Machine Learning Methods for Survival Data in Clinical Trials Using R/Python

This short course is for those who are interested in learning data science principles and applying machine learning models in survival data sets from clinical trials or observational studies with an intervention arm. The course will explain the foundational underpinnings of the concepts behind these learning algorithms and their successful application in clinical research. The course will cover both R and Python programming to analyze the example data sets. For those who are interested in learning how machine learning can find underlying patterns in the data that may be pointing to a therapeutic benefit or detecting a safety signal in a subgroup with respect to time to event outcomes – this course will provide the methodological and programmatic tools for conducting their research. This one-day short course will provide a comprehensive overview of relevant statistical machine learning methods in the first half and the second half will focus on programming concepts. Topics include classical methods, such as the Cox model, as well as machine learning tools, including Bayesian and frequentist supervised learning, algorithms and software in R/Python, and numerous applications in survival analysis.