Mitigating Feature Homogenization in Deep Graph Architectures for Clinical Data Representation

This research redefines International Classification of Diseases (ICD) coding as a sophisticated multi-label prediction problem, requiring the assignment of multiple codes to detailed discharge summaries. Current automated ICD coding techniques face challenges in effectively classifying medical diagnostic texts that involve complex and sparse label distributions, especially when model parameters are adjusted using traditional backpropagation methods. We present LGG-NRGrand, a novel adversarial framework that approaches ICD coding through the generation of labeled graphs. A significant challenge in this field is the widespread issue of Over-Smoothing in deep graph neural networks, which results in uniform or indistinct node representations. Our model is designed to improve the capacity for learning heterogeneous graph representations within a layered network architecture. Specifically, we introduce NRGrand, a single-relational deep graph neural network structure that mitigates the Over-Smoothing problem while capturing more detailed graph features during the representation learning phase. The LGG-NRGrand model is trained using an adversarial reinforcement framework, employing an adversarial domain adaptation technique. Experimental results indicate that LGG-NRGrand surpasses current methods on key evaluation metrics, including micro-F1, micro-AUC, and P@K.