UMLS-based data augmentation for natural language processing of clinical research literature. (23rd December 2020)

• Record Type: Journal Article
• Authors: Kang, Tian; Perotte, Adler; Tang, Youlan; Ta, Casey; Weng, Chunhua
• Is Part Of: Journal of the American Medical Informatics Association. Volume 28:Number 4(2021)
• Page Start: 812
• Page End: 823
• Publication Date: 2020-12-23
• Subjects: Unified Medical Language System -- UMLS -- natural language processing -- NLP -- machine learning -- evidence based medicine -- named entity recognition -- data augmentation; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocaa309
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective: The study sought to develop and evaluate a knowledge-based data augmentation method to improve the performance of deep learning models for biomedical natural language processing by overcoming training data scarcity. Materials and Methods: We extended the easy data augmentation (EDA) method for biomedical named entity recognition (NER) by incorporating the Unified Medical Language System (UMLS) knowledge and called this method UMLS-EDA. We designed experiments to systematically evaluate the effect of UMLS-EDA on popular deep learning architectures for both NER and classification. We also compared UMLS-EDA to BERT. Results: UMLS-EDA enables substantial improvement for NER tasks from the original long short-term memory conditional random fields (LSTM-CRF) model (micro-F1 score: +5%, + 17%, and +15%), helps the LSTM-CRF model (micro-F1 score: 0.66) outperform LSTM-CRF with transfer learning by BERT (0.63), and improves the performance of the state-of-the-art sentence classification model. The largest gain on micro-F1 score is 9%, from 0.75 to 0.84, better than classifiers with BERT pretraining (0.82). Conclusions: This study presents a UMLS-based data augmentation method, UMLS-EDA. It is effective at improving deep learning models for both NER and sentence classification, and contributes original insights for designing new, superior deep learning approaches for low-resource biomedical domains.