A study of early sepsis detection models based on multivariate medical time series
Sepsis is a life-threatening complication caused by the body's response to an infection. Therefore, it is important to have an accurate method to detect sepsis as early as possible. The features have missing values and non-uniform sampling frequencies, hence a GP based interpolation method is proposed. Additionally, this work develops and compares different sepsis detection models based on real medical data which can predict the occurrence of sepsis during hospitalization.
Aren Maes obtained his M.Sc. degree in Computer Science Engineering at Ghent University in 2019. Since August 2019, he is active as a PhD student in the Internet Technology and Data Science Lab (IDLab) at Ghent University where he is working on data analysis techniques for medical time series data.