A general procedure for natural language generation is described. The symbolic processing of monitored parameters is accomplished by comparing their numerical values with ranges established on the basis of specific initial conditions and associated with appropriate literals. The model described provides a systematic procedure for the symbolic classification of variables using a conceptually well-defined semantic set, which is absolutely adaptable to the particular characteristics of each process under examination. The model has been developed to represent realistically the problem of intensive care monitoring. Its application in this environment could provide the elements of analysis necessary for the development of an expert system that would, in turn, allow the establishment of systematic intelligent monitoring.<<ETX>>
[1]
R M Gardner,et al.
Computerized data management and decision making in critical care.
,
1985,
The Surgical clinics of North America.
[2]
Janos Sztipanovits,et al.
Model based approach in intelligent patient monitoring
,
1988,
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society.
[3]
Lawrence M. Fagan,et al.
Representation of Dynamic Clinical Knowledge: Measurement Interpretation in the Intensive Care Unit
,
1979,
IJCAI.
[4]
V. Moret-Bonillo,et al.
ESTER: an expert system for management of respiratory weaning therapy
,
1989,
IEEE Transactions on Biomedical Engineering.