☆ 4.7 Article

Extensive evaluation of transformer-based architectures for adverse drug events extraction

KNOWLEDGE-BASED SYSTEMS (2023)

Related references

Note: Only part of the references are listed.

Review Biochemistry & Molecular Biology

The Pharmaceutical Industry in 2021. An Analysis of FDA Drug Approvals from the Perspective of Molecules

Beatriz G. de la Torre et al.

Summary: Similar to last year, 2021 will be remembered for the COVID-19 pandemic. Despite the approval of five vaccines, the pandemic remains uncontrolled. However, there have been significant drug approvals by the FDA, with 50 drugs authorized in 2021. Nitrogen aromatic heterocycles and fluorine atoms continue to be predominant among small molecules.

MOLECULES (2022)

Add to Collection

Article Health Care Sciences & Services

Monitoring User Opinions and Side Effects on COVID-19 Vaccines in the Twittersphere: Infodemiology Study of Tweets

Beatrice Portelli et al.

Summary: This study aims to create a web portal to monitor the public's opinion on COVID-19 vaccines through social media analysis. By analyzing tweets and visualizing data, the study provides insights into the public's views on vaccines and their changing trends. The research found that users tend to share news from reliable sources, and the general sentiment of Twitter users towards vaccines is negative/neutral.

JOURNAL OF MEDICAL INTERNET RESEARCH (2022)

Add to Collection

Article Medicine, Research & Experimental

Increasing adverse drug events extraction robustness on social media: Case study on negation and speculation

Simone Scaboro et al.

Summary: In the past decade, there has been an increase in users reporting adverse drug events on social media platforms. To quickly examine these large amounts of text, pharmacovigilance has used natural language processing techniques, but the robustness of these models has been questioned when dealing with linguistic phenomena like negations and speculations. This article introduces a benchmark to test the performance of four state-of-the-art systems in detecting ADEs containing negations and speculations, and proposes two strategies to increase the robustness of these models, resulting in significant improvements in performance.

EXPERIMENTAL BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Multimodal model with text and drug embeddings for adverse drug reaction classification

Andrey Sakhovskiy et al.

Summary: This paper introduces a multimodal model for classifying tweets as potential signals for adverse drug effects or drug reactions. The experimental results show that our models achieve state-of-the-art F1 measures in the Social Media Mining for Health Research and Applications (#SMM4H) benchmarks, and improve the accuracy by 8% in the classification of French tweets.

JOURNAL OF BIOMEDICAL INFORMATICS (2022)

Add to Collection

Article Computer Science, Information Systems

DeepADEMiner: a deep learning pharmacovigilance pipeline for extraction and normalization of adverse drug event mentions on Twitter

Arjun Magge et al.

Summary: Research on pharmacovigilance from social media data faces challenges in large-scale data analysis. The study introduces an ADE extraction pipeline that achieves state-of-the-art performance and satisfactory results on a new dataset.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2021)

Add to Collection

Article Biochemical Research Methods

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

Jinhyuk Lee et al.

BIOINFORMATICS (2020)

Add to Collection

Article Public, Environmental & Occupational Health

Adverse Events in Twitter-Development of a Benchmark Reference Dataset: Results from IMI WEB-RADR

Juergen Dietrich et al.

DRUG SAFETY (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

SpanBERT: Improving Pre-training by Representing and Predicting Spans

Mandar Joshi et al.

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (2020)

Add to Collection

Review Medical Informatics

Using Electronic Health Records to Identify Adverse Drug Events in Ambulatory Care: A Systematic Review

Chenchen Feng et al.

APPLIED CLINICAL INFORMATICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Using semantic analysis of texts for the identification of drugs with similar therapeutic effects

E. V. Tutubalina et al.

RUSSIAN CHEMICAL BULLETIN (2017)

Add to Collection

Article Multidisciplinary Sciences

MIMIC-III, a freely accessible critical care database

Alistair E. W. Johnson et al.

SCIENTIFIC DATA (2016)

Add to Collection

Article Computer Science, Theory & Methods

Text and Data Mining Techniques in Adverse Drug Reaction Detection

Sarvnaz Karimi et al.

ACM COMPUTING SURVEYS (2015)

Add to Collection

Article Computer Science, Interdisciplinary Applications

CADEC: A corpus of adverse drug event annotations

Sarvnaz Karimi et al.

JOURNAL OF BIOMEDICAL INFORMATICS (2015)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Portable automatic text classification for adverse drug reaction detection via multi-corpus training

Abeed Sarker et al.

JOURNAL OF BIOMEDICAL INFORMATICS (2015)

Add to Collection

Review Computer Science, Interdisciplinary Applications

Utilizing social media data for pharmacovigilance: A review

Abeed Sarker et al.

JOURNAL OF BIOMEDICAL INFORMATICS (2015)

Add to Collection

Article Computer Science, Information Systems

Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features

Azadeh Nikfarjam et al.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Framewise phoneme classification with bidirectional LSTM and other neural network architectures

A Graves et al.

NEURAL NETWORKS (2005)

Add to Collection

Article Biochemistry & Molecular Biology

Strong medicine

M Wadman

NATURE MEDICINE (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.