Use of Learning Management System Data to Predict Student Success in a Pharmacy Capstone Course

Area of Science:

• Educational Technology
• Data Science in Education
• Pharmacy Education

Background:

• Learning management system (LMS) data offers potential for identifying at-risk students in online courses.
• Previous research has not fully explored changes in student engagement over time within LMS platforms.

Purpose of the Study:

• To apply group-based trajectory modeling (GBTM) to LMS data for identifying predictors of successful course completion.
• To investigate the association of LMS activity and synchronous session attendance with academic performance.

Main Methods:

• Exploratory GBTM was utilized to analyze LMS activity (page views, time, dates) and virtual synchronous learning session attendance.
• Student groups were defined based on trajectories of weekly page view counts using structural equation modeling.
• The study was conducted in a capstone disease-management course for a Doctor of Pharmacy program.

Main Results:

• Three distinct page view engagement groups were identified: high (1,818 views), moderate (1,029 views), and low (441 views).
• Group assignment showed a moderate association with final grades.
• Consistent attendance at synchronous sessions significantly improved the predictive accuracy of academic performance within engagement groups.

Conclusions:

• GBTM applied to LMS data, incorporating synchronous engagement, can provide early indicators of students at risk of failing.
• This approach enables targeted interventions for at-risk students in online learning environments.
• Further validation with diverse LMS data and earlier curriculum integration is recommended.