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

Area of Science:

• Nursing Education
• Health Informatics
• Evidence-Based Practice

Background:

• Emerging technologies and big data necessitate innovative teaching strategies in nursing.
• Traditional methods may not adequately prepare nurses for complex, evidence-based care.
• Active learning appeals to modern learners' desire for engagement and immediate feedback.

Purpose of the Study:

• To evaluate the impact of active learning methods on nursing students' attitudes and learning styles.
• To tailor educational interventions using real-world data for a nursing research course.
• To assess student engagement and satisfaction with novel teaching approaches.

Main Methods:

• A pretest/posttest study design was employed with 126 nursing students.
• The Grasha-Riechmann Student Learning Style Scale assessed learning preferences.
• Active learning interventions involved analyzing adverse drug events from Twitter and the Federal Adverse Event Reporting System (FAERS).

Main Results:

• Significant pretest/posttest differences were observed in five of six learning style preferences (P < .05).
• Active learning methods led to high levels of student engagement and satisfaction.
• Data mining of adverse drug events provided valuable real-world insights and introduced research principles.

Conclusions:

• Active learning strategies, particularly data mining, are effective in enhancing nursing students' learning experiences.
• These methods successfully bridge the gap between academic learning and practical, evidence-based nursing.
• Innovative educational approaches are crucial for preparing tech-savvy nursing students for contemporary healthcare challenges.