ACE-ICD: Acronym Expansion As Data Augmentation For Automated ICD Coding
This work addresses the challenge of accurate ICD coding for clinical documentation and billing by improving model handling of medical acronyms, representing an incremental advancement over existing methods.
The paper tackles the problem of automated ICD coding by addressing the overlooked issue of medical acronyms in clinical notes, proposing a data augmentation technique using large language models to expand acronyms and incorporating consistency training, which achieves new state-of-the-art performance on the MIMIC-III dataset across various code settings.
Automatic ICD coding, the task of assigning disease and procedure codes to electronic medical records, is crucial for clinical documentation and billing. While existing methods primarily enhance model understanding of code hierarchies and synonyms, they often overlook the pervasive use of medical acronyms in clinical notes, a key factor in ICD code inference. To address this gap, we propose a novel effective data augmentation technique that leverages large language models to expand medical acronyms, allowing models to be trained on their full form representations. Moreover, we incorporate consistency training to regularize predictions by enforcing agreement between the original and augmented documents. Extensive experiments on the MIMIC-III dataset demonstrate that our approach, ACE-ICD establishes new state-of-the-art performance across multiple settings, including common codes, rare codes, and full-code assignments. Our code is publicly available.