MCRAGE: Synthetic Healthcare Data for Fairness

arXiv:2310.18430v2 Announce Type: replace-cross
Abstract: In the field of healthcare, electronic health records (EHR) serve as crucial training data for developing machine learning models for diagnosis, treatment, and the management of healthcare resources. However, medical datasets are often imbalanced in terms of sensitive attributes such as race/ethnicity, gender, and age. Machine learning models trained on class-imbalanced EHR datasets perform significantly worse in deployment for individuals of the minority classes compared to samples from majority classes, which may lead to inequitable …

abstract age arxiv cs.lg data datasets diagnosis ehr electronic electronic health records fairness gender health healthcare healthcare data however machine machine learning machine learning models management medical race records resources serve stat.ml synthetic terms training training data treatment type