Introduction to Machine Learning for Epi

Machine learning, broadly defined as analytic techniques that fit models algorithmically by adapting to patterns in data, is growing in use across many areas within public health and healthcare. This course is intended for students with existing training in epidemiology and basic biostatistics who seek an introduction to the use of machine learning within epidemiologic research and practice. This includes an overview of key-terms and commonly-used algorithms, debates of the ethical and scientific considerations on the use of data-driven analytics when the goals are improvements in public health and causal inference and in-depth discussions about common implementations of machine learning within the current epidemiologic literature. Using a flipped classroom format, the course will combine online lecture videos with in-class discussions and group exercises to ensure a balance of substantive knowledge and practical skills. Through this hybrid learning approach, students will learn to apply critical thinking techniques as they explore the opportunities and limitations of using machine learning within the context of epidemiology. Throughout the duration of the course, all classes will include clear examples from the epidemiologic literature, discussions on ethical issues surrounding the use of machine learning and hands-on programming exercises in R/R Studio. After completion of this course, students will be able to discuss scenarios where machine learning can (and cannot) benefit epidemiologic analysis, analyze public health data using commonly-used machine learning techniques in R software, and pursue either more in-depth technical training or informed collaborations with scientists with specialized machine learning expertise.