Fairness-Aware Interpretable Modeling (FAIM) for Trustworthy Machine Learning in Healthcare

arXiv:2403.05235v1 Announce Type: new
Abstract: The escalating integration of machine learning in high-stakes fields such as healthcare raises substantial concerns about model fairness. We propose an interpretable framework - Fairness-Aware Interpretable Modeling (FAIM), to improve model fairness without compromising performance, featuring an interactive interface to identify a "fairer" model from a set of high-performing models and promoting the integration of data-driven evidence and clinical expertise to enhance contextualized fairness. We demonstrated FAIM's value in reducing sex and race biases by …

abstract arxiv concerns cs.ai cs.cy cs.lg fairness fields framework healthcare identify integration interactive machine machine learning modeling performance raises trustworthy type