A research framework for pharmacovigilance in health social media

Identification and evaluation of patient adverse drug event reports

Xiao Liu, Hsinchun Chen

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Social media offer insights of patients' medical problems such as drug side effects and treatment failures. Patient reports of adverse drug events from social media have great potential to improve current practice of pharmacovigilance. However, extracting patient adverse drug event reports from social media continues to be an important challenge for health informatics research. In this study, we develop a research framework with advanced natural language processing techniques for integrated and high-performance patient reported adverse drug event extraction. The framework consists of medical entity extraction for recognizing patient discussions of drug and events, adverse drug event extraction with shortest dependency path kernel based statistical learning method and semantic filtering with information from medical knowledge bases, and report source classification to tease out noise. To evaluate the proposed framework, a series of experiments were conducted on a test bed encompassing about postings from major diabetes and heart disease forums in the United States. The results reveal that each component of the framework significantly contributes to its verall effectiveness. Our framework significantly outperforms prior work.

Original languageEnglish (US)
Pages (from-to)268-279
Number of pages12
JournalJournal of Biomedical Informatics
Volume58
DOIs
StatePublished - Dec 1 2015

Fingerprint

Social Media
Pharmacovigilance
Social Identification
Drug-Related Side Effects and Adverse Reactions
Health
Medical problems
Research
Hospital beds
Natural Language Processing
Semantics
Informatics
Knowledge Bases
Treatment Failure
Noise
Processing
Heart Diseases
Learning
Experiments
Pharmaceutical Preparations

Keywords

  • Adverse drug event extraction
  • Health social media analytics
  • Information search and retrieval
  • Knowledge acquisition
  • Pharmacovigilance
  • Text mining

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

@article{3f6da2efcf8a4be3b8e8bd1293ea774e,
title = "A research framework for pharmacovigilance in health social media: Identification and evaluation of patient adverse drug event reports",
abstract = "Social media offer insights of patients' medical problems such as drug side effects and treatment failures. Patient reports of adverse drug events from social media have great potential to improve current practice of pharmacovigilance. However, extracting patient adverse drug event reports from social media continues to be an important challenge for health informatics research. In this study, we develop a research framework with advanced natural language processing techniques for integrated and high-performance patient reported adverse drug event extraction. The framework consists of medical entity extraction for recognizing patient discussions of drug and events, adverse drug event extraction with shortest dependency path kernel based statistical learning method and semantic filtering with information from medical knowledge bases, and report source classification to tease out noise. To evaluate the proposed framework, a series of experiments were conducted on a test bed encompassing about postings from major diabetes and heart disease forums in the United States. The results reveal that each component of the framework significantly contributes to its verall effectiveness. Our framework significantly outperforms prior work.",
keywords = "Adverse drug event extraction, Health social media analytics, Information search and retrieval, Knowledge acquisition, Pharmacovigilance, Text mining",
author = "Xiao Liu and Hsinchun Chen",
year = "2015",
month = "12",
day = "1",
doi = "10.1016/j.jbi.2015.10.011",
language = "English (US)",
volume = "58",
pages = "268--279",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - A research framework for pharmacovigilance in health social media

T2 - Identification and evaluation of patient adverse drug event reports

AU - Liu, Xiao

AU - Chen, Hsinchun

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Social media offer insights of patients' medical problems such as drug side effects and treatment failures. Patient reports of adverse drug events from social media have great potential to improve current practice of pharmacovigilance. However, extracting patient adverse drug event reports from social media continues to be an important challenge for health informatics research. In this study, we develop a research framework with advanced natural language processing techniques for integrated and high-performance patient reported adverse drug event extraction. The framework consists of medical entity extraction for recognizing patient discussions of drug and events, adverse drug event extraction with shortest dependency path kernel based statistical learning method and semantic filtering with information from medical knowledge bases, and report source classification to tease out noise. To evaluate the proposed framework, a series of experiments were conducted on a test bed encompassing about postings from major diabetes and heart disease forums in the United States. The results reveal that each component of the framework significantly contributes to its verall effectiveness. Our framework significantly outperforms prior work.

AB - Social media offer insights of patients' medical problems such as drug side effects and treatment failures. Patient reports of adverse drug events from social media have great potential to improve current practice of pharmacovigilance. However, extracting patient adverse drug event reports from social media continues to be an important challenge for health informatics research. In this study, we develop a research framework with advanced natural language processing techniques for integrated and high-performance patient reported adverse drug event extraction. The framework consists of medical entity extraction for recognizing patient discussions of drug and events, adverse drug event extraction with shortest dependency path kernel based statistical learning method and semantic filtering with information from medical knowledge bases, and report source classification to tease out noise. To evaluate the proposed framework, a series of experiments were conducted on a test bed encompassing about postings from major diabetes and heart disease forums in the United States. The results reveal that each component of the framework significantly contributes to its verall effectiveness. Our framework significantly outperforms prior work.

KW - Adverse drug event extraction

KW - Health social media analytics

KW - Information search and retrieval

KW - Knowledge acquisition

KW - Pharmacovigilance

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84947939048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947939048&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2015.10.011

DO - 10.1016/j.jbi.2015.10.011

M3 - Article

VL - 58

SP - 268

EP - 279

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -