Transformer models have achieved great success across many NLP problems. However, previous studies in automated ICD coding concluded that these models fail to outperform some of the earlier solutions such as CNN-based models. In this paper we challenge this conclusion. We present a simple and scalable method to process long text with the existing transformer models such as BERT. We show that this method significantly improves the previous results reported for transformer models in ICD coding, and is able to outperform one of the prominent CNN-based methods.
@article{arxiv.2211.02519,
title = {BERT for Long Documents: A Case Study of Automated ICD Coding},
author = {Arash Afkanpour and Shabir Adeel and Hansenclever Bassani and Arkady Epshteyn and Hongbo Fan and Isaac Jones and Mahan Malihi and Adrian Nauth and Raj Sinha and Sanjana Woonna and Shiva Zamani and Elli Kanal and Mikhail Fomitchev and Donny Cheung},
journal= {arXiv preprint arXiv:2211.02519},
year = {2022}
}