Clinical Contradiction Detection

Dave Makhervaks, Plia Gillis, Kira Radinsky


Abstract
Detecting contradictions in text is essential in determining the validity of the literature and sources that we consume. Medical corpora are riddled with conflicting statements. This is due to the large throughput of new studies and the difficulty in replicating experiments, such as clinical trials. Detecting contradictions in this domain is hard since it requires clinical expertise. We present a distant supervision approach that leverages a medical ontology to build a seed of potential clinical contradictions over 22 million medical abstracts. We automatically build a labeled training dataset consisting of paired clinical sentences that are grounded in an ontology and represent potential medical contradiction. The dataset is used to weakly-supervise state-of-the-art deep learning models showing significant empirical improvements across multiple medical contradiction datasets.
Anthology ID:
2023.emnlp-main.80
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1248–1263
Language:
URL:
https://aclanthology.org/2023.emnlp-main.80
DOI:
10.18653/v1/2023.emnlp-main.80
Bibkey:
Cite (ACL):
Dave Makhervaks, Plia Gillis, and Kira Radinsky. 2023. Clinical Contradiction Detection. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1248–1263, Singapore. Association for Computational Linguistics.
Cite (Informal):
Clinical Contradiction Detection (Makhervaks et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.80.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.80.mp4