MCRAGE: Synthetic Healthcare Data for Fairness
This addresses fairness issues in healthcare AI for minority populations, but it is incremental as it builds on existing generative modeling techniques.
The paper tackles the problem of class imbalance in electronic health records (EHR) datasets, which leads to biased machine learning models and inequitable healthcare outcomes for minority groups, by proposing MCRAGE, a method that uses a conditional denoising diffusion probabilistic model to generate synthetic data for underrepresented classes, resulting in improved model performance as measured by metrics like Accuracy, F1 score, and AUROC.
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 those from majority classes, which may lead to inequitable healthcare outcomes for minority groups. To address this challenge, we propose Minority Class Rebalancing through Augmentation by Generative modeling (MCRAGE), a novel approach to augment imbalanced datasets using samples generated by a deep generative model. The MCRAGE process involves training a Conditional Denoising Diffusion Probabilistic Model (CDDPM) capable of generating high-quality synthetic EHR samples from underrepresented classes. We use this synthetic data to augment the existing imbalanced dataset, resulting in a more balanced distribution across all classes, which can be used to train less biased downstream models. We measure the performance of MCRAGE versus alternative approaches using Accuracy, F1 score and AUROC of these downstream models. We provide theoretical justification for our method in terms of recent convergence results for DDPMs.