A chronological pharmacovigilance network analytics approach for predicting adverse drug events

Behrooz Davazdahemami, Dursun Delen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objectives This study extends prior research by combining a chronological pharmacovigilance network approach with machine-learning (ML) techniques to predict adverse drug events (ADEs) based on the drugs' similarities in terms of the proteins they target in the human body. The focus of this research, though, is particularly centered on predicting the drug-ADE associations for a set of 8 common and high-risk ADEs. Materials and methods large collection of annotated MEDLINE biomedical articles was used to construct a drug-ADE network, and the network was further equipped with information about drugs' target proteins. Several network metrics were extracted and used as predictors in ML algorithms to predict the existence of network edges (ie, associations or relationships). Results Gradient boosted trees (GBTs) as an ensemble ML algorithm outperformed other prediction methods in identifying the drug-ADE associations with an overall accuracy of 92.8% on the validation sample. The prediction model was able to predict drug-ADE associations, on average, 3.84 years earlier than they were actually mentioned in the biomedical literature. Conclusion While network analysis and ML techniques were used in separation in prior ADE studies, our results showed that they, in combination with each other, can boost the power of one another and predict better. Moreover, our results highlight the superior capability of ensemble-Type ML methods in capturing drug-ADE patterns compared to the regular (ie, singular), ML algorithms.

Original languageEnglish
Pages (from-to)1311-1321
Number of pages11
JournalJournal of the American Medical Informatics Association
Volume25
Issue number10
DOIs
StatePublished - 1 Oct 2018
Externally publishedYes

Fingerprint

Pharmacovigilance
Drug-Related Side Effects and Adverse Reactions
Pharmaceutical Preparations
Human Body
Research
MEDLINE
Machine Learning
Proteins

Keywords

  • adverse drug events
  • ensemble models
  • machine learning
  • network analysis
  • prediction
  • target proteins

Cite this

@article{992190db9fdd47a3af8c1167b6d5d759,
title = "A chronological pharmacovigilance network analytics approach for predicting adverse drug events",
abstract = "Objectives This study extends prior research by combining a chronological pharmacovigilance network approach with machine-learning (ML) techniques to predict adverse drug events (ADEs) based on the drugs' similarities in terms of the proteins they target in the human body. The focus of this research, though, is particularly centered on predicting the drug-ADE associations for a set of 8 common and high-risk ADEs. Materials and methods large collection of annotated MEDLINE biomedical articles was used to construct a drug-ADE network, and the network was further equipped with information about drugs' target proteins. Several network metrics were extracted and used as predictors in ML algorithms to predict the existence of network edges (ie, associations or relationships). Results Gradient boosted trees (GBTs) as an ensemble ML algorithm outperformed other prediction methods in identifying the drug-ADE associations with an overall accuracy of 92.8{\%} on the validation sample. The prediction model was able to predict drug-ADE associations, on average, 3.84 years earlier than they were actually mentioned in the biomedical literature. Conclusion While network analysis and ML techniques were used in separation in prior ADE studies, our results showed that they, in combination with each other, can boost the power of one another and predict better. Moreover, our results highlight the superior capability of ensemble-Type ML methods in capturing drug-ADE patterns compared to the regular (ie, singular), ML algorithms.",
keywords = "adverse drug events, ensemble models, machine learning, network analysis, prediction, target proteins",
author = "Behrooz Davazdahemami and Dursun Delen",
year = "2018",
month = "10",
day = "1",
doi = "10.1093/jamia/ocy097",
language = "English",
volume = "25",
pages = "1311--1321",
journal = "Journal of the American Medical Informatics Association",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "10",

}

A chronological pharmacovigilance network analytics approach for predicting adverse drug events. / Davazdahemami, Behrooz; Delen, Dursun.

In: Journal of the American Medical Informatics Association, Vol. 25, No. 10, 01.10.2018, p. 1311-1321.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A chronological pharmacovigilance network analytics approach for predicting adverse drug events

AU - Davazdahemami, Behrooz

AU - Delen, Dursun

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Objectives This study extends prior research by combining a chronological pharmacovigilance network approach with machine-learning (ML) techniques to predict adverse drug events (ADEs) based on the drugs' similarities in terms of the proteins they target in the human body. The focus of this research, though, is particularly centered on predicting the drug-ADE associations for a set of 8 common and high-risk ADEs. Materials and methods large collection of annotated MEDLINE biomedical articles was used to construct a drug-ADE network, and the network was further equipped with information about drugs' target proteins. Several network metrics were extracted and used as predictors in ML algorithms to predict the existence of network edges (ie, associations or relationships). Results Gradient boosted trees (GBTs) as an ensemble ML algorithm outperformed other prediction methods in identifying the drug-ADE associations with an overall accuracy of 92.8% on the validation sample. The prediction model was able to predict drug-ADE associations, on average, 3.84 years earlier than they were actually mentioned in the biomedical literature. Conclusion While network analysis and ML techniques were used in separation in prior ADE studies, our results showed that they, in combination with each other, can boost the power of one another and predict better. Moreover, our results highlight the superior capability of ensemble-Type ML methods in capturing drug-ADE patterns compared to the regular (ie, singular), ML algorithms.

AB - Objectives This study extends prior research by combining a chronological pharmacovigilance network approach with machine-learning (ML) techniques to predict adverse drug events (ADEs) based on the drugs' similarities in terms of the proteins they target in the human body. The focus of this research, though, is particularly centered on predicting the drug-ADE associations for a set of 8 common and high-risk ADEs. Materials and methods large collection of annotated MEDLINE biomedical articles was used to construct a drug-ADE network, and the network was further equipped with information about drugs' target proteins. Several network metrics were extracted and used as predictors in ML algorithms to predict the existence of network edges (ie, associations or relationships). Results Gradient boosted trees (GBTs) as an ensemble ML algorithm outperformed other prediction methods in identifying the drug-ADE associations with an overall accuracy of 92.8% on the validation sample. The prediction model was able to predict drug-ADE associations, on average, 3.84 years earlier than they were actually mentioned in the biomedical literature. Conclusion While network analysis and ML techniques were used in separation in prior ADE studies, our results showed that they, in combination with each other, can boost the power of one another and predict better. Moreover, our results highlight the superior capability of ensemble-Type ML methods in capturing drug-ADE patterns compared to the regular (ie, singular), ML algorithms.

KW - adverse drug events

KW - ensemble models

KW - machine learning

KW - network analysis

KW - prediction

KW - target proteins

UR - http://www.scopus.com/inward/record.url?scp=85054889086&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocy097

DO - 10.1093/jamia/ocy097

M3 - Article

C2 - 30085102

AN - SCOPUS:85054889086

VL - 25

SP - 1311

EP - 1321

JO - Journal of the American Medical Informatics Association

JF - Journal of the American Medical Informatics Association

SN - 1067-5027

IS - 10

ER -