Investigation of bias in the automated assessment of school violence.

Journal: Journal of biomedical informatics
PMID: 39153563

Abstract

OBJECTIVES: Natural language processing and machine learning have the potential to lead to biased predictions. We designed a novel Automated RIsk Assessment (ARIA) machine learning algorithm that assesses risk of violence and aggression in adolescents using natural language processing of transcribed student interviews. This work evaluated the possible sources of bias in the study design and the algorithm, tested how much of a prediction was explained by demographic covariates, and investigated the misclassifications based on demographic variables.

Authors

  • Lara J Kanbar
    Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. Electronic address: lara.kanbar@cchmc.org.
  • Anagh Mishra
    Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
  • Alexander Osborn
    Division of Child and Adolescent Psychiatry, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States.
  • Andrew Cifuentes
    Division of Child and Adolescent Psychiatry, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
  • Jennifer Combs
    Division of Child and Adolescent Psychiatry, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA.
  • Michael Sorter
    Division of Psychiatry, Cincinnati Children's Hospital Medical Center, University of Cincinnati, Cincinnati, OH, USA.
  • Drew Barzman
    Cincinnati Children's Hospital Medical Center (CCHMC), Cincinnati, USA. drew.barzman@cchmc.org.
  • Judith W Dexheimer
    Department of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA Division of Pediatric Emergency Medicine, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.

Keywords

External Resources

Popular Topics
Recent Journals