This graduate course follows a research-based teaching approach and discusses methods for combining human intelligence with machine learning to solve problems from health informatics. For practical applications we focus on the Julia language - besides of R and Python. Students should get acquainted with the specific features of medical data and basic examples of automatic and interactive machine learning, also being able to use specific programming languages for carrying out various typical project exercises.

ML meets health informatics, introduction to the health domain, challenges and future direction; fundamentals and specifics of biomedical data, information and knowledge;  knowledge, decision, cognition, reasoning, probability, uncertainty, Bayesian statistics;  aML - Applied Machine Learning, deep learning on biomedical images, with practical exercises using Berkeley Caffe;  aML: text document classification in Python;  aML: Julia for learning machine learning, practical introduction to the Julia language on examples;  iML - Interactive Machine Learning: protein folding, crowdsourcing, gamification and ML;  iML: towards open medical data: k-anonymization, privacy preserving ML; iML: intelligent, interactive visualization and visual analytics, subspace clustering;  iML: interactive tumor growth simulation; outlook and future challenges.

ECTS-Breakdown (sum=75h, corresponds with 3 ECTS):

15h: presence during lecture

15h: preparation before and after lecture

30h: preparation and presentation of project

15h: written exam including preparation

paper based on selected project (40%)

presentation of selected project (30%)

final written exam (30%)