Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Recordsopen access

Authors
Park, SangjeeBong, Jun-WooPark, InseoLee, HwaminChoi, JiyounPark, PyoungjaeKim, YoonChoi, Hyun-SooKang, Sanghee
Issue Date
Nov-2022
Publisher
MDPI
Keywords
standardization of operative report; medical code prediction; ConBERT; ICD-9 code
Citation
Applied Sciences-basel, v.12, no.21
Indexed
SCIE
SCOPUS
Journal Title
Applied Sciences-basel
Volume
12
Number
21
URI
https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/61859
DOI
10.3390/app122111250
ISSN
2076-3417
2076-3417
Abstract
This operative report documents the details of a surgery. Standardization of the medical terminology for the operative report written in free text is significant for performing medical research and establishing insurance systems by accurately sharing information on treatment. However, standardization of operative reports is a labor-intensive task that has a risk of induced errors. We have proposed a concatenation of bidirectional encoder representations from transformers (ConBERT) model for predicting the International Classification of Disease-9 code using the operative report and diagnosis recorded in free text to standardize the operative report automatically. We compared the pre-trained models of BERT and character BERT and created a new model by concatenating the combinations of each model. The proposed ConBERT model showed a micro AP score of 0.7672, F1 score of 0.7415, and AUC of 0.9842. In addition, we developed a web-based application to demonstrate the performance of our model and make it publicly accessible.
Files in This Item
There are no files associated with this item.
Appears in
Collections
2. Clinical Science > Department of Transplantation and Vascular Surgery > 1. Journal Articles
1. Basic Science > Department of Medical Informatics > 1. Journal Articles
2. Clinical Science > Department of Colon and Rectal Surgery > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Park, Pyoung Jae photo

Park, Pyoung Jae
Guro Hospital (Department of Transplantation and Vascular Surgery, Guro Hospital)
Read more

Altmetrics

Total Views & Downloads

BROWSE