Chinese-Named Entity Recognition From Adverse Drug Event Records: Radical Embedding-Combined Dynamic Embedding-Based BERT in a Bidirectional Long Short-term Conditional Random Field (Bi-LSTM-CRF) Model

Hong Wu; Jiatong Ji; Haimei Tian; Yao Chen; Weihong Ge; Haixia Zhang; Feng Yu; Jianjun Zou; Mitsuhiro Nakamura; Jun Liao

doi:10.2196/26407

Chinese-Named Entity Recognition From Adverse Drug Event Records: Radical Embedding-Combined Dynamic Embedding-Based BERT in a Bidirectional Long Short-term Conditional Random Field (Bi-LSTM-CRF) Model

JMIR Med Inform. 2021 Dec 1;9(12):e26407. doi: 10.2196/26407.

Authors

Hong Wu¹, Jiatong Ji², Haimei Tian³, Yao Chen¹, Weihong Ge⁴, Haixia Zhang⁴, Feng Yu², Jianjun Zou⁵, Mitsuhiro Nakamura⁶, Jun Liao¹

Affiliations

¹ School of Science, China Pharmaceutical University, Nanjing, China.
² School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China.
³ School of Computer Engineering, Jinling Institute of Technology, Nanjing, China.
⁴ Department of Pharmacy, Nanjing Drum Tower Hospital, Nanjing, China.
⁵ Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China.
⁶ Laboratory of Drug Informatics, Gifu Pharmaceutical University, Gifu, Japan.

PMID: 34855616
PMCID: PMC8686410
DOI: 10.2196/26407

Abstract

Background: With the increasing variety of drugs, the incidence of adverse drug events (ADEs) is increasing year by year. Massive numbers of ADEs are recorded in electronic medical records and adverse drug reaction (ADR) reports, which are important sources of potential ADR information. Meanwhile, it is essential to make latent ADR information automatically available for better postmarketing drug safety reevaluation and pharmacovigilance.

Objective: This study describes how to identify ADR-related information from Chinese ADE reports.

Methods: Our study established an efficient automated tool, named BBC-Radical. BBC-Radical is a model that consists of 3 components: Bidirectional Encoder Representations from Transformers (BERT), bidirectional long short-term memory (bi-LSTM), and conditional random field (CRF). The model identifies ADR-related information from Chinese ADR reports. Token features and radical features of Chinese characters were used to represent the common meaning of a group of words. BERT and Bi-LSTM-CRF were novel models that combined these features to conduct named entity recognition (NER) tasks in the free-text section of 24,890 ADR reports from the Jiangsu Province Adverse Drug Reaction Monitoring Center from 2010 to 2016. Moreover, the man-machine comparison experiment on the ADE records from Drum Tower Hospital was designed to compare the NER performance between the BBC-Radical model and a manual method.

Results: The NER model achieved relatively high performance, with a precision of 96.4%, recall of 96.0%, and F1 score of 96.2%. This indicates that the performance of the BBC-Radical model (precision 87.2%, recall 85.7%, and F1 score 86.4%) is much better than that of the manual method (precision 86.1%, recall 73.8%, and F1 score 79.5%) in the recognition task of each kind of entity.

Conclusions: The proposed model was competitive in extracting ADR-related information from ADE reports, and the results suggest that the application of our method to extract ADR-related information is of great significance in improving the quality of ADR reports and postmarketing drug safety evaluation.

Keywords: BERT; adverse drug reaction; deep learning; electronic medical records; named entity recognition.

©Hong Wu, Jiatong Ji, Haimei Tian, Yao Chen, Weihong Ge, Haixia Zhang, Feng Yu, Jianjun Zou, Mitsuhiro Nakamura, Jun Liao. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 01.12.2021.