Utilizing Text Mining on Online Medical Forums to Predict Label Change due to Adverse Drug Reactions

Abstract

We present an end-to-end text mining methodology for relation extraction of adverse drug reactions (ADRs) from medical forums on the Web. Our methodology is novel in that it combines three major characteristics: (i) an underlying concept of using a head-driven phrase structure grammar (HPSG) based parser; (ii) domain-specific relation patterns, the acquisition of which is done primarily using unsupervised methods applied to a large, unlabeled text corpus; and (iii) automated post-processing algorithms for enhancing the set of extracted relations.We empirically demonstrate the ability of our proposed approach to predict ADRs prior to their reporting by the Food and Drug Administration (FDA). Put differently, we put our approach to a predictive test by demonstrating that our methodology can credibly point to ADRs that were not uncovered in clinical trials for evaluating new drugs that come to market but were only reported later on by the FDA as a label change.

Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records

“…While the method is simple, its result might present no explicit clinical relevance of a derived drug-event pair [ 9 ] due to disregard relational context that might express an exact impression in a clinical event such as a drug treats a symptom or a drug causes a symptom. To fill in this research gap, many researchers consider surrounding contexts around drug and event entities within clinical texts and represent such data by either using pattern-based method [ 10 – 15 ] or feature-based method [ 16 – 18 ]. Consequently, a potential ADR is identified by either training supervised learning or semisupervised learning [ 19 ] model.…”

“…Despite the method is simple, it disregards semantic dependency among surrounding contexts that might express real clinical evident. On the other hand, a pattern-based method [ 14 , 15 ] is manifested that achieves more accurate clinical relation extraction because it relies on cues or trigger words that usually implies a semantic relation. Although, a pattern-based method is more efficient than the window-based method, a set of predefined patterns or redundant pattern filtering by a human is required.…”

Combination of Deep Recurrent Neural Networks and Conditional Random Fields for Extracting Adverse Drug Reactions from User Reviews

“…NLP techniques have been applied in five main domain of texts: (i) biomedical literature, clinical trial records, and electronic medical/health records (e.g., medical correspondence and letters) [ 3 , 5 , 10 , 27 – 30 ]; (ii) short messages from Twitter [ 9 , 31 , 32 ]; (iii) user reviews from health-related and e-commerce websites [ 4 , 26 , 33 , 34 ]; (iv) web search logs [ 22 ]; and (v) forum discussions and message boards about medications, health conditions, treatment modality, and so on [ 35 – 37 ]. Most of these works focused on creating linguistic methods based on keywords for extracting major adverse effects, classifiers to detect whether a text contains ADRs or is relevant to drug reactions, and sequence labeling algorithms to extract mentions of ADRs.…”

Big Data Analyses in Health and Opportunities for Research in Radiology

“…Both Feldman and colleagues and Sampathkumar and colleagues' methods identified adverse drug reactions that were not identified during clinical trials but were eventually identified by the Food and Drug Administration causing a label change. 9,10 Researchers also explored analysis of sentiment 11 in forums (i.e., whether posters are positive, negative, or neutral about a topic). Other researchers also explored content summarization techniques to summarize an entire forum and the themes that are present in the conversations.…”