Extensions to the Time-Oriented Database Model to Support Temporal Reasoning in Medical Expert Systems

Reference: Kahn, M. G.; Fagan, L. M.; & Tu, S. Extensions to the Time-Oriented Database Model to Support Temporal Reasoning in Medical Expert Systems. 1991.

Abstract: Physicians faced with diagnostic and therapeutic decisions must reason about clinical features that change over time. Electronic database-management systems (DBMS) can increase access to patient data, but most such systems are limited in their ability to store and retrieve complex temporal information. For example, the skillful analysis of clinical data requires accounting for all concurrent clinical contexts that may alter the interpretation of the raw data. Most medical DMBSs cannot retrieve patient data indexed by a set of specific clinical events. The Time-Oriented Databank (TOD) model, the most widely used data model for medical database systems, simply associates a time stamp with each observation. We describe two extensions to electronic medical databases that were created specifically to solve temporal reasoning problems that we encountered in constructing medical expert systems. A key feature of both extensions is that stored data are partitioned into groupings, such as sequential clinical visits, clinical exacerbations, or other abstract events that have clinical relevance. The temporal network (TNET) is an object- oriented database that extends the temporal reasoning capabilities of ONCOCIN, a medical expert system that provides chemotherapy advice. TNET uses persistent objects to associate intervals of time during which "an event of clinical interest" was occurring with medical observations in a patient's electronic medical record. TNET can capture temporal relationships among recorded information that cannot be represented in TOD-based databases. A second object-oriented system, called the extended temporal network (ETNET), is both an extension and a simplification of TNET. Like TNET, ETNET uses persistent objects to represent relevant intervals; unlike the first system, however, ETNET contains reasoning methods (rules) that can be executed when an event represented by an object "begins," and that are withdrawn when that event "concludes." Although TNET and ETNET do not solve all temporal reasoning problems found in medical decision making, these new structures enable patient database systems to model complex temporal relationships, to store and retrieve patient data based on clinical context, and, in ETNET, to modify the reasoning methods available to an expert system based on the onset or conclusion of clinical events.

Jump to... [KSL] [SMI] [Reports by Author] [Reports by KSL Number] [Reports by Year]
Send mail to: ksl-info@ksl.stanford.edu to send a message to the maintainer of the KSL Reports.