Corpus ID: 226282395

FairLens: Auditing Black-box Clinical Decision Support Systems

@article{Panigutti2020FairLensAB,
  title={FairLens: Auditing Black-box Clinical Decision Support Systems},
  author={Cecilia Panigutti and A. Perotti and A. Panisson and P. Bajardi and D. Pedreschi},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.04049}
}
The pervasive application of algorithmic decision-making is raising concerns on the risk of unintended bias in AI systems deployed in critical settings such as healthcare. The detection and mitigation of biased models is a very delicate task which should be tackled with care and involving domain experts in the loop. In this paper we introduce FairLens, a methodology for discovering and explaining biases. We show how our tool can be used to audit a fictional commercial black-box model acting as… Expand
1 Citations

Figures and Tables from this paper

References

SHOWING 1-10 OF 59 REFERENCES
Aequitas: A Bias and Fairness Audit Toolkit
  • 51
  • PDF
Can AI Help Reduce Disparities in General Medical and Mental Health Care?
  • 54
  • PDF
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
  • 75
  • PDF
...
1
2
3
4
5
...