A drug-adverse event extraction algorithm to support pharmacovigilance knowledge mining from PubMed citations.

PubMedPublished 1 January 2011Open access

Wéi Wang, Krystl Haerian, Hojjat Salmasian, Rave Harpaz, Herbert Chase, Carol Friedman

Citations44

TL;DR

A method is reported on that automatically determines whether a specific adverse event (AE) is caused by a specific drug based on the content of PubMed citations, and shows that AUROC was 0.93 and 0.86 respectively.

Abstract

Adverse drug events (ADEs) create a serious problem causing substantial harm to patients. An executable standardized knowledgebase of drug-ADE relations which is publicly available would be valuable so that it could be used for ADE detection. The literature is an important source that could be used to generate a knowledgebase of drug-ADE pairs. In this paper, we report on a method that automatically determines whether a specific adverse event (AE) is caused by a specific drug based on the content of PubMed citations. A drug-ADE classification method was initially developed to detect neutropenia based on a pre-selected set of drugs. This method was then applied to a different set of 76 drugs to determine if they caused neutropenia. For further proof of concept this method was applied to 48 drugs to determine whether they caused another AE, myocardial infarction. Results showed that AUROC was 0.93 and 0.86 respectively.

Keywords

Immunology and MicrobiologyComputer SciencePharmacology, Toxicology and Pharmaceutics

On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes

1,887 Citations2001Andrew Y. Ng, Michael I. Jordan

It is shown, contrary to a widely-held belief that discriminative classifiers are almost always to be preferred, that there can often be two distinct regimes of performance as the training set size is increased, one in which each algorithm does better.

European Journal of Clinical PharmacologyA Bayesian neural network method for adverse drug reaction signal generation

1,402 Citations1998Andrew Bate, Marie Lindquist +5 more

The BCPNN will be an extremely useful adjunct to the expert assessment of very large numbers of spontaneously reported ADRs, and can be used in the detection of significant signals from the data set of the WHO Programme on International Drug Monitoring.

ScienceDrug Target Identification Using Side-Effect Similarity

1,249 Citations2008Mónica Campillos, Michael Kuhn +3 more

Applied to 746 marketed drugs, a network of 1018 side effect–driven drug-drug relations became apparent, 261 of which are formed by chemically dissimilar drugs from different therapeutic indications, hinting at new uses of marketed drugs.

Classifying semantic relations in bioscience texts

259 Citations2004Barbara Rosario, Marti A. Hearst

This work examines the problem of distinguishing among seven relation types that can occur between the entities "treatment" and "disease" in bioscience text, and finds that the latter help achieve high classification accuracy.

View PDF

PubMedExploring text mining from MEDLINE.

68 Citations2002Padmini Srinivasan, Thomas C. Rindflesch

A text mining application that exploits the MeSH heading subheading combinations present in MEDLINE records and suggests that this summary and the diversity indicators will be useful a health care practitioner or researcher.

View PDF

Meeting of the Association for Computational LinguisticsExtraction of Disease-Treatment Semantic Relations from Biomedical Sentences

23 Citations2010Oana Frunza, Diana Inkpen

This paper describes the study on identifying semantic relations that exist between diseases and treatments in biomedical sentences, which focuses on three semantic relations: Cure, Prevent, and Side Effect.