A TEMPORAL ANALYSIS OF QMR - ABSTRACTED TEMPORAL REPRESENTATION AND REASONING AND INITIAL ASSESSMENT OF DIAGNOSTIC PERFORMANCE TRADE-OFFS

Explicit temporal representation and reasoning (TRR) in medical decisi on-support systems (MDSS) is generally considered to be a useful but o ften neglected aspect of system design and implementation. Given the g reat burden of explicit TRR both in knowledge acquisition and computat ional efficiency, developers of general-purpose large-scale systems ty pically utilize implicit (i.e., abstracted) forms of TRR. We are inter ested in understanding better the trade-offs of not incorporating expl icit TRR in large general-purpose MDSS along the dimensions of system expressive power and diagnostic accuracy. In particular, we examine th e types of abstracted TRR employed in QMR, a diagnostic system in the domain of general internal medicine, and the high-level effects of suc h an implicit treatment of time in the system's diagnostic performance . We present our findings and discuss implications for MDSS design and implementation practices.