Description-based Label Attention Classifier for Explainable ICD-9 Classification
This work addresses the need for more interpretable models in clinical billing tasks, though it appears incremental as it builds on existing transformer-based encoders.
The authors tackled the problem of automated ICD-9 coding from noisy clinical texts by proposing a description-based label attention classifier to improve explainability, achieving strong results on the MIMIC-III-50 dataset.
ICD-9 coding is a relevant clinical billing task, where unstructured texts with information about a patient's diagnosis and treatments are annotated with multiple ICD-9 codes. Automated ICD-9 coding is an active research field, where CNN- and RNN-based model architectures represent the state-of-the-art approaches. In this work, we propose a description-based label attention classifier to improve the model explainability when dealing with noisy texts like clinical notes. We evaluate our proposed method with different transformer-based encoders on the MIMIC-III-50 dataset. Our method achieves strong results together with augmented explainablilty.