%0 Journal Article
%@ 2369-3762
%I JMIR Publications
%V 10
%N 
%P e51388
%T Enriching Data Science and Health Care Education: Application and Impact of Synthetic Data Sets Through the Health Gym Project
%A Kuo,Nicholas I-Hsien
%A Perez-Concha,Oscar
%A Hanly,Mark
%A Mnatzaganian,Emmanuel
%A Hao,Brandon
%A Di Sipio,Marcus
%A Yu,Guolin
%A Vanjara,Jash
%A Valerie,Ivy Cerelia
%A de Oliveira Costa,Juliana
%A Churches,Timothy
%A Lujic,Sanja
%A Hegarty,Jo
%A Jorm,Louisa
%A Barbieri,Sebastiano
%+ Centre for Big Data Research in Health, The University of New South Wales, Level 2, AGSM Building (G27), Botany St, Kensington NSW, Sydney, 2052, Australia, 61 0293850645, n.kuo@unsw.edu.au
%K medical education
%K generative model
%K generative adversarial networks
%K privacy
%K antiretroviral therapy (ART)
%K human immunodeficiency virus (HIV)
%K data science
%K educational purposes
%K accessibility
%K data privacy
%K data sets
%K sepsis
%K hypotension
%K HIV
%K science education
%K health care AI
%D 2024
%7 16.1.2024
%9 Viewpoint
%J JMIR Med Educ
%G English
%X Large-scale medical data sets 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 data sets applicable to various areas of data science education, including machine learning, data visualization, and traditional statistical models. Initially, we generated 3 synthetic data sets for sepsis, acute hypotension, and antiretroviral therapy for HIV infection. This paper discusses the educational applications of Health Gym’s synthetic data sets. We illustrate this through their use in postgraduate health data science courses delivered by the University of New South Wales, Australia, and a Datathon event, involving academics, students, clinicians, and local health district professionals. We also include adaptable worked examples using our synthetic data sets, designed to enrich hands-on tutorial and workshop experiences. Although we highlight the potential of these data sets in advancing data science education and health care artificial intelligence, we also emphasize the need for continued research into the inherent limitations of synthetic data.
%M 38227356
%R 10.2196/51388
%U https://mededu.jmir.org/2024/1/e51388
%U https://doi.org/10.2196/51388
%U http://www.ncbi.nlm.nih.gov/pubmed/38227356