Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
This work addresses a critical problem in healthcare for clinicians and researchers dealing with incomplete multimodal data, though it appears incremental as it builds on existing Bayesian and multimodal learning methods.
The paper tackles the challenge of learning from multimodal and incomplete clinical data with limited samples by proposing a Bayesian approach that integrates generative and discriminative formulations, enabling automatic imputation of missing views and robust inference across data sources.
Real-world clinical problems are often characterized by multimodal data, usually associated with incomplete views and limited sample sizes in their cohorts, posing significant limitations for machine learning algorithms. In this work, we propose a Bayesian approach designed to efficiently handle these challenges while providing interpretable solutions. Our approach integrates (1) a generative formulation to capture cross-view relationships with a semi-supervised strategy, and (2) a discriminative task-oriented formulation to identify relevant information for specific downstream objectives. This dual generative-discriminative formulation offers both general understanding and task-specific insights; thus, it provides an automatic imputation of the missing views while enabling robust inference across different data sources. The potential of this approach becomes evident when applied to the multimodal clinical data, where our algorithm is able to capture and disentangle the complex interactions among biological, psychological, and sociodemographic modalities.