Big Health Data

Preventing hospital re-admissions, minimizing risk of sepsis among patients admitted to hospital, understanding why people stay away from appointments, and many other aspects within behavior of patients and staff at Danish hospitals is something that may find solutions or answers hidden deeply in the vast amount of data available.
In this applied research project, vast amounts of anonymous health data are being analyzed and scrutinized using machine learning techniques to try identify new patterns in the data that can be used to intervene in irrational behavior, prevent poor outcome of patient flows and/or or at least identify correlations or dependencies among data. Among the techniques are artificial neural networks, clustering and K-means methods, etc.
Furthermore, new tools, methods, and work processes will be sought developed to help clinical staff understand the big amount of health data, and use it for better treatment of patients.