ABSTRACT
Machine learning (ML) offers potential opportunities to enhance the learning, teaching, and assessments within veterinary medical education including but not limited to assisting with admissions processes as well as student progress evaluations. The purpose of this primer is to assist veterinary educators in appraising and potentially adopting these rapid upcoming advances in data science and technology. In the first section, we introduce ML concepts and highlight similarities/differences between ML and classical statistics. In the second section, we provide a step-by-step worked example using simulated veterinary student data to answer a hypothesis-driven question. Python syntax with explanations is provided within the text to create a random forest ML prediction model, a model composed of decision trees with each decision tree being composed of nodes and leaves. Within each step of the model creation, specific considerations such as how to manage incomplete student records are highlighted when applying ML algorithms within the veterinary education field. The results from the simulated data demonstrate how decisions by the veterinary educator during ML model creation may impact the most important features contributing to the model. These results highlight the need for the veterinary educator to be fully transparent during the creation of ML models and future research is needed to establish guidelines for handling data not missing at random in medical education, and preferred methods for model evaluation.
ABSTRACT
Current teaching approaches in human and veterinary medicine across North America, Europe, and Australia include lectures, group discussions, feedback, role-play, and web-based training. Increasing class sizes, changing learning preferences, and economic and logistical challenges are influencing the design and delivery of communication skills in veterinary undergraduate education. The study's objectives were to (1) assess the effectiveness of small-group and web-based methods for teaching communication skills and (2) identify which training method is more effective in helping students to develop communication skills. At the Ross University School of Veterinary Medicine (RUSVM), 96 students were randomly assigned to one of three groups (control, web, or small-group training) in a pre-intervention and post-intervention group design. An Objective Structured Clinical Examination (OSCE) was used to measure communication competence within and across the intervention and control groups. Reliability of the OSCEs was determined by generalizability theory to be 0.65 (pre-intervention OSCE) and 0.70 (post-intervention OSCE). Study results showed that (1) small-group training was the most effective teaching approach in enhancing communication skills and resulted in students scoring significantly higher on the post-intervention OSCE compared to the web-based and control groups, (2) web-based training resulted in significant though considerably smaller improvement in skills than small-group training, and (3) the control group demonstrated the lowest mean difference between the pre-intervention/post-intervention OSCE scores, reinforcing the need to teach communication skills. Furthermore, small-group training had a significant effect in improving skills derived from the initial phase of the consultation and skills related to giving information and planning.