Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach

Bollegala, Danushka ORCID: 0000-0003-4476-7003, Maskell, Simon ORCID: 0000-0003-1917-2913, Sloane, Richard, Hajne, Joanna and Pirmohamed, Munir ORCID: 0000-0002-7534-7266 (2018) Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach. JMIR PUBLIC HEALTH AND SURVEILLANCE, 4 (2). pp. 292-303.

Text jmir.pdf - Author Accepted Manuscript Download (521kB)

Abstract

<h4>Background</h4>Detecting adverse drug reactions (ADRs) is an important task that has direct implications for the use of that drug. If we can detect previously unknown ADRs as quickly as possible, then this information can be provided to the regulators, pharmaceutical companies, and health care organizations, thereby potentially reducing drug-related morbidity and saving lives of many patients. A promising approach for detecting ADRs is to use social media platforms such as Twitter and Facebook. A high level of correlation between a drug name and an event may be an indication of a potential adverse reaction associated with that drug. Although numerous association measures have been proposed by the signal detection community for identifying ADRs, these measures are limited in that they detect correlations but often ignore causality.<h4>Objective</h4>This study aimed to propose a causality measure that can detect an adverse reaction that is caused by a drug rather than merely being a correlated signal.<h4>Methods</h4>To the best of our knowledge, this was the first causality-sensitive approach for detecting ADRs from social media. Specifically, the relationship between a drug and an event was represented using a set of automatically extracted lexical patterns. We then learned the weights for the extracted lexical patterns that indicate their reliability for expressing an adverse reaction of a given drug.<h4>Results</h4>Our proposed method obtains an ADR detection accuracy of 74% on a large-scale manually annotated dataset of tweets, covering a standard set of drugs and adverse reactions.<h4>Conclusions</h4>By using lexical patterns, we can accurately detect the causality between drugs and adverse reaction-related events.

Item Type:	Article
Uncontrolled Keywords:	machine learning, ADR detection, causality, lexical patterns, causality detection, support vector machines
Depositing User:	Symplectic Admin
Date Deposited:	12 Jun 2018 10:52
Last Modified:	19 Jan 2023 01:32
DOI:	10.2196/publichealth.8214
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3022470