Handling Uncertainty in Health Data using Generative Algorithms

Download PDF

Mahdi Arab Loodaricheh, Neh Majmudar, Anita Raja, Ansaf Salleb-Aouissi

Published: 07 Mar 2025, Last Modified: 25 Mar 2025GenAI4Health PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Uncertainty, Class Imbalance, Data augmentation, Deep Learning, Tabular-to-Image transformation, Bayesian Network, Robustness
Abstract: 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.
Submission Number: 52