I work at the Information Systems Group of the School of Industrial Engineering of Eindhoven University of Technology. My research is on fuzzy modeling, decision making and computational intelligence methods for advanced decision support. Currently, I am interested in applying these techniques for business process intelligence in the healthcare. In the past, I have shown the added value of these methods in supply chains, finance and logistics. I am part of the Healthcare and Business Process Intelligence research clusters of our group.
Current research interests
- Fuzzy set based decision models and decision support.
- Healthcare process intelligence.
- Health(care) decision support.
Prizes and nominations
- Honorable mention for conference best student paper award (co-author of R.J. Almeida), 2012 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, March 2012.
- Nominated for conference best paper award, 14th Belgium-Netherlands Conference on Artificial Intelligence, October 2002.
- Nominated for conference best paper award, 12th Belgium-Netherlands Conference on Artificial Intelligence, November 2000.
- Mention in CoIL Challenge 2000 International Competition on Data Mining.
- Member of Editorial Board, Soft Computing (2009–).
- Member of Editorial Board, Fuzzy Sets and Systems (2007–).
- Associate Editor, Advances in Fuzzy Systems (2007–).
- Associate Editor, International Journal of Engineering and Management (2007–).
- Guest Editor, IEEE Transactions on Systems, Man and Cybernetics: Part B – Cybernetics, Special issue on cognitive and smart adaptation in computer–communication networks (December 2006).
- Associate Editor, IEEE Transactions on Fuzzy Systems (2002–2007,2010,2012).
Current research topics
In the past, it was believed that the outcome of care delivery depends exclusively on the experience and good judgment of the clinician, the patient characteristics and the properties of the specific illness or disease. In recent years, there is a growing awareness that the medical outcomes are influenced strongly by the design of the total system in which care is delivered. In the age of computer-assisted operations, the design of care delivery systems can be improved significantly by providing meaningful process intelligence support. This can be achieved by integrating all available types of information into decision procedures.
In this research, we develop new methods for risk monitoring of intensive care patients based on a multitude of information sources, such as measurements of vital signs, lab results, nurses’ notes and other medical information. Computational intelligence and machine learning methods are used for identifying models for continuous-time risk indices. The goal is to provide evidence for the use and integration of these methods into clinical practice. In a second project, process mining methods are applied on clinical data in order to determine the actual processes that anesthetists use during a well-defined type of operation. The contribution here is partly methodological, for extending process mining methods to deal with clinical data, and partly practical to link process variation to the variability of medical outcomes. ;