Data Mining for Adverse Drug Events: Impact on Six Learning Styles.

Abstract

Emerging technologies and big data influence the role of nurses, calling for new ways of thinking and teaching. Innovative educational methods are needed to prepare students for providing evidence-based care in today's complex healthcare environment. Active learning methods appeal to tech-savvy, self-directed learners who desire instant results during the learning process. The aim of this pretest/posttest study was to evaluate the impact of active learning methods on student attitudes and feelings, using the Grasha-Riechmann Student Learning Style Scale. Results were used to tailor active learning interventions using Twitter and Federal Adverse Event Reporting System data, for a research and evidence-based practice nursing course. Participants (N = 126) evaluated tweets describing adverse drug events and their concordance with federal reporting system data. Paired-samples t test results revealed significant differences (P < .05) between pretest/posttest for five of the six learning style preferences. Active learning methods resulted in high levels of student engagement and satisfaction. Data mining as an active learning intervention is popular with learners and offers a quick, valuable way to reveal real-world adverse drug event experiences while introducing basic research principles.