VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
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 different topic clusters that will cover the most relevant applications of ML in Health Care, as e.g. 1) Structured time series: Temporal time series of structured data often appear in biomedical datasets, presenting challenges such as containing variables with different periodicities or being influenced by static data. 2) Medical notes: Many medical observations are stored as free text. We will analyze strategies for extracting knowledge from these textual records. 3) Medical images: Images are a fundamental piece of information in many medical disciplines. We will study how to train ML algorithms to analyze and interpret medical images effectively. 4) Genomics data: ML in genomics is still an emerging subfield. However, given that genomics data are arguably the most extensive and complex datasets in biomedicine, we expect many relevant ML applications to arise in the near future. We will review and discuss current applications and challenges in genomics data analysis. 5) Explainable/Interpretable ML: Interpretable and explainable machine learning focuses on the design of human-understandable models and algorithms that allow for black-box model introspection after training, i.e., post hoc. We will explore methods to make ML models more transparent, particularly in the context of healthcare. 6) Representation Learning: Representation learning is a crucial aspect of ML in healthcare. It involves learning meaningful representations from data, which can be especially valuable in tasks like medical image analysis, feature extraction from biomedical time series data, or dimensionality reduction. We will delve into techniques for efficient representation learning to enhance the performance of healthcare ML models.