Improving interpretability and performance of risk prediction models for decision support in clinical environments

Main host institution

  • KU Leuven

Foreign host institution

  • Faculty of Health Sciences, University of Maribor


  • Public tender for co-financing the Slovenian part of joint Flemish-Slovenian projects where The Research Foundation – Flanders, FWO has the role of the leading institution

Problem description

Recently rediscovered and vastly improved neural network based techniques, commonly named deep learning techniques, are becoming increasingly popular as a predictive tool in different fields of healthcare. It was shown that deep learning techniques outperform less complex predictive models on many occasions, especially in cases where feature engineering is needed prior to prediction. On the other hand, deep learning based risk estimation allows very limited interpretation for healthcare experts or patients.


To address this challenge, this project will research the embedding of deep learning models and feature extraction in visual analytics techniques. Visual analytics (VA) combines automated analysis with visualization techniques to gain insight into complex datasets and to support interpretability of models. More specifically, we will research how we can design, develop and evaluate interactive VA techniques on top of different prediction models for chronic diseases risk estimation, such as Type 2 Diabetes (T2D) and Cardiovascular Diseases (CVD) .