Annotation and detection of drug effects in text for pharmacovigilance

  title={Annotation and detection of drug effects in text for pharmacovigilance},
  author={Paul Thompson and Sophia Daikou and Kenju Ueno and Riza Theresa Batista-Navarro and Junichi Tsujii and Sophia Ananiadou},
  journal={Journal of Cheminformatics},
Pharmacovigilance (PV) databases record the benefits and risks of different drugs, as a means to ensure their safe and effective use. Creating and maintaining such resources can be complex, since a particular medication may have divergent effects in different individuals, due to specific patient characteristics and/or interactions with other drugs being administered. Textual information from various sources can provide important evidence to curators of PV databases about the usage and effects… 
Discovering Adverse Drug Reactions from Twitter: A Sentiment Analysis Perspective
Using Twitter as a source for potential drug reaction detection, a database of 30,000 tweets with mentions of four distinct drugs was investigated, which resulted in finding 5 0 adverse reactions, showing that social networks can help in the discovery of adverse events, but there is a need for robust pre-processing.
Building a semantically annotated corpus for chronic disease complications using two document types
The PrevComp corpus is developed, which is annotated with information relevant to the identification of disease complications, underlying risk factors, and prevention measures, in the context of the interaction between hypertension and diabetes.
PGxCorpus: a Manually Annotated Corpus for Pharmacogenomics
PGxCorpus is introduced, a manually annotated corpus designed to fill the gap and to enable the automatic extraction of PGx relationships from text and to synthesize and summarize PGx knowledge.
PGxCorpus, a manually annotated corpus for pharmacogenomics
PGxCorpus is introduced, a manually annotated corpus designed to fill the gap and to enable the automatic extraction of PGx relationships from text and how it may be leveraged to synthesize and summarize PGx knowledge.
Annotation of Adverse Drug Reactions in Patients’ Weblogs
This paper crawled patient’s weblog articles shared on an online patient-networking platform and annotated the effects of drugs therein reported, and identified spans describing drug reactions and assigned labels for related drug names, standard codes for the symptoms of the reactions, and types of effects.
The 2011–2020 Trends of Data-Driven Approaches in Medical Informatics for Active Pharmacovigilance
It is found that appropriate methods and guidelines for active pharmacovigilance using medical big data are still required and should continue to be developed.
An annotated corpus with nanomedicine and pharmacokinetic parameters
A corpus of annotated drug product inserts taken from the US Food and Drug Administration’s Drugs@FDA online database is constructed and the reliability of the manual annotations are evaluated and the use of the corpus is demonstrated by evaluating two state-of-the-art named entity extraction systems, OpenNLP and Stanford NER.
Improving classification of Adverse Drug Reactions through Using Sentiment Analysis and Transfer Learning
A neural model that combines sentiment analysis with transfer learning techniques to improve ADR detection in social media postings is presented and it is shown that, in combination with rich representations of words and their contexts, transfer learning is beneficial.
Opportunities and Challenges of Using Big Data to Detect Drug‐Drug Interaction Risk
  • S. Quinney
  • Medicine, Biology
    Clinical pharmacology and therapeutics
  • 2019
Assessment of results may be hampered by the lack of gold standard positive and negative interacting drug pairs, but integrating clinical data mining with mechanistic understanding of drug action can promote confidence in DDI predictions.


A drug-adverse event extraction algorithm to support pharmacovigilance knowledge mining from PubMed citations.
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.
DrugQuest - a text mining workflow for drug association discovery
DrugQuest is a text mining tool for knowledge discovery: it is designed to cluster DrugBank records based on text attributes in order to find new associations between drugs.
Evaluation of Linear Classifiers on Articles Containing Pharmacokinetic Evidence of Drug-Drug Interactions
A set of classifiers for identifying published articles relevant to experimental pharmacokinetic DDI evidence were implemented, finding that the combination of unigram and bigram textual features gave better performance than unigrams alone, and that normalization transforms that adjusted for feature frequency and document length improved classification.
Extraction of Adverse Drug Effects from Clinical Records
Assessment of how much adverse-effect information is contained in records, and automatic extracting accuracy of the current standard Natural Language Processing (NLP) system revealed that 7.7% of records include adverse event information, and that 59% of them can be extracted automatically.
LimTox: a web tool for applied text mining of adverse event and toxicity associations of compounds, drugs and genes
Although the main focus of LimTox is on adverse liver events, it enables also basic searches for other organ level toxicity associations (nephrotoxicity, cardiotoxicity, thyrotoxicity and phospholipidosis), and integrates a range of text mining, named entity recognition and information extraction components.
Text mining for drug-drug interaction.
A comprehensive pharmacokinetics ontology was constructed that includes all aspects of in vitro pharmacokinetic experiments, in vivo Pharmacokinetics studies, as well as drug metabolism and transportation enzymes and the utility of the PK corpus was demonstrated by a drug interaction extraction text mining analysis.