A TEMPORAL-ABSTRACTION MEDIATOR FOR PROTOCOL-BASED DECISION-SUPPORT SYSTEMS

The inability of many clinical decision-support applications to integr ate with existing databases limits the wide-scale deployment of such s ystems. To overcome this obstacle, we have designed a data-interpretat ion module that can be embedded in a general architecture for protocol -based reasoning and that can support the fundamental task of detectin g temporal abstractions. We have developed this software module by cou pling two existing systems - RESUME and Chronus - that provide complem entary temporal-abstraction techniques at the application and the data base levels, respectively. Their encapsulation into a single module th us can resolve the temporal queries of protocol planners with the doma in-specific knowledge needed for the temporal-abstraction task and wit h primary time-stamped data stored in autonomous clinical databases. W e show that other computer methods for the detection of temporal abstr actions do not scale up to the data- and knowledge-intensive environme nts of protocol-based decision-support systems.