ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records
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, standardizatio...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/21/11250 |
_version_ | 1827647265657847808 |
---|---|
author | Sangjee Park Jun-Woo Bong Inseo Park Hwamin Lee Jiyoun Choi Pyoungjae Park Yoon Kim Hyun-Soo Choi Sanghee Kang |
author_facet | Sangjee Park Jun-Woo Bong Inseo Park Hwamin Lee Jiyoun Choi Pyoungjae Park Yoon Kim Hyun-Soo Choi Sanghee Kang |
author_sort | Sangjee Park |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-09T19:16:45Z |
format | Article |
id | doaj.art-074ffbcbe4f84f3fb711b5d9cac5191a |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T19:16:45Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-074ffbcbe4f84f3fb711b5d9cac5191a2023-11-24T03:40:31ZengMDPI AGApplied Sciences2076-34172022-11-0112211125010.3390/app122111250ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical RecordsSangjee Park0Jun-Woo Bong1Inseo Park2Hwamin Lee3Jiyoun Choi4Pyoungjae Park5Yoon Kim6Hyun-Soo Choi7Sanghee Kang8Department of Convergence Security, Kangwon National University, Chuncheon 24253, KoreaDepartment of Surgery, Korea University Guro Hospital, Korea University College of Medicine, Seoul 08308, KoreaDepartment of Convergence Security, Kangwon National University, Chuncheon 24253, KoreaDepartment of Medical Informatics, Korea University College of Medicine, Seoul 02841, KoreaKorea University Guro Hospital Medical Record Information Team, Seoul 08308, KoreaDepartment of Surgery, Korea University Guro Hospital, Korea University College of Medicine, Seoul 08308, KoreaDepartment of Computer Science, Engineering, Kangwon National University, Chuncheon 24253, KoreaDepartment of Computer Science, Engineering, Kangwon National University, Chuncheon 24253, KoreaDepartment of Surgery, Korea University Guro Hospital, Korea University College of Medicine, Seoul 08308, KoreaThis 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.https://www.mdpi.com/2076-3417/12/21/11250standardization of operative reportmedical code predictionConBERTICD-9 code |
spellingShingle | Sangjee Park Jun-Woo Bong Inseo Park Hwamin Lee Jiyoun Choi Pyoungjae Park Yoon Kim Hyun-Soo Choi Sanghee Kang ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records Applied Sciences standardization of operative report medical code prediction ConBERT ICD-9 code |
title | ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records |
title_full | ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records |
title_fullStr | ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records |
title_full_unstemmed | ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records |
title_short | ConBERT: A Concatenation of Bidirectional Transformers for Standardization of Operative Reports from Electronic Medical Records |
title_sort | conbert a concatenation of bidirectional transformers for standardization of operative reports from electronic medical records |
topic | standardization of operative report medical code prediction ConBERT ICD-9 code |
url | https://www.mdpi.com/2076-3417/12/21/11250 |
work_keys_str_mv | AT sangjeepark conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT junwoobong conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT inseopark conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT hwaminlee conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT jiyounchoi conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT pyoungjaepark conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT yoonkim conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT hyunsoochoi conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords AT sangheekang conbertaconcatenationofbidirectionaltransformersforstandardizationofoperativereportsfromelectronicmedicalrecords |