| | |
Summary: Towards an Introspective Architecture for
Meta-level Reasoning in Clinical Decision
Support Systems
Tor Gunnar Houeland and Agnar Aamodt
Department of Computer and Information Science,
Norwegian University of Science and Technology,
NO-7491 Trondheim, Norway
{houeland,agnar}@idi.ntnu.no
Abstract. The paper presents core elements of a meta-level architecture
for clinical decision support, in the domain of palliative care. The goal of
the reported research is to develop an architecture and an integrated set
of methods for an introspective meta-level reasoner. Within the archi-
tecture a system is under development that addresses the identification
and utilization of clinical guidelines for the assessment and treatment of
cancer pain. Case-based reasoning is a core component of the architec-
ture, which also incorporates rule-based and probabilistic model-based
methods. The paper presents the overall architectural constraints and
exemplifies parts of it through structured component descriptions.
1 Introduction
A clinical decision support system that covers several clinical tasks, such as
|
