Text mining for pharmacovigilance: Using machine learning for drug name recognition and drug–drug interaction extraction and classification

Abacha, Asma Ben; Chowdhury, Md. Faisal Mahbub; Karanasiou, Aikaterini; Mrabet, Yassine; Lavelli, Alberto; Zweigenbaum, Pierre

doi:10.1016/j.jbi.2015.09.015

Cited by 70 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, the WBI-NER system that ranked first in the SemEval-2013 Task 9.1 (Recognition and classification of pharmacological substances, DNR), [3] is based on a linearchain CRF with specialized features. Other similar systems for DNR [2,13] use various general-and domainspecific features. In CCE, the same approach (feature engineering + conventional ML classifier) has achieved the best results.…”

Section: Related Workmentioning

confidence: 99%

“…Current state-of-the-art ML methods follow a two-step process: 1) feature engineering and 2) automated classification. [1,2,3,4] The first step represents the text by numeric vectors using domainspecific knowledge. The second step refers to the task of classifying each word into a different named-entity class, with popular choices for the classifier being the linear-chain Conditional Random Fields (CRF), Structural Support Vector Machines (S-SVM) and maximumentropy classifiers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

Unanue

Borzeshi

Piccardi

2017

Journal of Biomedical Informatics

106

View full text Add to dashboard Cite

Background. Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word "embeddings". Objectives. (i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets. Methods. Two deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models. Results. We have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DDI-DrugBank and DDI-MedLine, but not in the 2010 i2b2/VA IRB Revision dataset. Conclusion. We present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

Unanue

Borzeshi

Piccardi

2017

Journal of Biomedical Informatics

106

View full text Add to dashboard Cite

show abstract

“…The framework of this active learning approach is a sequential process: initial model generation, querying, training, and iteration. The CRF Algorithm BIO approach was also studied by Ben Abacha et al [14]. The features for the CRF algorithm are formulated based on token and linguistics feature and semantic feature.…”

Section: Related Workmentioning

confidence: 99%

“…Our proposed method is evaluated on DrugBank and MedLine medical open dataset obtained from SemEval 2013 Competition task 9.1; see https://www.cs.york.ac.uk/semeval-2013/task9/, which is also used by [11, 12, 14]. The format of both medical texts is in English where some sentences contain drug name entities.…”

Section: Introductionmentioning

confidence: 99%

A New Data Representation Based on Training Data Characteristics to Extract Drug Name Entity in Medical Text

Sadikin

Fanany

Basaruddin

2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

One essential task in information extraction from the medical corpus is drug name recognition. Compared with text sources come from other domains, the medical text mining poses more challenges, for example, more unstructured text, the fast growing of new terms addition, a wide range of name variation for the same drug, the lack of labeled dataset sources and external knowledge, and the multiple token representations for a single drug name. Although many approaches have been proposed to overwhelm the task, some problems remained with poor F-score performance (less than 0.75). This paper presents a new treatment in data representation techniques to overcome some of those challenges. We propose three data representation techniques based on the characteristics of word distribution and word similarities as a result of word embedding training. The first technique is evaluated with the standard NN model, that is, MLP. The second technique involves two deep network classifiers, that is, DBN and SAE. The third technique represents the sentence as a sequence that is evaluated with a recurrent NN model, that is, LSTM. In extracting the drug name entities, the third technique gives the best F-score performance compared to the state of the art, with its average F-score being 0.8645.

show abstract

“…This is evident from close to 70% of DDI articles and >50% of ADRs articles being published in the last ten years. Automated approaches have been developed for the recognition and extraction of DDIs or ADRs alone 6–8 , and there is an increasing interest in identifying ADRs caused by DDIs using text-mining approaches 9 . Since DDIs may occur when two drugs interact with the same gene 8 or when one drug inhibits or induces the metabolic pathway of the other drug 10 , it has also been suggested that incorporating drug-gene interactions (DGIs) can enhance the prediction of DDIs 8 .…”

Section: Introductionmentioning

confidence: 99%

Machine learning workflow to enhance predictions of Adverse Drug Reactions (ADRs) through drug-gene interactions: application to drugs for cutaneous diseases

Raja

Patrick

Elder

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Adverse drug reactions (ADRs) pose critical public health issues, affecting over 6% of hospitalized patients. While knowledge of potential drug-drug interactions (DDI) is necessary to prevent ADR, the rapid pace of drug discovery makes it challenging to maintain a strong insight into DDIs. In this study, we present a novel literature-mining framework for enhancing the predictions of DDIs and ADR types by integrating drug-gene interactions (DGIs). The ADR types were adapted from a DDI corpus, including i) adverse effect; ii) effect at molecular level; iii) effect related to pharmacokinetics; and iv) DDIs without known ADRs. By using random forest classifier our approach achieves an F-score of 0.87 across the ADRs classification using only the DDI features. We then enhanced the performance of the classifier by including DGIs (F-score = 0.90), and applied the classification model trained with the DDI corpus to identify the drugs that might interact with the drugs for cutaneous diseases. We successfully predict previously known ADRs for drugs prescribed to cutaneous diseases, and are also able to identify promising new ADRs.

show abstract

Text mining for pharmacovigilance: Using machine learning for drug name recognition and drug–drug interaction extraction and classification

Cited by 70 publications

References 18 publications

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

A New Data Representation Based on Training Data Characteristics to Extract Drug Name Entity in Medical Text

Machine learning workflow to enhance predictions of Adverse Drug Reactions (ADRs) through drug-gene interactions: application to drugs for cutaneous diseases

Contact Info

Product

Resources

About