JMIR Publications

ABSTRACT

Large-scale medical datasets are vital for hands-on education in health data science, but are often inaccessible due to privacy concerns. Addressing this gap, we developed the Health Gym project, a free and open-source platform designed to generate synthetic health datasets applicable to various areas of data science education, including machine learning, data visualisation, and traditional statistical models. Initially, we generated three synthetic datasets for sepsis, acute hypotension, and antiretroviral therapy for human immunodeficiency virus. This paper discusses the educational applications of the Health Gym's synthetic datasets. We illustrate this through their use in postgraduate health data science courses delivered by the University of New South Wales (UNSW), Australia, and a Datathon event, involving academics, students, clinicians, and local health district professionals. We also include adaptable worked examples using our synthetic datasets, designed to enrich hands-on tutorial and workshop experiences. While we highlight the potential of these datasets in advancing data science education and healthcare AI, we also emphasise the need for continued research into the inherent limitations of synthetic data.