Evaluation of linear classifiers on articles containing pharmacokinetic evidence of drug-drug interactions

TL;DR

This study evaluates linear classifiers on PubMed abstracts to identify articles with pharmacokinetic evidence of drug-drug interactions, aiming to improve literature mining for DDI research.

Contribution

It systematically compares various linear classifiers and feature transformations, including NER features, for classifying pharmacokinetic DDI evidence in biomedical literature.

Findings

Unigram and bigram features improve classification performance.

Normalization transforms enhance classifier accuracy.

NER features and dictionaries did not significantly aid classification.

Abstract

Background. Drug-drug interaction (DDI) is a major cause of morbidity and mortality. [...] Biomedical literature mining can aid DDI research by extracting relevant DDI signals from either the published literature or large clinical databases. However, though drug interaction is an ideal area for translational research, the inclusion of literature mining methodologies in DDI workflows is still very preliminary. One area that can benefit from literature mining is the automatic identification of a large number of potential DDIs, whose pharmacological mechanisms and clinical significance can then be studied via in vitro pharmacology and in populo pharmaco-epidemiology. Experiments. We implemented a set of classifiers for identifying published articles relevant to experimental pharmacokinetic DDI evidence. These documents are important for identifying causal mechanisms behind putative drug-drug interactions, an important step in the extraction of large numbers of potential DDIs. We evaluate performance of several linear classifiers on PubMed abstracts, under different feature transformation and dimensionality reduction methods. In addition, we investigate the performance benefits of including various publicly-available named entity recognition features, as well as a set of internally-developed pharmacokinetic dictionaries. Results. We found that several classifiers performed well in distinguishing relevant and irrelevant abstracts. We found that the combination of unigram and bigram textual features gave better performance than unigram features alone, and also that normalization transforms that adjusted for feature frequency and document length improved classification. For some classifiers, such as linear discriminant analysis (LDA), proper dimensionality reduction had a large impact on performance. Finally, the inclusion of NER features and dictionaries was found not to help classification.