Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017

Maksim Belousov; Nikola Milosevic; William Dixon; Goran Nenadic

Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017

Maksim Belousov, Nikola Milosevic, William Dixon, Goran Nenadic

Research output: Contribution to conference › Paper › peer-review

Abstract

Adverse drug reactions (ADRs) are unwanted or harmful effects experienced after the administration of a certain drug or a combination of drugs, presenting a challenge for drug development and drug administration. In this paper, we present a set of taggers for extracting adverse drug reactions and related entities, including factors, severity, negations, drug class and animal. The systems used a mix of rule-based, machine learning (CRF) and deep learning (BLSTM with word2vec embeddings) methodologies in order to annotate the data. The systems were
submitted to adverse drug reaction shared task, organised during Text Analytics Conference in 2017 by National Institute for Standards and Technology, achieving F1-scores of 76.00 and 75.61 respectively

Original language	English
Number of pages	11
Publication status	Published - 2018
Event	Text Analysis Conference: TAC 2017 Workshop - National Institute of Standards and Technology, Gaithersburg, Maryland, United States Duration: 13 Nov 2017 → 14 Nov 2017

Conference

Conference	Text Analysis Conference
Country/Territory	United States
City	Gaithersburg, Maryland
Period	13/11/17 → 14/11/17

Keywords

health informatics
text mining
drug labels
Adverse drug events

Access to Document

https://tac.nist.gov/publications/2017/participant.papers/TAC2017.GN_team.proceedings.pdf

1 Poster

Extracting adverse drug reactions and their context using sequence labelling ensembles
Milosevic, N., Nenadic, G., Belousov, M. & Dixon, W., Apr 2018.
Research output: Contribution to conference › Poster › peer-review

Cite this

@conference{24be066927ef4ec48dfbe23c3fa05d53,

title = "Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017",

abstract = "Adverse drug reactions (ADRs) are unwanted or harmful effects experienced after the administration of a certain drug or a combination of drugs, presenting a challenge for drug development and drug administration. In this paper, we present a set of taggers for extracting adverse drug reactions and related entities, including factors, severity, negations, drug class and animal. The systems used a mix of rule-based, machine learning (CRF) and deep learning (BLSTM with word2vec embeddings) methodologies in order to annotate the data. The systems weresubmitted to adverse drug reaction shared task, organised during Text Analytics Conference in 2017 by National Institute for Standards and Technology, achieving F1-scores of 76.00 and 75.61 respectively",

keywords = "health informatics, text mining, drug labels, Adverse drug events",

author = "Maksim Belousov and Nikola Milosevic and William Dixon and Goran Nenadic",

year = "2018",

language = "English",

note = "Text Analysis Conference : TAC 2017 Workshop ; Conference date: 13-11-2017 Through 14-11-2017",

}

TY - CONF

T1 - Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017

AU - Belousov, Maksim

AU - Milosevic, Nikola

AU - Dixon, William

AU - Nenadic, Goran

PY - 2018

Y1 - 2018

N2 - Adverse drug reactions (ADRs) are unwanted or harmful effects experienced after the administration of a certain drug or a combination of drugs, presenting a challenge for drug development and drug administration. In this paper, we present a set of taggers for extracting adverse drug reactions and related entities, including factors, severity, negations, drug class and animal. The systems used a mix of rule-based, machine learning (CRF) and deep learning (BLSTM with word2vec embeddings) methodologies in order to annotate the data. The systems weresubmitted to adverse drug reaction shared task, organised during Text Analytics Conference in 2017 by National Institute for Standards and Technology, achieving F1-scores of 76.00 and 75.61 respectively

AB - Adverse drug reactions (ADRs) are unwanted or harmful effects experienced after the administration of a certain drug or a combination of drugs, presenting a challenge for drug development and drug administration. In this paper, we present a set of taggers for extracting adverse drug reactions and related entities, including factors, severity, negations, drug class and animal. The systems used a mix of rule-based, machine learning (CRF) and deep learning (BLSTM with word2vec embeddings) methodologies in order to annotate the data. The systems weresubmitted to adverse drug reaction shared task, organised during Text Analytics Conference in 2017 by National Institute for Standards and Technology, achieving F1-scores of 76.00 and 75.61 respectively

KW - health informatics

KW - text mining

KW - drug labels

KW - Adverse drug events

M3 - Paper

T2 - Text Analysis Conference

Y2 - 13 November 2017 through 14 November 2017

ER -

Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017

Abstract

Conference

Keywords

Access to Document

Fingerprint

Research output

Extracting adverse drug reactions and their context using sequence labelling ensembles

Cite this