A graduate level course exploring the challenges and opportunities in machine learning for clinical and healthcare applications. Topics include causal inference, interpretability, fairness and ethics. Covers models for risk stratification, time-series analysis, reinforcement learning, computer vision and NLP. Discussions moderated by Danny Eytan and Uri Shalit about how these techniques will change public health and personalized medicine.
This course reviews basic and advanced topics in causal inference. Covers graphical causal models, Pearl’s do-calculus and Rubin’s potential outcomes framework. Advanced topics include causal discovery and connections to reinforcement learning and covariate shift. Examples from medicine, economics and public policy, social media, marketing and sales.