Text and Data Mining Techniques in Adverse Drug Reaction Detection

Abstract

We review data mining and related computer science techniques that have been studied in the area of drug safety to identify signals of adverse drug reactions from different data sources, such as spontaneous reporting databases, electronic health records, and medical literature. Development of such techniques has become more crucial for public heath, especially with the growth of data repositories that include either reports of adverse drug reactions, which require fast processing for discovering signals of adverse reactions, or data sources that may contain such signals but require data or text mining techniques to discover them. In order to highlight the importance of contributions made by computer scientists in this area so far, we categorize and review the existing approaches, and most importantly, we identify areas where more research should be undertaken.

Natural Language Analysis of Online Health Forums

“…A comprehensive review of NLP systems used for text processing in the medical domain can be found in [8]. Prior research in finding useful health related information from social media, mainly focused on named entity extraction (NER) tasks such as discovering ADRs in relation to a drug or treatment as reported in [8].…”

“…Prior research in finding useful health related information from social media, mainly focused on named entity extraction (NER) tasks such as discovering ADRs in relation to a drug or treatment as reported in [8]. For example, Nikfarjam et al [12] built a system, called ADRMine, using CRFs for recognising ADR mentions from social media.…”

“…In order to extract this type of information from free text in medical forums, natural language analysis of the text is required [5]. As has been pointed out by Karimi et al [8], detecting, from unstructured text, the disease, treatment and symptom entities, their attributes and existing relationships, is a major research issue in the Natural Language Processing (NLP) domain. Although progress has been made in extracting entities, there is still the challenge of extracting specific relationships between these entities [7].…”

An Optimized Drug Similarity Framework for Side-effect Prediction

“…Drug side-effects are effects which are secondary to the intended effects [1]. They have drawn attention of the society because they cause a large number of morbidity and fatality every year.…”

Classification of Web Documents Using Hybrid Feature Selection.

“…The movement of the market is depended on the information of the online news articles, reactions, and proceedings is turned out to be an budding theme for investigation in the field data mining and text mining [5].To establish the outcome of modern methods for text classifications are elucidated in [6] which three problems were highlighted: documents demonstration, classifier erection and classifier assessment. Therefore, generating an information structure that can signify the data, and creating a classifier that can be utilized to visualize the class label of a document with high accuracy, develops into the major issues in text categorization.…”