loading
Documents

Research.Publish.Connect.

Paper

Authors: Susmitha Wunnava 1 ; Xiao Qin 1 ; Tabassum Kakar 1 ; Xiangnan Kong 1 ; Elke A. Rundensteiner 1 ; Sanjay K. Sahoo 2 and Suranjan De 2

Affiliations: 1 Worcester Polytechnic Institute, United States ; 2 U.S. Food and Drug Administration, United States

ISBN: 978-989-758-281-3

Keyword(s): Pharmacovigilance, Adverse Drug Reaction, Class Imbalance, Ensemble Learning.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Biomedical Engineering ; Data Mining ; Databases and Information Systems Integration ; Enterprise Information Systems ; Health Information Systems ; Pattern Recognition and Machine Learning ; Sensor Networks ; Signal Processing ; Soft Computing

Abstract: Recognizing named entities in Adverse Drug Reactions narratives is a fundamental step towards extracting valuable patient information from unstructured text into a structured thus actionable format. This then unlocks advanced data analytics towards intelligent pharmacovigilance. Yet existing biomedical named entity recognition (NER) tools are limited in their ability to identify certain entity types from these domain-specific narratives and result in significant performance differences in terms of accuracy. To address these challenges, we propose an ensemble approach that integrates a rich variety of named entity recognizers to procure the final result. First, one critical problem faced by NER in the biomedical context is that the data is highly skewed. That is, only 1% of words belong to a certain medical entity type, such as, the reason for medication usage compared to all other non-reason words. We propose a balanced, under-sampled bagging strategy that is dependent on the imbalance level to overcome the class imbalance problem. Second, we present an ensemble of heterogeneous recognizers approach that leverages a novel ensemble combiner. Our experimental results show that for biomedical text datasets: (i) a balanced learning environment along with an Ensemble of Heterogeneous Classifiers constantly improves the performance over individual base learners and, (ii) stacking-based ensemble combiner methods outperform simple Majority Voting by 0.30 F-measure. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.158.208.189

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Wunnava S., Qin X., Kakar T., Kong X., Rundensteiner E., Sahoo S. and De S. (2018). One Size Does Not Fit All: An Ensemble Approach Towards Information Extraction from Adverse Drug Event Narratives.In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, ISBN 978-989-758-281-3, pages 176-188. DOI: 10.5220/0006600201760188

@conference{healthinf18,
author={Susmitha Wunnava and Xiao Qin and Tabassum Kakar and Xiangnan Kong and Elke A. Rundensteiner and Sanjay K. Sahoo and Suranjan De},
title={One Size Does Not Fit All: An Ensemble Approach Towards Information Extraction from Adverse Drug Event Narratives},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF,},
year={2018},
pages={176-188},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006600201760188},
isbn={978-989-758-281-3},
}

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF,
TI - One Size Does Not Fit All: An Ensemble Approach Towards Information Extraction from Adverse Drug Event Narratives
SN - 978-989-758-281-3
AU - Wunnava S.
AU - Qin X.
AU - Kakar T.
AU - Kong X.
AU - Rundensteiner E.
AU - Sahoo S.
AU - De S.
PY - 2018
SP - 176
EP - 188
DO - 10.5220/0006600201760188

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.