Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure

Tafti, Ahmad P.; Badger, Jonathan C.; LaRose, Eric; Shirzadi, Ehsan; Mahnke, Andrea; Mayer, John; Ye, Zhan; Page, David; Peissig, Peggy L.

doi:10.2196/medinform.9170

Cited by 48 publications

(38 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In response to the growing number of safety reports, many efforts in recent years have been made to automate the identification of AEs using annotation and text-mining methods in a variety of source document types such as electronic health records, clinical notes, and social media [8][9][10][11][12][13][14][15][16][17]. Other groups have employed classification approaches for identifying text from similar sources as AEs [18][19][20][21][22][23][24][25][26][27][28][29]. However, few efforts have focused on the classification of identified AEs with regard to their type, severity, seriousness, or causality [30][31][32][33].…”

Section: Methodsmentioning

confidence: 99%

Application of Augmented Intelligence for Pharmacovigilance Case Seriousness Determination

Routray

Tetarenko²,

Abu-Assal

et al. 2019

Drug Saf

View full text Add to dashboard Cite

Introduction Identification of adverse events and determination of their seriousness ensures timely detection of potential patient safety concerns. Adverse event seriousness is a key factor in defining reporting timelines and is often performed manually by pharmacovigilance experts. The dramatic increase in the volume of safety reports necessitates exploration of scalable solutions that also meet reporting timeline requirements. Objective The aim of this study was to develop an augmented intelligence methodology for automatically identifying adverse event seriousness in spontaneous, solicited, and medical literature safety reports. Deep learning models were evaluated for accuracy and/or the F1 score against a ground truth labeled by pharmacovigilance experts. Methods Using a stratified random sample of safety reports received by Celgene, we developed three neural networks for addressing identification of adverse event seriousness: (1) a binary adverse-event level seriousness classifier; (2) a classifier for determining seriousness categorization at the adverse-event level; and (3) an annotator for identifying seriousness criteria terms to provide supporting evidence at the document level. Results The seriousness classifier achieved an accuracy of 83.0% in post-marketing reports, 92.9% in solicited reports, and 86.3% in medical literature reports. F1 scores for seriousness categorization were 77.7 for death, 78.9 for hospitalization, and 75.5 for important medical events. The seriousness annotator achieved an F1 score of 89.9 in solicited reports, and 75.2 in medical literature reports. Conclusions The results of this study indicate that a neural network approach can provide an accurate and scalable solution for potentially augmenting pharmacovigilance practitioner determination of adverse event seriousness in spontaneous, solicited, and medical literature reports. Ramani Routray and Niki Tetarenko contributed equally to this work.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of Augmented Intelligence for Pharmacovigilance Case Seriousness Determination

Routray

Tetarenko²,

Abu-Assal

et al. 2019

Drug Saf

View full text Add to dashboard Cite

show abstract

“…However, much of the technical details have not been published; for example, the use of complex logic. This and other similar efforts 18 are mostly data-centric. A slightly similar work to this paper has been developed at Massachusetts General Hospital (QPID Inc. 5 ), offering solutions at a commercial level, but no prototype is available to experiment with.…”

Section: Related Workmentioning

confidence: 89%

MicroShare: Privacy-Preserved Medical Resource Sharing through MicroService Architecture

Yang¹,

Zu²,

Liu³

et al. 2018

Int. J. Biol. Sci.

View full text Add to dashboard Cite

This paper takes up the problem of medical resource sharing through MicroService architecture without compromising patient privacy. To achieve this goal, we suggest refactoring the legacy EHR systems into autonomous MicroServices communicating by the unified techniques such as RESTFul web service. This lets us handle clinical data queries directly and far more efficiently for both internal and external queries. The novelty of the proposed approach lies in avoiding the data de-identification process often used as a means of preserving patient privacy. The implemented toolkit combines software engineering technologies such as Java EE, RESTful web services, JSON Web Tokens to allow exchanging medical data in an unidentifiable XML and JSON format as well as restricting users to the need-to-know principle. Our technique also inhibits retrospective processing of data such as attacks by an adversary on a medical dataset using advanced computational methods to reveal Protected Health Information (PHI). The approach is validated on an endoscopic reporting application based on openEHR and MST standards. From the usability perspective, the approach can be used to query datasets by clinical researchers, governmental or non-governmental organizations in monitoring health care and medical record services to improve quality of care and treatment.

show abstract

“…Results showed the nonassociation between the use of this drug and any major cardiovascular event (e.g., myocardial infarction, stroke, or death). Tafti et al (2017) presented the development of a Big Data Neural Network system whose main objective is the discovery and identification of adverse drug events from scientific articles and social networks related to health. To carry out this task, authors used a ML-based approach (Michalski et al, 2013), NLP (Collobert et al, 2011) and distributed processing frameworks such as Apache Spark.…”

Section: Hypotheses Generation and Knowledge Discoverymentioning

confidence: 99%

An advanced review on text mining in medicine

Luque

Luna

Luque

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Health care professionals produce abundant textual information in their daily clinical practice and this information is stored in many diverse sources and, generally, in textual form. The extraction of insights from all the gathered information, mainly unstructured and lacking normalization, is one of the major challenges in computational medicine. In this respect, text mining (TM) assembles different techniques to derive valuable insights from unstructured textual data so it has led to be especially relevant in medicine. The aim of this paper is therefore to provide an extensive review of existing techniques and resources to perform TM tasks in medicine. In this review, more than 90 relevant research studies have been analyzed, describing the most important practical applications, terminological resources, tools, and open challenges of TM in medicine. This article is categorized under: Application Areas > Health Care Algorithmic Development > Biological Data Mining Algorithmic Development > Hierarchies and Trees Algorithmic Development > Ensemble Methods

show abstract

Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure

Cited by 48 publications

References 47 publications

Application of Augmented Intelligence for Pharmacovigilance Case Seriousness Determination

Application of Augmented Intelligence for Pharmacovigilance Case Seriousness Determination

MicroShare: Privacy-Preserved Medical Resource Sharing through MicroService Architecture

An advanced review on text mining in medicine

Contact Info

Product

Resources

About