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

Moodle course webpage


Location

Tue 10-12 HG D 7.2

Tue 13-14 HG D 7.2

Course Schedule

DateTopicMaterialTutorialPaper Presentation
Introduction
Lecture Slides JV
Lecture Slides VB
Lecture Slides GR
Recording_JV
Recording_VB_Tutorial
Recording_GR
Intro-
Imaging
Lecture Slides
Lecture Recording Part 1
Lecture Recording Part 2
Tutorial Recording
Imaging-
Time-Series
Lecture Slides
Lecture Recording Part1
Lecture Recording Part2
Tutorial Recording
Presentation Slides 1
Presentation Slides 2
Project1Imaging paper1, paper2
Representation Learning
Lecture Slides
Lecture Recording
Tutorial Recording
Presentation Slides 1
Presentation Slides 2
Representation LearningTime-series paper1, paper2
NLP
Lecture Slides
Lecture Recording
Tutorial Recording
NLPRepresentation Learning paper1, paper2
Interpretability 1
Lecture Slides
Lecture Recording
Tutorial Recording
Project 2NLP paper1, paper2
No Lecture
Tutorial Recording
Interpretability-
Intepretability 2
Lecture Slides
Lecture Recording
Lecture Demos
Project 1 presentationsEthics paper1, paper2
Genetics Supervised
Lecture Slides
Lecture Recording
Lecture Demos
Tutorial Recording
Project 3Interpretability paper1, paper2
Genetics Unsupervised
Lecture Slides
Lecture Recording
Lecture Demos
Tutorial Recording
Genetics-
Survival Analysis
Lecture Slides
Lecture Recording
Lecture Demos
Project 2 presentationsGenetics paper1, paper2
Privacy
Lecture Slides
Lecture Recording
Tutorial Recording
Survival AnalysisSurvival Analysis paper1, paper2
Ethics (lecture is virtual)
Lecture Slides
Lecture Recording
Tutorial Recording
Exam questions-
Exam Polls etc
Lecture Slides
Project 3 PresentationsPrivacy paper1, paper2