SCENARIO RECOGNITION FOR TEMPORAL REASONING IN MEDICAL DOMAINS

The recognition of high level clinical scenes is fundamental in patien t monitoring. In this paper, we propose a technique for recognizing a session, i.e. the clinical process evolution, by comparison against a predetermined set of scenarios, i.e. the possible behaviors for this p rocess. We use temporal constraint networks to represent both scenario and session. Specific operations on networks are then applied to perf orm the recognition task. An index of temporal proximity is introduced to quantify the degree of matching between two temporal networks in o rder to select the best scenario fitting a session. We explore the app lication of our technique, implemented in the Deja Vu system, to the r ecognition of typical medical scenarios with both precise and imprecis e temporal information. (C) 1998 Elsevier Science B.V. All rights rese rved.