Identifying adverse drug events from patient social media: A case study for diabetes

Abstract

Patient social media sites have emerged as major platforms for discussion of treatments and drug side effects, making them a promising source for listening to patients' voices in adverse drug event reporting. However, extracting patient reports from social media continues to be a challenge in health informatics research. In light of the need for more robust extraction methods, the authors developed a novel information extraction framework for identifying adverse drug events from patient social media. They also conducted a case study on a major diabetes patient social media platform to evaluate their framework's performance. Their approach achieves an f-measure of 86 percent in recognizing discussion of medical events and treatments, an f-measure of 69 percent for identifying adverse drug events, and an f-measure of 84 percent in patient report extraction. Their proposed methods significantly outperformed prior work in extracting patient reports of adverse drug events in health social media.