- Basics of probability and linear algebra
- ML Basics, evaluation of ML models
- What is different in healthcare? Health data modalities, imbalance, rare events, stakeholders, etc.
- Intro to pandas, sklearn, pytorch
- Classification methods for healthcare
- Diagnosis, prognosis, stratification/staging, segmentation
- SVM, random forests, xgboost
- Unsupervised methods for healthcare
- PCA, ICA, Tensor decomposition
- Clustering
- Graphical models for healthcare
- Bayesian networks
- Hidden Markov models
- Causality
- Causal discovery
- Causal inference
- Deep learning for healthcare
- CNNs
- Recurrent networks
- Autoencoders
- Self-supervised learning
- Generative models
- Large language models
- Federated learning and privacy
- Trustworthy ML for healthcare
- Explainability
- Robustness
- Fairness
- Safety
- Ethics of AI in Healthcare