Towards data-driven predictive models in hospital care
Electronic medical records and lately electronic health records serve as a rich source of data for analytical and research purposes. This talk will focus on two key ideas that allow the integration of data-driven predictive models in everyday hospital care. We will address the data privacy issues that can limit the performance of the developed predictive models due to limited sample sizes. On the other hand, once the large repositories of data are available we can target patient conditions more individually by searching for similar cases, retrospectively or in real time. Some characteristics of data and types of problems that can be addressed by personalized predictive models will be presented in the second part of the talk.
About the lecturer
Gregor Štiglic is a Vice-Dean for Research, an Associate Professor and Head of Research Institute at the University of Maribor, Faculty of Health Sciences. He worked as a Visiting Researcher at the Data Analysis and Biomedical Analytics (DABI) Center at Temple University (2012) and as a Visiting Assistant Professor at Shah Lab, Stanford School of Medicine (2013). His research interests encompass application of knowledge discovery and predictive modelling techniques to large healthcare datasets. Specific areas of his technical interest include comprehensibility of classifiers, stability of feature selection algorithms, meta-learning and longitudinal rule discovery. His work was published in multiple conferences, journals and book chapters. Gregor gave talks on different topics from his knowledge discovery in healthcare and bioinformatics research at renowned research institutions such as IBM Watson Research Center, Stanford University and University of Tokyo. He currently serves as the Program Chair of the IEEE International Conference on Healthcare Informatics (ICHI) 2016 conference and as chair of the Data Mining for Medicine and Healthcare (DMMH) 2016 workshop