Format

Send to

Choose Destination
J Biomed Inform. 2017 Feb;66:72-81. doi: 10.1016/j.jbi.2016.12.005. Epub 2016 Dec 16.

Accuracy of an automated knowledge base for identifying drug adverse reactions.

Author information

1
Epidemiology Analytics, Janssen Research & Development, LLC, Raritan, NJ, United States; Erasmus University Medical Center, Rotterdam, Netherlands; Observational Health Data Sciences and Informatics (OHDSI), New York, NY, United States. Electronic address: evoss3@its.jnj.com.
2
University of Pittsburgh, Pittsburgh, PA, United States; Observational Health Data Sciences and Informatics (OHDSI), New York, NY, United States.
3
Epidemiology Analytics, Janssen Research & Development, LLC, Raritan, NJ, United States; Columbia University, New York, NY, United States; Observational Health Data Sciences and Informatics (OHDSI), New York, NY, United States.
4
Erasmus University Medical Center, Rotterdam, Netherlands; Observational Health Data Sciences and Informatics (OHDSI), New York, NY, United States.
5
Epidemiology Analytics, Janssen Research & Development, LLC, Raritan, NJ, United States; Observational Health Data Sciences and Informatics (OHDSI), New York, NY, United States.

Abstract

INTRODUCTION:

Drug safety researchers seek to know the degree of certainty with which a particular drug is associated with an adverse drug reaction. There are different sources of information used in pharmacovigilance to identify, evaluate, and disseminate medical product safety evidence including spontaneous reports, published peer-reviewed literature, and product labels. Automated data processing and classification using these evidence sources can greatly reduce the manual curation currently required to develop reference sets of positive and negative controls (i.e. drugs that cause adverse drug events and those that do not) to be used in drug safety research.

METHODS:

In this paper we explore a method for automatically aggregating disparate sources of information together into a single repository, developing a predictive model to classify drug-adverse event relationships, and applying those predictions to a real world problem of identifying negative controls for statistical method calibration.

RESULTS:

Our results showed high predictive accuracy for the models combining all available evidence, with an area under the receiver-operator curve of ⩾0.92 when tested on three manually generated lists of drugs and conditions that are known to either have or not have an association with an adverse drug event.

CONCLUSIONS:

Results from a pilot implementation of the method suggests that it is feasible to develop a scalable alternative to the time-and-resource-intensive, manual curation exercise previously applied to develop reference sets of positive and negative controls to be used in drug safety research.

KEYWORDS:

Adverse drug reaction; Health outcome; Knowledge base; Machine-learning experiment; Pharmacovigilance

PMID:
27993747
PMCID:
PMC5316295
DOI:
10.1016/j.jbi.2016.12.005
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center