Utilizing predictive analytics to identify at-risk students in digitalized medical education: a motivational perspective

Abstract

Digitalization has become an imperative of medical education but, also, it raises the questions of forecasting, determination of the latest educational trends and predict system responsiveness. The results indicate that utilizing predictive analytics is an important aspect for transferring to digitalized learning. The aim of the present research is to assess motivation index among medical students establishing effective models of predictive analytics and to design the multi-component target-oriented algorithm of pedagogical interventions for improvement of digitalized medical education. The findings show that pedagogical interventions affected the educational process positively and slightly increased students’ academic outcomes. The growth of motivation index for the experimental dashboard in the successful category was +7,7 % and +5,98 % for the safe category. The number of students facing potential risks decreased by 9,4 % and at-risk students by 4,27 % in the experimental dashboard. We suggest that neglecting early identification of at-risk students brings to low academic performance. This demonstrates that implementing the multi-component target-oriented algorithm of pedagogical interventions contributes to improvement of the educational process in the institutions of higher medical education. To conclude, the detailed description of pedagogical intervention was presented to facilitate the use of the algorithm in digitalized medical education.