A.C.M. ten Teije

Knowledge Representation for Health-Care

Process model comparison and similar processes retrieval are key issues to be addressed in many real world situations, and particularly relevant ones in medical applications, where similarity quantification can be exploited to accomplish goals such as conformance checking, local process adaptation analysis, and hospital ranking. In recent years, we have implemented a framework which allows to: (i) extract the actual process model from the available process execution traces, through process mining techniques; and (ii) compare (mined) process models, by relying on a novel distance measure. Our distance measure is knowledge-intensive, in the sense that it explicitly makes use of domain knowledge, and can be properly adapted on the basis of the available knowledge representation formalism. We also exploit all the available mined information (e.g., temporal information about delays between activities). Interestingly, our metric explicitly takes into account complex control flow information too, which is often neglected in the literature. The framework has been successfully tested in stroke management.

Construction of problem-solving methods as parametric design

The knowledge-engineering literature contains a number of approaches for constructing or selecting problem solvers. Some of these approaches are based on indexing and selecting a problem solver from a library, others are based on a knowledge acquisition process, or are based on search-strategies. None of these approaches sees constructing a problem solver as a configuration task that could be solved with an appropriate configuration method. We introduce a representation of the functionality of problem-solving methods that allows us to view the construction of problem solvers as a configuration problem, and specifically as a parametric design problem. From the available methods for parametric design, we use propose-critique-modify for the automated configuration of problem-solving methods. We illustrate this approach by a scenario in a small car domain example.

{Knowledge Representation for Health Care (AIME 2015 International Joint Workshop, KR4HC/ProHealth 2015)

In this keynote presentation, my intent is to explore the evolution of the field of computer-based clinical decision support (CDS) – and its associated tasks of knowledge acquisition, knowledge modeling, knowledge representation, knowledge management, and knowledge integration into care processes – over the past five decades. I believe that we are now in a period of significant disruption – both in the health care system itself and in the technology to support it. As a result of these disruptors, I am convinced that we will need to not only continue the efforts that have proved useful in the past but also to develop some new strategies to meet the new challenges.