CS 598
Graduate
Fall 2025
Spring 2025
Deep Learning for Healthcare
Deep learning methods and their applications in healthcare, combining theory, hands-on programming and a research-oriented project on real healthcare problems. No healthcare background is needed; Python is required, and linear algebra, calculus and Linux familiarity help.
What you will learn
- Implement deep learning models: DNNs, CNNs, RNNs, autoencoders, attention models, GNNs and generative models
- Apply them to clinical tasks: prediction, phenotyping, treatment recommendation, clinical NLP and imaging
- Work with real medical data in PyTorch and Jupyter, using PyHealth for health-record processing and modeling
- Reproduce and extend a recent deep learning for healthcare paper
How the course works
- Lectures and readings
- Video lectures and weekly readings covering both theory and applications.
- Labs
- Self-guided exercises on deep learning basics and PyHealth.
- Homework
- Five auto-graded programming assignments.
- Final project
- A team or solo reproduction and extension of a published paper, with a proposal, peer-reviewed draft, report, short video and code repository.
Textbooks
- Introduction to Deep Learning for Healthcare, Cao Xiao and Jimeng Sun
- Machine Learning for Drug Discovery, Tianfan Fu, Cao Xiao and Jimeng Sun
Generative AI tools such as ChatGPT and Claude are allowed for the final project, provided students validate and understand every output.