Hervé Chaudet1. 1. Laboratoire d'Informatique Fondamentale, UMR CNRS 6166, Université de la Méditerranée, Faculté de Médecine, 27 bd Jean Moulin, 13385 Marseille Cedex 5, France. herve.chaudet@medecine.univ-mrs.fr
Abstract
OBJECTIVE: The email reporting system has been recognized as a key tool for early warning of disease outbreaks and surveillance of emerging diseases. The aim of the work reported here was to develop a formal language for building an event-centered representation of outbreak histories, described by outbreak reports, which could be used for tracking the spread of epidemics. METHODS: The SpatioTemporal Extended Event Language (STEEL) we have built is an extension of the Event Calculus that is based on joint spatial and temporal location of event occurrences and structured conglomeration of events. This language allows us to represent and build aggregates of events, according to their spatiotemporal location. MATERIAL AND RESULTS: In a proof of concept study, this language was implemented in Prolog. A trial corpus of 35 outbreak reports from a PROMED-Mail diffusion list was hand coded in an experimental implementation of STEEL. The performances of this language were compared with three human experts during a question and answer task on this corpus. The experiment showed agreement between responses of the experts and the system. CONCLUSION: STEEL ensures the spatial and temporal location of event occurrence. The resulting representation is very close to the narrative. Further work must be made to develop a system capable of automatically modeling outbreak reports.
OBJECTIVE: The email reporting system has been recognized as a key tool for early warning of disease outbreaks and surveillance of emerging diseases. The aim of the work reported here was to develop a formal language for building an event-centered representation of outbreak histories, described by outbreak reports, which could be used for tracking the spread of epidemics. METHODS: The SpatioTemporal Extended Event Language (STEEL) we have built is an extension of the Event Calculus that is based on joint spatial and temporal location of event occurrences and structured conglomeration of events. This language allows us to represent and build aggregates of events, according to their spatiotemporal location. MATERIAL AND RESULTS: In a proof of concept study, this language was implemented in Prolog. A trial corpus of 35 outbreak reports from a PROMED-Mail diffusion list was hand coded in an experimental implementation of STEEL. The performances of this language were compared with three human experts during a question and answer task on this corpus. The experiment showed agreement between responses of the experts and the system. CONCLUSION: STEEL ensures the spatial and temporal location of event occurrence. The resulting representation is very close to the narrative. Further work must be made to develop a system capable of automatically modeling outbreak reports.