EUVIMEDEUVIMED entdecken
Crossref

Childhood academic experiences and employment outcomes in adults with disabilities or chronic health conditions: A machine-learning approach.

Bryan R Christ, Lucie Adams iD, Jack D Watson, Olivia Chapman, Madeline Lee, Beau LeBlond, Paul B Perrin iD

Rehabilitation Psychology · 2025

DOI: 10.1037/rep0000640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Rehabilitation Psychology, 2025. Verfasst von Bryan R Christ und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Data Science, University of Virginia. Hauptthemen laut MEDLINE: Employment, Persons with Disabilities, Machine Learning.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE/OBJECTIVE: Prior research highlights the complex interplay among disability, education, employment, and poverty, underscoring the importance of investigating how positive academic experiences among disabled individuals may predict employment status and poverty levels, potentially many years later. To address this gap, this study examined how educational factors including academic satisfaction, college degree attainment, and unmet academic accommodation needs predict employment and poverty among adults with disabilities or chronic health conditions. RESEARCH METHOD/DESIGN: A sample of 409 adults with disabilities or chronic health conditions while they had attended school in the United States completed an online survey of these constructs. Random forest models and their built-in measures of feature (or predictor) importance were used to predict the binary outcomes of employment status and poverty status using academic satisfaction, college degree attainment, and unmet academic accommodation needs as well as several common sociodemographic characteristics, including age, disability level, gender, rurality, and minority racial/ethnic identity. Across measures of feature importance, the academic factors showed comparable or greater predictive importance than all other sociodemographic predictors, and correlational analyses revealed that these academic factors were associated with higher levels of employment and lower levels of poverty. CONCLUSION/IMPLICATION: These findings suggest that positive educational experiences and accommodations are important predictors of both employment and poverty outcomes for individuals with disabilities. Future research should further explore how specific educational experiences impact employment outcomes for individuals with disabilities and examine supports and interventions that can create positive academic experiences. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmploymentPersons with DisabilitiesMachine LearningHumansFemaleAdultChronic DiseaseMaleMiddle AgedUnited StatesPovertyEducational StatusYoung Adult

Autor:innen und Institutionen

  • School of Data Science, University of Virginia.
  • Department of Psychology, University of Virginia.
  • Department of Psychology, Virginia Commonwealth University.

ORCID-Profile: Lucie Adams, Paul B Perrin

Zitieren

APA

Christ, B. R., Adams, L., Watson, J. D., Chapman, O., Lee, M., LeBlond, B., & Perrin, P. B. (2025). Childhood academic experiences and employment outcomes in adults with disabilities or chronic health conditions: A machine-learning approach. Rehabilitation Psychology. https://doi.org/10.1037/rep0000640

Vancouver

Christ BR, Adams L, Watson JD, Chapman O, Lee M, LeBlond B, et al. Childhood academic experiences and employment outcomes in adults with disabilities or chronic health conditions: A machine-learning approach. Rehabilitation Psychology. 2025. doi:10.1037/rep0000640

BibTeX
@article{Christ2025,
  author = {Christ, Bryan R and Adams, Lucie and Watson, Jack D and Chapman, Olivia and Lee, Madeline and LeBlond, Beau and Perrin, Paul B},
  title = {Childhood academic experiences and employment outcomes in adults with disabilities or chronic health conditions: A machine-learning approach},
  journal = {Rehabilitation Psychology},
  year = {2025},
  doi = {10.1037/rep0000640}
}
Kostenlos starten →