Benchmarking the most popular XAI used for explaining clinical predictive models: Untrustworthy but could be useful.

Journal: Health informatics journal
PMID: 39716973

Abstract

OBJECTIVE: This study aimed to assess the practicality and trustworthiness of explainable artificial intelligence (XAI) methods used for explaining clinical predictive models.

Authors

  • Aida Brankovic
    CSIRO Australian e-Health Research Centre, Brisbane, QLD, 4029, Australia. aida.brankovic@csiro.au.
  • David Cook
    Key Family of Companies Indianapolis, Indiana.
  • Jessica Rahman
    CSIRO Australian e-Health Research Centre, Australia. Electronic address: jessica.rahman@csiro.au.
  • Sankalp Khanna
    CSIRO Australian e-Health Research Centre, Brisbane, QLD, 4029, Australia.
  • Wenjie Huang
    The University of Queensland, Brisbane, QLD, Australia.

Keywords

External Resources

Popular Topics
Recent Journals