Motivation

The health sector is faced with the challenge of an ever-increasing variety of data types and sources. These include traditional and new medical devices, which nowadays are all capable of generating large amounts of clinically relevant data. Additionally, modern medicine is confronted with an unprecedented data flood arising from recent technology breakthroughs, e.g. in genome sequencing, imaging and remote sensing amongst others, which are becoming part of routine clinical care at an ever-increasing pace. Despite this rapid increase in data diversity and volume, only a surprisingly small fraction of this data is currently integrated into processes in clinical practice. Integration is hindered, amongst others, by the lack of modern IT infrastructure capable of aggregating and integrating this data, and thereby allowing clinicians to take advantage of a holistic view of all available data that would allow optimal diagnosis and treatment. At the same time, these data sets, which are often unique and invaluable, are not available for research purposes, thus hampering clinical research and the translation of research insights into clinical practice.