2. Teaching

261-5120-00L Computational Biomedicine II (Spring 2018)

Semester Spring Semester 2018
Lecturers G. Rätsch
Periodicity yearly course
Language of instruction 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 four topic clusters that will cover the most relevant applications of ML in Biomedicine:

1) Structured time series: Temporal time series of structured data often appear in biomedical datasets, presenting challenges as containing variables with different periodicities, being conditioned by static data, etc.
2) Medical notes: Vast amount of medical observations are stored in the form of free text, we will analyze stategies for extracting knowledge from them.
3) Medical images: Images are a fundamental piece of information in many medical disciplines. We will study how to train ML algorithms with them.
4) 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.

Prerequisites / Notice
Data Structures & Algorithms, Introduction to Machine Learning, Statistics/Probability, Programming in Python, Unix Command Line

Relation to Course 261-5100-00 Computational Biomedicine: This course is a continuation of the previous course with new topics related to medical data and machine learning. The format of Computational Biomedicine II will also be different. It is helpful but not essential to attend Computational Biomedicine before attending Computational Biomedicine II.

Location

The lecture will be held at ETH in ML H 41.1.

Projects

The descriptions for the projects of the course:

Course Overview

Date Topic Course Material
01.03.2018 Lecture: Introduction Lecture Slides 01
08.03.2018 Lecture: Sequence learning & Machine Learning Lecture Slides 02
15.03.2018 Lecture: Natural Language Processing of Clinical Texts Lecture Slides 03 Exercise notebook
22.03.2018 Lecture: Representational Learning Lecture Slides 04 Representation Learning
Student presentations 1. Diet Networks: Thin Parameters for Fat Genomics
2. Deep learning of the tissue-regulated splicing code
12.04.2018 Lecture: Time Series in Electronic Health Records Lecture Slides 05 Exercises
Student presentations 1. Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes
2. Creating a universal SNP and small indel variant caller with deep neural networks
19.04.2018 Lecture: Survival Analyses Lecture Slides 06 Exercise notebook
Student presentations 1. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records
2. Quantifying Mental Health from Social Media with Neural User Embeddings
26.04.2018 Lecture: Machine Learning in Radiology Lecture Slides 07
Student presentations 1. Gaussian Process Robust Regression for Noisy Heart Rate Data
2. Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks
03.05.2018 Lecture: Introduction to CNNs for Medical Image Analysis Lecture Slides 08
Student presentations 1. Deep Survival Analysis
2. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning
17.05.2018 Lecture: Privacy Preserving Computing Lecture Slides 09
Student presentations 1. Scalable and accurate deep learning for electronic health records
2. Detecting Cancer Metastases on Gigapixel Pathology Images
24.05.2018 Lecture: Interpretability of Machine Learning Models Lecture Slides 10
Student presentations 1. Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
2. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
31.05.2018 Lecture: Ethics of Big Medical Data Analytics Lecture Slides 11
Student presentations 1. RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism