Applying a Fuzzy Temporal Constraint System to medical diagnoses

In this paper we present the application of a Fuzzy Temporal Constraint System we have developed to the case of Severe Acute Respiratory Syndrome (SARS). The idea is to schedule the temporal evolutions of symptoms which characterize this ill-known disease by modelling them in a Temporal Constraint Network and then to check their consistency w.r.t patients’ data. In particular, we show how handling both fuzzy qualitative and metric constraints allows us to represent in a flexible way the symptoms in different patients thus making possible to deduce characteristic periods of an unknown disease such as SARS was. A new user interface is proposed for the system.