Data augmentation to improve syndromic detection from emergency department notes
Open Access
- 30 January 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 198-205
Abstract
Using natural language processing algorithms requires a large amount of annotated data, which is difficult to obtain in clinical settings. In this work we aimed to develop and evaluate data augmentation methods to enhance the performance of classification tasks implemented in a medical domain. Three text augmentation methods were evaluated for generating febrile convulsion-like emergency department (ED) presentations. These were synthetic text generation, domain-specific data augmentation, and task-agnostic data augmentation techniques. We used a transformer-based classifier, first establishing a baseline by training with non-augmented data, then training on each set of augmented data to compare the results with the baseline. The synthetic text generation augmentation method was clearly superior, with the f-score improving by 12% compared with the baseline. The domain-specific approach improved the score by 6%, while the task-agnostic augmentation method failed to enhance classification performance. Our study shows that data augmentation methods can be used for generating artificial ED data to enhance classification of critical syndromes, thereby assisting syndromic surveillance to contribute to improving public health.Keywords
This publication has 10 references indexed in Scilit:
- Are synthetic clinical notes useful for real natural language processing tasks: A case study on clinical entity recognitionJournal of the American Medical Informatics Association, 2021
- Natural Language Generation Model for Mammography Reports SimulationIEEE Journal of Biomedical and Health Informatics, 2020
- Clinical Text Data in Machine Learning: Systematic ReviewJMIR Medical Informatics, 2020
- Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art2020
- A survey on Image Data Augmentation for Deep LearningJournal of Big Data, 2019
- Synthesizing electronic health records using improved generative adversarial networksJournal of the American Medical Informatics Association, 2018
- Generative Adversarial Networks: An OverviewIEEE Signal Processing Magazine, 2018
- Enriching Word Vectors with Subword InformationTransactions of the Association for Computational Linguistics, 2017
- Using chief complaints for syndromic surveillance: A review of chief complaint based classifiers in North AmericaJournal of Biomedical Informatics, 2013
- Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutionsJournal of the American Medical Informatics Association, 2011