Using Machine Learning in Veterinary Medical Education: An Introduction for Veterinary Medicine Educators

SIMPLE SUMMARY: Machine learning (ML) is subfield of artificial intelligence that enables computers to learn from data and improve their performance without being explicitly programmed by a human. ML has the potential to enhance veterinary medical education by improving learning, teaching, and assessments. This primer introduces ML concepts to veterinary educators and administrators, highlighting their similarities and differences with classical statistics. It then provides a step-by-step example using simulated veterinary student data to address a specific question: which records in the simulated veterinary student data will predict a student passing or failing a specific course. The example demonstrates the use of the Python programming language to create a random forest ML prediction model, a type of ML algorithm which is composed of many decision trees and each of these trees is composed of nodes and leaves. During the creation of the random forest model, we emphasize specific considerations such as managing student records which may have missing information. The results show how decisions made by veterinary educators during ML model creation may impact which type of records are shown to be most important. While this form of ML may prove to be beneficial, transparency in creating ML models is crucial, and further research is needed to establish best practices and guidelines for veterinary medical education ML projects. 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.