Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning
This work addresses the challenge of leveraging complex hierarchies in clinical notes for healthcare professionals, though it appears incremental as it builds on existing hypergraph methods.
The paper tackled the problem of underutilizing hierarchical information in clinical notes for patient condition prediction by proposing a multi-level hypergraph neural network, which achieved improved performance on in-hospital mortality prediction using the MIMIC-III dataset.
Leveraging knowledge from electronic health records (EHRs) to predict a patient's condition is essential to the effective delivery of appropriate care. Clinical notes of patient EHRs contain valuable information from healthcare professionals, but have been underused due to their difficult contents and complex hierarchies. Recently, hypergraph-based methods have been proposed for document classifications. Directly adopting existing hypergraph methods on clinical notes cannot sufficiently utilize the hierarchy information of the patient, which can degrade clinical semantic information by (1) frequent neutral words and (2) hierarchies with imbalanced distribution. Thus, we propose a taxonomy-aware multi-level hypergraph neural network (TM-HGNN), where multi-level hypergraphs assemble useful neutral words with rare keywords via note and taxonomy level hyperedges to retain the clinical semantic information. The constructed patient hypergraphs are fed into hierarchical message passing layers for learning more balanced multi-level knowledge at the note and taxonomy levels. We validate the effectiveness of TM-HGNN by conducting extensive experiments with MIMIC-III dataset on benchmark in-hospital-mortality prediction.