Application of Synthetic Datasets across Courses in Health Informatics Education

Health information education plays a crucial role in training healthcare professionals to understand and manage patient data. Hands-on experience in all phases of data management and analysis is essential to empower students and enable them to apply the knowledge and skills gained from coursework to class projects and in real life scenarios. However, it is challenging for health information education to use real-world datasets directly in the classes due to security and privacy concerns. Synthetic datasets that mimic real-world healthcare data can be used as a teaching tool in health informatics education. These datasets offer numerous advantages, such as providing a consistent and reliable source of data for faculty and students, protecting patient privacy, and enabling the exploration of complex healthcare scenarios. In this paper, we demonstrate the development and implementation of three synthetic datasets across the health informatics curriculum at George Mason University. These synthetic datasets are used to teach critical skills such as database management, data integration, coding, and data mining.