The utility of adaptive eLearning data in predicting dental students' learning performance in a blended learning course

Objectives: To examine the impact of dental students' usage patterns within an adaptive learning platform (ALP), using ALP-related indicators, on their final exam performance. Methods: Track usage data from the ALP, combined with demographic and academic data including age, gender, pre- and post-test scores, and cumulative grade point average (GPA) were retrospectively collected from 115 second-year dental students enrolled in a blended learning review course. Learning performance was measured by post-test scores. Data were analyzed using correlation coefficients and linear regression tests. Results: The ALP-related variables (without controlling for background demographics and academic data) accounted for 29.6% of student final exam performance (R2=0.296, F(10,104)=4.37, p=0.000). Positive significant ALP-related predictors of post-test scores were improvement after activities (β=0.507, t(104)=2.101, p=0.038), timely completed objectives (β=0.391, t(104)=2.418, p=0.017), and number of revisions (β=0.127, t(104)=3.240, p=0.002). Number of total activities, regardless of learning improvement, negatively predicted post-test scores (β= -0.088, t(104)=-4.447, p=0.000). The significant R2 change following the addition of gender, GPA, and pre-test score (R2=0.689, F(13, 101)=17.24, p=0.000), indicated that these predictors explained an additional 39% of the variance in student performance beyond that explained by ALP-related variables, which were no longer significant. Inclusion of cumulative GPA and pre-test scores showed to be the strongest and only predictors of post-test scores (β=18.708, t(101)=4.815, p=0.038) and (β=0.449, t(101)=6.513, p=0.038), respectively. Conclusions: Track ALP-related data can be valuable indicators of learning behavior. Careful and contextual analysis of ALP data can guide future studies to examine practical and scalable interventions.