Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks

Lena Schmidt, Lena Schmidt, Julie Weeds, Julian P. T. Higgins

2020

Abstract

This research on data extraction methods applies recent advances in natural language processing to evidence synthesis based on medical texts. Texts of interest include abstracts of clinical trials in English and in multilingual contexts. The main focus is on information characterized via the Population, Intervention, Comparator, and Outcome (PICO) framework, but data extraction is not limited to these fields. Recent neural network architectures based on transformers show capacities for transfer learning and increased performance on downstream natural language processing tasks such as universal reading comprehension, brought forward by this architecture’s use of contextualized word embeddings and self-attention mechanisms. This paper contributes to solving problems related to ambiguity in PICO sentence prediction tasks, as well as highlighting how annotations for training named entity recognition systems are used to train a high-performing, but nevertheless flexible architecture for question answering in systematic review automation. Additionally, it demonstrates how the problem of insufficient amounts of training annotations for PICO entity extraction is tackled by augmentation. All models in this paper were created with the aim to support systematic review (semi)automation. They achieve high F1 scores, and demonstrate the feasibility of applying transformer-based classification methods to support data mining in the biomedical literature.

Paper Citation

in Harvard Style

Schmidt L., Weeds J. and Higgins J. (2020). Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks. In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 5: HEALTHINF; ISBN 978-989-758-398-8, SciTePress, pages 83-94. DOI: 10.5220/0008945700830094

in Bibtex Style

@conference{healthinf20,
author={Lena Schmidt and Julie Weeds and Julian P. T. Higgins},
title={Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 5: HEALTHINF},
year={2020},
pages={83-94},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008945700830094},
isbn={978-989-758-398-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 5: HEALTHINF
TI - Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks
SN - 978-989-758-398-8
AU - Schmidt L.
AU - Weeds J.
AU - Higgins J.
PY - 2020
SP - 83
EP - 94
DO - 10.5220/0008945700830094
PB - SciTePress