Abstract:
First-year nurse practitioner and physician assistant students were presented with four simulated patient encounters in which they flagged pertinent findings. Data mining revealed a sub-group of students that did significantly poorer identifying pertinent findings, particularly negative findings. Overall student performance was high, masking the existence of this sub-group. These results demonstrate the potential of learning analytics for uncovering clinical reasoning errors among healthcare students. While we utilized the xAPI standard, other options and platforms are available that require less technical expertise. Regardless of approach, it is essential to carefully design the data to be gathered and how it will be analyzed.
Learning Objectives:
- Understand what learning analytics is and how it can be implemented in virtual patients.
- Recognize the potential of learning analytics for clinical education by exploring some preliminary results.
- Become familiar with technical options and challenges in implementing learning analytics.