Towards BERT-based Automatic ICD Coding: Limitations and Opportunities

Damian Pascual, Sandro Luck, Roger Wattenhofer


Abstract
Automatic ICD coding is the task of assigning codes from the International Classification of Diseases (ICD) to medical notes. These codes describe the state of the patient and have multiple applications, e.g., computer-assisted diagnosis or epidemiological studies. ICD coding is a challenging task due to the complexity and length of medical notes. Unlike the general trend in language processing, no transformer model has been reported to reach high performance on this task. Here, we investigate in detail ICD coding using PubMedBERT, a state-of-the-art transformer model for biomedical language understanding. We find that the difficulty of fine-tuning the model on long pieces of text is the main limitation for BERT-based models on ICD coding. We run extensive experiments and show that despite the gap with current state-of-the-art, pretrained transformers can reach competitive performance using relatively small portions of text. We point at better methods to aggregate information from long texts as the main need for improving BERT-based ICD coding.
Anthology ID:
2021.bionlp-1.6
Volume:
Proceedings of the 20th Workshop on Biomedical Language Processing
Month:
June
Year:
2021
Address:
Online
Venues:
BioNLP | NAACL
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
54–63
Language:
URL:
https://aclanthology.org/2021.bionlp-1.6
DOI:
10.18653/v1/2021.bionlp-1.6
Bibkey:
Cite (ACL):
Damian Pascual, Sandro Luck, and Roger Wattenhofer. 2021. Towards BERT-based Automatic ICD Coding: Limitations and Opportunities. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 54–63, Online. Association for Computational Linguistics.
Cite (Informal):
Towards BERT-based Automatic ICD Coding: Limitations and Opportunities (Pascual et al., BioNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bionlp-1.6.pdf