An improved data augmentation approach and its application in medical named entity recognition

• Published in: BMC medical informatics and decision making Vol. 24; no. 1; pp. 221 - 13
• Main Authors: Chen, Hongyu, Dan, Li, Lu, Yonghe, Chen, Minghong, Zhang, Jinxia
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 05.08.2024; BioMed Central; BMC
• Subjects: Algorithms; Analysis; Annotations; Classification; Computational linguistics; Data augmentation; Data mining; Deep Learning; Electronic health records; Evaluation; Humans; Language; Language processing; Machine learning; Medical named entity recognition; Medical records; Methods; Natural language interfaces; Natural Language Processing; Neural networks; Recognition; Replacement augmentation; Semantics; Text categorization; Text features; Training; China; Deep learning; Data augmentation; Text features; Replacement augmentation; Medical named entity recognition
• DOI: 10.1186/s12911-024-02624-x
• ISSN: 1472-6947

Performing data augmentation in medical named entity recognition (NER) is crucial due to the unique challenges posed by this field. Medical data is characterized by high acquisition costs, specialized terminology, imbalanced distributions, and limited training resources. These factors make achieving high performance in medical NER particularly difficult. Data augmentation methods help to mitigate these issues by generating additional training samples, thus balancing data distribution, enriching the training dataset, and improving model generalization. This paper proposes two data augmentation methods-Contextual Random Replacement based on Word2Vec Augmentation (CRR) and Targeted Entity Random Replacement Augmentation (TER)-aimed at addressing the scarcity and imbalance of data in the medical domain. When combined with a deep learning-based Chinese NER model, these methods can significantly enhance performance and recognition accuracy under limited resources. Experimental results demonstrate that both augmentation methods effectively improve the recognition capability of medical named entities. Specifically, the BERT-BiLSTM-CRF model achieved the highest F1 score of 83.587%, representing a 1.49% increase over the baseline model. This validates the importance and effectiveness of data augmentation in medical NER.