Machine Learning for Health Care
Course Details
| Number | 261-5120-00L |
| Lecturers | V. Boeva, G. Rätsch, J. Vogt |
| Semester | Spring 2022 |
| Language | English |
Abstract
The course will review the most relevant methods and applications of Machine Learning in Biomedicine, discuss the main challenges they present and their current technical problems.
Objective
During the last years, we have observed a rapid growth in the field of Machine Learning (ML), mainly due to improvements in ML algorithms, the increase of data availability and a reduction in computing costs. This growth is having a profound impact in biomedical applications, where the great variety of tasks and data types enables us to get benefit of ML algorithms in many different ways. In this course we will review the most relevant methods and applications of ML in biomedicine, discuss the main challenges they present and their current technical solutions.
Content
The course will consist of several topic clusters that will cover the most relevant applications of ML in Biomedicine:
1) Analysis of medical images: Images are a fundamental piece of information in many medical disciplines. We will study how to train ML algorithms with them.
2) Analysis of genomics data: ML in genomics is still an emerging subfield, but given that genomics data are arguably the most extensive and complex datasets that can be found in biomedicine, it is expected that many relevant ML applications will arise in the near future. We will review and discuss current applications and challenges.
3) Analysis of text and representation learning: Vast amount of medical observations are stored in the form of free text, we will analyze strategies for extracting knowledge from them.
4) Analysis of time series and sequence data: Temporal time series or sequential data often appear in biomedical datasets, presenting challenges as containing variables with different periodicities, being conditioned by static data, etc.
5) Interpretability & Privacy of ML methods. We will discuss the need for interpretable ML models, and we will discuss how differential private data can be generated e.g. by using GANs.
Prerequisites/Notice
Data Structures & Algorithms, Introduction to Machine Learning, Statistics/Probability, Programming in Python, Unix Command Line
Location
Tue 10-12 HG D 7.2
Tue 13-14 HG D 7.2
Course Schedule
| Date | Topic | Material | Tutorial | Paper Presentation |
|---|---|---|---|---|
| Introduction | Intro | - | ||
| Imaging | Imaging | - | ||
| Time-Series | Project1 | Imaging paper1, paper2 | ||
| Representation Learning | Representation Learning | Time-series paper1, paper2 | ||
| NLP | NLP | Representation Learning paper1, paper2 | ||
| Interpretability 1 | Project 2 | NLP paper1, paper2 | ||
| No Lecture | Interpretability | - | ||
| Intepretability 2 | Project 1 presentations | Ethics paper1, paper2 | ||
| Genetics Supervised | Project 3 | Interpretability paper1, paper2 | ||
| Genetics Unsupervised | Genetics | - | ||
| Survival Analysis | Project 2 presentations | Genetics paper1, paper2 | ||
| Privacy | Survival Analysis | Survival Analysis paper1, paper2 | ||
| Ethics (lecture is virtual) | Exam questions | - | ||
| Exam Polls etc | Project 3 Presentations | Privacy paper1, paper2 |