Title : An Evaluation Framework for the Comparison of Fine-Grained Predictive Models in Health Care
| Presenter | Ward van Breda |
| Abstract | Within the domain of health care, more and more fine-grained models are observed that predict the development of specific health (or disease-related) states over time. This is due to the increased use of sensors, allowing for continuous assessment, leading to a sharp increase of data. These specific models are often much more complex than high-level predictive models that e.g. give a general risk score for a disease. This makes the evaluation of these models far from trivial. In this paper, we present an evaluation framework which is able to score fine-grained temporal models that aim at predicting multiple health states. Hereby, models are evaluated on their capability to describe data, their capability to predict, the quality of the models parameters, and the model complexity. The framework is applied in the domain of mental health, specifically depression, by comparing two predictive models, thereby showing how the framework can be applied. |
Title : A purpose-based framework to detect re-purposing of accessed data
| Presenter | Valerio Di Bernardo |
| Abstract | Nowadays organizations that handle personal data need their IT systems to be compliant with privacy regulations which require personal data to be collected and processed only for specified, lawful and legitimate purposes. However, existing data protection mechanisms are not appropriate to fully comply with this principle: they are able to control who can access which data for which purpose, but not how the data are used once accessed. In this presentation an overview of my master´s thesis project will be presented. The objective of my project is to develop a formal framework which allows a system to verify that data are actually processed in ways that are consistent with the purposes for which data have been collected, thus detecting possible privacy infringements such as re-purposing. |