Dr. Mark Hoogendoorn

Mark Hoogendoorn is an Assistant Professor of Artificial Intelligence within the Computational Intelligence group of the Department of Computer Science at the VU University Amsterdam.

His research is positioned on the boundary between Machine Learning and the domain of Health and Wellbeing. His research interests include predictive modeling for diseases, personalized therapies and support systems, collectives of intelligent sensory and support devices, eHealth, and mHealth and the fundamental Machine Learning techniques that underpin these topics. For a list of his publications, click here.

Mark Hoogendoorn is currently a member of the Board of Directors of ISRII and chair the Special Interest Group on Data Standards and Sharing in the same organization. In addition, he is a member of the Triple-E E-Health network, Amsterdam Data Science, the Network Institute, and the Amsterdam Center for Business Analytics. He has been a Visiting Scientist within the Clinical Decision Making Group headed by Peter Szolovits at MIT (CSAIL) during the Summer of 2015 and a PostDoc at the Department of Computer Science and Engineering at the University of Minnesota in the group of Maria Gini (Fall 2007). Before 2012 he was part of the Agent Systems Group at the VU. He obtained his PhD degree in 2007 from the VU University Amsterdam as well.

He is currently involved in various research projects:

  • E-COMPARED (FP7 Health project) The project concerns the comparison of the effectiveness of therapies for depression and is a close collaboration between researchers from the domain of psychology (among which the psychologists of the Department of Clinical Psychology of the VU University Amsterdam) and computer science. The main focus within the project for us is the generation of predictive models for patients to enable more effective policy making. The project uses an automated mobile therapy developed in the EU FP7 funded ICT project ICT4Depression, a project he jointly coordinated with Michel Klein.
  • Data-Driven Lifestyle Support through Smart Devices In this project the aim is to develop approaches that enable more personalized forms of support for a healthy lifestyle. Hereto we focus on data collected via various smart devices which we use to create highly personalized interventions. In addition, we intend to derive different sets of users with similar preferences. The project is part of a large AAA Data Science project and is a collaboration with Philips Research.
  • Personalized smart health apps This project aims to develop techniques to learn to provide feedback and support to users in an effective way by means of health apps on their smart phone. The main focus is on reinforcement learning techniques that adapt to the user to provide the right interventions and feedback at the best moments in a context dependent manner and learn to do this as fast as possible. This project is funded by Mobiquity Inc.
  • Constrained personalization of smart health apps When personalization of apps on smart phones takes place automatically it is possible that certain undesired behavior is shown, e.g. inappropriate feedback or suggestions for interventions. This could be harmful for users which needs to be avoided. In this project, we aim to develop techniques to personalize within certain boundaries. We also consider this from a software architecture perspective and also study the consequences for the users. This project is a collaboration with the Software and Services Group of the VU (Patricia Lago and Ivano Malavolta).
  • Predictive modeling and outlier detection for large datasets A joint project with the Ministry of the Interior, the Department of Mathematics of the VU (Sandjai Bhulai), and the Center for Mathematics and Computer Science (Rob van der Mei).

Past projects include the aforementioned ICT4Depression project, a project on Prediction of Colorectal Cancer (joint with various University Medical Centers and Annette ten Teije at the VU), a modular robotics project called Symbrionand two coordination actions called FOCAS (FP7 ICT Coordination action) and AWARE. He is also involved in teaching several courses related to Artificial Intelligence and Computational Intelligence. In addition, he is the Master-coordinator for the various Artificial Intelligence programs and a member of the Examination Board of the Faculty of Sciences.

Role
Assistant professor
Domain
Artificial intelligence
Computer Science
Specialism
Life Sciences
Machine Learning
Application Area
General
Health care

Mark Hoogendoorn
Contact information

E: m.hoogendoorn@vu.nl