation programs. The Rehabilitation Services Administration Case Service Report secondary dataset (program years 2020–2022) was used. A machine learning approach was applied using a Least Absolute Shrinkage and Selection Operator (LASSO) regression model. Forty-seven potential covariates were entered into the model, and variable selection was determined automatically by the algorithm through a stepwise regression process, rather than manually choosing which variables to include (avoiding selection bias). The final model identified 23 potential predictors and was refined through multivariable logistic regression to eight significant variables. Veterans ( n =2,957) were significantly more likely to be employed if they received the short-term job support service (OR = 7.24, p <.01), supported employment services (OR = 5.06, p <.01), maintenance services (OR = 7.81, p <.01), and measurable skill gains-skills progression (OR = 5.39, p <.01) compared to those who did not receive the services. Employment was also linked to the source of disability. Veterans with ADHD were more likely to find employment, with an odds ratio of 2.15 ( p = .03). In contrast, veterans diagnosed with Schizophrenia and other psychotic disabilities (co-occurring with SUDs) were less likely to be employed, with an OR of 0.70 ( p < .01). Findings underscore the effectiveness of specific, evidence-based vocational rehabilitation services, such as short-term job supports, supported employment, maintenance services, and skill development, for veterans with SUDs and/or psychiatric disabilities. These results emphasize the importance of targeted service delivery within state-federal vocational rehabilitation programs and highlight the need for additional research to refine and tailor existing services to better support veterans pursuing employment or new career paths.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1177/00343552261416859

Or copy a formatted citation

@article{matthew2026,
  title        = {{A Machine Learning Model of Vocational Rehabilitation Employment Outcomes for Veterans with Psychiatric and/or Substance Use Disorders}},
  author       = {Matthew E. Sprong et al.},
  journal      = {Rehabilitation Counseling Bulletin},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1177/00343552261416859},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

A Machine Learning Model of Vocational Rehabilitation Employment Outcomes for Veterans with Psychiatric and/or Substance Use Disorders

Flags are reviewed by the Arbiter methodology team within 5 business days.


Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.