Cargando…
Knowledge-based extraction of adverse drug events from biomedical text
BACKGROUND: Many biomedical relation extraction systems are machine-learning based and have to be trained on large annotated corpora that are expensive and cumbersome to construct. We developed a knowledge-based relation extraction system that requires minimal training data, and applied the system f...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3973995/ https://www.ncbi.nlm.nih.gov/pubmed/24593054 http://dx.doi.org/10.1186/1471-2105-15-64 |
_version_ | 1782479408410394624 |
---|---|
author | Kang, Ning Singh, Bharat Bui, Chinh Afzal, Zubair van Mulligen, Erik M Kors, Jan A |
author_facet | Kang, Ning Singh, Bharat Bui, Chinh Afzal, Zubair van Mulligen, Erik M Kors, Jan A |
author_sort | Kang, Ning |
collection | PubMed |
description | BACKGROUND: Many biomedical relation extraction systems are machine-learning based and have to be trained on large annotated corpora that are expensive and cumbersome to construct. We developed a knowledge-based relation extraction system that requires minimal training data, and applied the system for the extraction of adverse drug events from biomedical text. The system consists of a concept recognition module that identifies drugs and adverse effects in sentences, and a knowledge-base module that establishes whether a relation exists between the recognized concepts. The knowledge base was filled with information from the Unified Medical Language System. The performance of the system was evaluated on the ADE corpus, consisting of 1644 abstracts with manually annotated adverse drug events. Fifty abstracts were used for training, the remaining abstracts were used for testing. RESULTS: The knowledge-based system obtained an F-score of 50.5%, which was 34.4 percentage points better than the co-occurrence baseline. Increasing the training set to 400 abstracts improved the F-score to 54.3%. When the system was compared with a machine-learning system, jSRE, on a subset of the sentences in the ADE corpus, our knowledge-based system achieved an F-score that is 7 percentage points higher than the F-score of jSRE trained on 50 abstracts, and still 2 percentage points higher than jSRE trained on 90% of the corpus. CONCLUSION: A knowledge-based approach can be successfully used to extract adverse drug events from biomedical text without need for a large training set. Whether use of a knowledge base is equally advantageous for other biomedical relation-extraction tasks remains to be investigated. |
format | Online Article Text |
id | pubmed-3973995 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2014 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-39739952014-04-04 Knowledge-based extraction of adverse drug events from biomedical text Kang, Ning Singh, Bharat Bui, Chinh Afzal, Zubair van Mulligen, Erik M Kors, Jan A BMC Bioinformatics Research Article BACKGROUND: Many biomedical relation extraction systems are machine-learning based and have to be trained on large annotated corpora that are expensive and cumbersome to construct. We developed a knowledge-based relation extraction system that requires minimal training data, and applied the system for the extraction of adverse drug events from biomedical text. The system consists of a concept recognition module that identifies drugs and adverse effects in sentences, and a knowledge-base module that establishes whether a relation exists between the recognized concepts. The knowledge base was filled with information from the Unified Medical Language System. The performance of the system was evaluated on the ADE corpus, consisting of 1644 abstracts with manually annotated adverse drug events. Fifty abstracts were used for training, the remaining abstracts were used for testing. RESULTS: The knowledge-based system obtained an F-score of 50.5%, which was 34.4 percentage points better than the co-occurrence baseline. Increasing the training set to 400 abstracts improved the F-score to 54.3%. When the system was compared with a machine-learning system, jSRE, on a subset of the sentences in the ADE corpus, our knowledge-based system achieved an F-score that is 7 percentage points higher than the F-score of jSRE trained on 50 abstracts, and still 2 percentage points higher than jSRE trained on 90% of the corpus. CONCLUSION: A knowledge-based approach can be successfully used to extract adverse drug events from biomedical text without need for a large training set. Whether use of a knowledge base is equally advantageous for other biomedical relation-extraction tasks remains to be investigated. BioMed Central 2014-03-04 /pmc/articles/PMC3973995/ /pubmed/24593054 http://dx.doi.org/10.1186/1471-2105-15-64 Text en Copyright © 2014 Kang et al.; licensee BioMed Central Ltd. http://creativecommons.org/licenses/by/2.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. |
spellingShingle | Research Article Kang, Ning Singh, Bharat Bui, Chinh Afzal, Zubair van Mulligen, Erik M Kors, Jan A Knowledge-based extraction of adverse drug events from biomedical text |
title | Knowledge-based extraction of adverse drug events from biomedical text |
title_full | Knowledge-based extraction of adverse drug events from biomedical text |
title_fullStr | Knowledge-based extraction of adverse drug events from biomedical text |
title_full_unstemmed | Knowledge-based extraction of adverse drug events from biomedical text |
title_short | Knowledge-based extraction of adverse drug events from biomedical text |
title_sort | knowledge-based extraction of adverse drug events from biomedical text |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3973995/ https://www.ncbi.nlm.nih.gov/pubmed/24593054 http://dx.doi.org/10.1186/1471-2105-15-64 |
work_keys_str_mv | AT kangning knowledgebasedextractionofadversedrugeventsfrombiomedicaltext AT singhbharat knowledgebasedextractionofadversedrugeventsfrombiomedicaltext AT buichinh knowledgebasedextractionofadversedrugeventsfrombiomedicaltext AT afzalzubair knowledgebasedextractionofadversedrugeventsfrombiomedicaltext AT vanmulligenerikm knowledgebasedextractionofadversedrugeventsfrombiomedicaltext AT korsjana knowledgebasedextractionofadversedrugeventsfrombiomedicaltext |