Graph Inference Towards ICD Coding
By: Xiaoxiao Deng
Potential Business Impact:
Helps doctors quickly give correct patient codes.
Automated ICD coding involves assigning standardized diagnostic codes to clinical narratives. The vast label space and extreme class imbalance continue to challenge precise prediction. To address these issues, LabGraph is introduced -- a unified framework that reformulates ICD coding as a graph generation task. By combining adversarial domain adaptation, graph-based reinforcement learning, and perturbation regularization, LabGraph effectively enhances model robustness and generalization. In addition, a label graph discriminator dynamically evaluates each generated code, providing adaptive reward feedback during training. Experiments on benchmark datasets demonstrate that LabGraph consistently outperforms previous approaches on micro-F1, micro-AUC, and P@K.
Similar Papers
LTR-ICD: A Learning-to-Rank Approach for Automatic ICD Coding
Machine Learning (CS)
Helps doctors sort patient sickness codes faster.
Structured Information Matters: Explainable ICD Coding with Patient-Level Knowledge Graphs
Computation and Language
Helps doctors quickly organize patient notes.
Evaluation and LLM-Guided Learning of ICD Coding Rationales
Artificial Intelligence
Helps doctors understand patient records better.