Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention
TL
TL;DR
A model based on bidirectional encoder representations from transformers (BERT) using the sequence attention method for automatic ICD code assignment and is performing better than a performance of the state-of-the-art model using the MIMIC-III dataset.
Abstract
Clinical notes are unstructured text generated by clinicians during patient encounters. Clinical notes are usually accompanied by a set of metadata codes from the international classification of diseases (ICD). ICD code is an important code used in various operations, including insurance, reimbursement, medical diagnosis, etc. Therefore, it is important to classify ICD codes quickly and accurately. However, annotating these codes is costly and time-consuming. So we propose a model based on bidirectional encoder representations from transformers (BERT) using the sequence attention method for automatic ICD code assignment. We evaluate our approach on the medical information mart for intensive care III (MIMIC-III) benchmark dataset. Our model achieved performance of macro-averaged F1: 0.62898 and micro-averaged F1: 0.68555 and is performing better than a performance of the state-of-the-art model using the MIMIC-III dataset. The contribution of this study proposes a method of using BERT that can be applied to documents and a sequence attention method that can capture important sequence information appearing in documents.
References19 items
1
Prediction of Atrial Fibrillation Cases: Convolutional Neural Networks Using the Output Texts of Electrocardiography
2
An explainable CNN approach for medical codes prediction from clinical text
3
Various Approaches for Predicting Stroke Prognosis using Magnetic Resonance Imaging Text Records
4
Longformer: The Long-Document Transformer
5