Machine Learning for Complex Medical Temporal Sequences - Tutorial

Advances in machine learning and their application to medical data receive increasing attention and demonstrate immense benefits for patients and practitioners. The adoption of Electronic Health Records (EHRs) in combination with the penetration of smart technologies and the Internet of Things give a further boost to initiatives for patient self-management and empowerment, with new forms of health-relevant data becoming available and requiring new data acquisition and analytics' workflows. In this tutorial, we elaborate on what temporal sequences of healthcare-related data look like, and we focus on two particular challenges: how to learn on medical sequences with gaps and how to deliver reasoning about what the model has learned.