BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining
This addresses the time-consuming and expensive process of ICD coding for hospitals, though it is incremental as it builds on existing BERT methods.
The paper tackles the problem of automating ICD coding from electronic health records (EHR) notes, which is typically manual and costly, by proposing BERT-XML, a model that trains BERT from scratch on EHR data and achieves improved performance over off-the-shelf models.
Clinical interactions are initially recorded and documented in free text medical notes. ICD coding is the task of classifying and coding all diagnoses, symptoms and procedures associated with a patient's visit. The process is often manual and extremely time-consuming and expensive for hospitals. In this paper, we propose a machine learning model, BERT-XML, for large scale automated ICD coding from EHR notes, utilizing recently developed unsupervised pretraining that have achieved state of the art performance on a variety of NLP tasks. We train a BERT model from scratch on EHR notes, learning with vocabulary better suited for EHR tasks and thus outperform off-the-shelf models. We adapt the BERT architecture for ICD coding with multi-label attention. While other works focus on small public medical datasets, we have produced the first large scale ICD-10 classification model using millions of EHR notes to predict thousands of unique ICD codes.