Development of an adverse drug reaction corpus from consumer health posts

Maryam Zolnoori; Timothy B. Patrick; Kin Wah Fung; Paul Fontelo; Anthony Faiola; Yi Shuan Shirley Wu; Kelly Xu; Jiaxi Zhu; Christina E. Eldredge

Development of an adverse drug reaction corpus from consumer health posts

Maryam Zolnoori, Timothy B. Patrick, Kin Wah Fung, Paul Fontelo, Anthony Faiola, Yi Shuan Shirley Wu, Kelly Xu, Jiaxi Zhu, Christina E. Eldredge

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

UWM-Adverse Drug Events Corpus (UWM-ADEC) is an annotated corpus that has been developed from consumer drug review posts in social media. In this corpus, we identified four types of Adverse Drug Reactions (ADRs) including physiological, psychological, cognitive, and functional problems. Additionally, we mapped the ADRs to corresponding concepts in Unified medical language Systems (UMLS). The quality of the corpus was measured using well-defined guidelines, double coding, high inter-annotator agreement, and final reviews by pharmacists and clinical terminologists. This corpus is a valuable source for research in the area of text mining and machine learning for ADRs identifications from consumer health posts, specifically for psychiatric medications.

Original language	English
Pages (from-to)	19-26
Number of pages	8
Journal	CEUR Workshop Proceedings
Volume	1996
State	Published - 2017
Event	2nd Social Media Mining for Health Research and Applications Workshop, SMM4H 2017 - Washington, United States Duration: Nov 4 2017 → …

ASJC Scopus subject areas

General Computer Science

Cite this

@article{12cec829e3004f618d51c14d66fe029d,

title = "Development of an adverse drug reaction corpus from consumer health posts",

abstract = "UWM-Adverse Drug Events Corpus (UWM-ADEC) is an annotated corpus that has been developed from consumer drug review posts in social media. In this corpus, we identified four types of Adverse Drug Reactions (ADRs) including physiological, psychological, cognitive, and functional problems. Additionally, we mapped the ADRs to corresponding concepts in Unified medical language Systems (UMLS). The quality of the corpus was measured using well-defined guidelines, double coding, high inter-annotator agreement, and final reviews by pharmacists and clinical terminologists. This corpus is a valuable source for research in the area of text mining and machine learning for ADRs identifications from consumer health posts, specifically for psychiatric medications.",

author = "Maryam Zolnoori and Patrick, {Timothy B.} and Fung, {Kin Wah} and Paul Fontelo and Anthony Faiola and Wu, {Yi Shuan Shirley} and Kelly Xu and Jiaxi Zhu and Eldredge, {Christina E.}",

year = "2017",

language = "English",

volume = "1996",

pages = "19--26",

note = "2nd Social Media Mining for Health Research and Applications Workshop, SMM4H 2017 ; Conference date: 04-11-2017",

}

TY - JOUR

T1 - Development of an adverse drug reaction corpus from consumer health posts

AU - Zolnoori, Maryam

AU - Patrick, Timothy B.

AU - Fung, Kin Wah

AU - Fontelo, Paul

AU - Faiola, Anthony

AU - Wu, Yi Shuan Shirley

AU - Xu, Kelly

AU - Zhu, Jiaxi

AU - Eldredge, Christina E.

PY - 2017

Y1 - 2017

N2 - UWM-Adverse Drug Events Corpus (UWM-ADEC) is an annotated corpus that has been developed from consumer drug review posts in social media. In this corpus, we identified four types of Adverse Drug Reactions (ADRs) including physiological, psychological, cognitive, and functional problems. Additionally, we mapped the ADRs to corresponding concepts in Unified medical language Systems (UMLS). The quality of the corpus was measured using well-defined guidelines, double coding, high inter-annotator agreement, and final reviews by pharmacists and clinical terminologists. This corpus is a valuable source for research in the area of text mining and machine learning for ADRs identifications from consumer health posts, specifically for psychiatric medications.

AB - UWM-Adverse Drug Events Corpus (UWM-ADEC) is an annotated corpus that has been developed from consumer drug review posts in social media. In this corpus, we identified four types of Adverse Drug Reactions (ADRs) including physiological, psychological, cognitive, and functional problems. Additionally, we mapped the ADRs to corresponding concepts in Unified medical language Systems (UMLS). The quality of the corpus was measured using well-defined guidelines, double coding, high inter-annotator agreement, and final reviews by pharmacists and clinical terminologists. This corpus is a valuable source for research in the area of text mining and machine learning for ADRs identifications from consumer health posts, specifically for psychiatric medications.

UR - http://www.scopus.com/inward/record.url?scp=85037035751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037035751&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85037035751

SN - 1613-0073

VL - 1996

SP - 19

EP - 26

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 2nd Social Media Mining for Health Research and Applications Workshop, SMM4H 2017

Y2 - 4 November 2017

ER -

Development of an adverse drug reaction corpus from consumer health posts

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this