OH00AQ40 Machine learning in Medicine (5 cr)
Cooperation network course
Network: Education network on Inverse Problems
This course is offered through the Network for Inverse Problems. These studies are available for the following degree students:
- Bachelor's Degree Programme in Mathematics
- Bachelor's Degree Programme in Mathematics (Subject Teacher)
- Master’s Degree Programme in Mathematics
- Master's degree Programme in Mathematics (Subject Teacher)
- Doctoral Degree Programme in Mathematics and Statistics
Description
1. Introduction to Machine Learning 2. Short Mathematical Review 3. Classical Machine Learning - Linear regression - Logistic regression 4. Unsupervised Learning - Clustering (K-means) - Dimensionality reduction (PCA) 5. Principles of ML in Medicine - Data issues: sampling, stratification, preprocessing, normalization - Challenges and bias - Cross-validation and generalization - Patient separation - Model evaluation 6. Introduction to Neural Networks 7. Tree-Based and Ensemble Models 8. Ethics in Machine Learning
Learning outcomes
The objective of this course is to provide students with a foundation in machine learning and its applications in medicine. Upon completion, student will be able to: - Understand the basic concepts and principles of machine learning and apply reasoning to interpret data and model results. - Recognize common machine learning problem types (e.g., classification, regression, clustering) and the methods used to address them in medical applications, and integrate knowledge from medicine, mathematics, and computer science when approaching practical problems. - Apply basic machine learning models using Python and work with some medical data, considering challenges such as bias or limited sample sizes. - Gain an understanding of performance evaluation metrics and validation methods. - Recognize ethical considerations and challenges in applying machine learning responsibly in medicine.
Additional information
-Important Note: The content of this course closely overlaps with OH00AQ39 (Principles of Machine Learning in Medicine). Students are advised to take only one of these courses to avoid redundancy. -Please familiarize yourself with the electronic examination procedures before the final exam. -We welcome students from diverse backgrounds and perspectives. Diversity is recognized as a resource and strength, and we aim to support students’ learning needs both in and out of class. -A large amount of code and AI-generated solutions is publicly available for introductory ML tasks. In this course, their use is strongly discouraged, as the primary goal is to learn by implementing methods independently.
Description of prerequisites
-Basic understanding of Python programming is required to complete the project work. -Mathematics and statistics: Basic understanding is recommended. -Linear algebra: Familiarity is helpful.