Handling Uncertainty in Health Data using Generative Algorithms
This addresses uncertainty and class imbalance in healthcare data, which is a high-stakes domain, but the approach appears incremental as it combines existing generative methods in a novel pipeline.
The paper tackles class imbalance in healthcare data by introducing RIGA, a pipeline that converts tabular data to images, uses generative models to generate balanced samples, and converts them back, resulting in improved classification performance and model robustness.
Understanding and managing uncertainty is crucial in machine learning, especially in high-stakes domains like healthcare, where class imbalance can impact predictions. This paper introduces RIGA, a novel pipeline that mitigates class imbalance using generative AI. By converting tabular healthcare data into images, RIGA leverages models like cGAN, VQVAE, and VQGAN to generate balanced samples, improving classification performance. These representations are processed by CNNs and later transformed back into tabular format for seamless integration. This approach enhances traditional classifiers like XGBoost, improves Bayesian structure learning, and strengthens ML model robustness by generating realistic synthetic data for underrepresented classes.