יובל שחר

The inability of many clinical decision-support systems to integrate with legacy databases limits the widescale deployment of such systems. To overcome this obstacle, we have designed a general data-interpretation module that can be embedded in a comprehensive architecture for protocol-based reasoning and that can support the fundamental task of detecting temporal abstractions. We have developed this software module by coupling two existing systems, RESUME an d Chronus. These two systems provide complementary temporalabstraction techniques at the application and the database levels; their encapsulation into a mediator system can, consequently, resolve the temporal-abstraction queries of protocol planners with domain-specific knowledge for the temporal-abstraction task and primary data stored in clinical databases. We show that other temporal-abstraction methods do not scale up to the data- and knowledgeintensive environments of protocol-based decision-support systems.