TEMPORAL REASONING AND TEMPORAL DATA MAINTENANCE IN MEDICINE - ISSUESAND CHALLENGES

We present a brief, nonexhaustive overview of research efforts in desi gning and developing time-oriented systems in medicine. The growing vo lume of research on time-oriented systems in medicine can be viewed fr om either an application point of view focusing on different generic t asks (e.g. diagnosis) and clinical areas (e.g. cardiology), or from a methodological point of view, distinguishing between different theoret ical approaches. In this overview, we focus on highlighting methodolog ical and theoretical choices, and conclude with suggestions for new re search directions. Two main research directions can be noted: temporal reasoning, which supports various temporal inference tasks (e.g. temp oral abstraction, time-oriented decision support, forecasting, data va lidation), and temporal data maintenance, which deals with storage and retrieval of data that have heterogeneous temporal dimensions. Effort s common to both research areas include the modeling of time, of tempo ral entities, and of temporal queries. We suggest that tasks such as a bstraction of time-oriented data and the handling of different tempora l-granularity levels should provide common ground for collaboration be tween the two research directions and fruitful areas for future resear ch. (C) 1997 Elsevier Science Ltd.