Portable Automatic Text Classification for Adverse Drug Reaction Detection via Multi-corpus Training

By Abeed Sarker, Graciela Gonzalez. Journal of Biomedical Informatics, 2014

374 citations recorded by the source corpus.

Objective Automatic detection of Adverse Drug Reaction (ADR) mentions from text has recently received significant interest in pharmacovigilance research. Current research focuses on various sources of text-based information, including social media — where enormous amounts of user posted data is available, which have the potential for use in pharmacovigilance if collected and filtered accurately. The aims of this study are: (i) to explore natural language processing approaches for generating useful features from text, and utilizing them in optimized machine learning algorithms for automatic classification of ADR assertive text segments; (ii) to present two data sets that we prepared for the task of ADR detection from user posted internet data; and (iii) to investigate if combining training data from distinct corpora can improve automatic classification accuracies. Methods One of our three data sets contains annotated sentences from clinical reports, and the two other data sets, built in-house, consist of annotated posts from social media. Our text classification approach relies on generating a large set of features, representing semantic properties (e.g., sentiment, polarity, and topic), from short text nuggets. Importantly, using our expanded feature sets, we combine training data from different corpora in attempts to boost classification accuracies. Results Our feature-rich classification approach performs significantly better than previously published approaches with ADR class F-scores of 0.812 (previously reported best: 0.770), 0.538 and 0.678 for the three data sets. Combining training data from multiple compatible corpora further improves the ADR F-scores for the in-house data sets to 0.597 (improvement of 5.9 units) and 0.704 (improvement of 2.6 units) respectively. Conclusions Our research results indicate that using advanced NLP techniques for generating information rich features from text can significantly improve classification accuracies over existing benchmarks. Our experiments illustrate the benefits of incorporating various semantic features such as topics, concepts, sentiments, and polarities. Finally, we show that integration of information from compatible corpora can significantly improve classification performance. This form of multi-corpus training may be particularly useful in cases where data sets are heavily imbalanced (e.g., social media data), and may reduce the time and costs associated with the annotation of data in the future.

Subfields: Computational Theory and Mathematics, Sociology and Political Science, Toxicology

View Paper: https://www.semanticscholar.org/paper/23de58fdc005c42f155d8949ad56305ad656084f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Sociology and Political Science

In Toxicology

Citations in the corpus

A Systematic Review on Imbalanced Data Challenges in Machine Learning (2019, methodology): “For instance, in Sarker and Gonzalez (2015), NLP and ML techniques have been used to automatic detect adverse drug reaction using multi-corpus training using social media text including medical information.”
Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features (2015, background): “…information has recently encouraged researchers to explore other resources for drug-safety information extraction including various health social networking sites, such as DS, 11,25,26 PatientsLikeMe, 27,28 and MedHelp; 29 generic social networks such as Twitter; 8,9,30 and users’ web search logs.”
Clinical Information Extraction Applications: A Literature Review (2017, methodology): “[98] proposed an automatic text classification approach for detecting adverse drug reaction using SVM.”
Utilizing Social Media Data for Pharmacovigilance: A Review (2015, methodology): “Most clas-siﬁcation research, however, have only used very basic linguistic features for classiﬁcation ( e.g. , bag of words), and only very recent research has focused on exploring deep linguistic and semantic features and advanced machine learning techniques [41].”