Active trust management for autonomous adaptive survivable systems (ATM's for AAss's)
IWSAS' 2000 Proceedings of the first international workshop on Self-adaptive software
Dynamic temporal interpretation contexts for temporal abstraction
Annals of Mathematics and Artificial Intelligence
Timing Is Everything: Temporal Reasoning and Temporal Data Maintenance in Medicine
AIMDM '99 Proceedings of the Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making
Temporal abstraction in intelligent clinical data analysis: A survey
Artificial Intelligence in Medicine
Automated trend detection with alternate temporal hypotheses
IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 1
Modelling diagnostic skills in the domain of skeletal dysplasias
Computer Methods and Programs in Biomedicine
An epistemology for clinically significant trends
AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
A general framework for time-aware decision support systems
Expert Systems with Applications: An International Journal
BPM' 2012 Proceedings of the 2012 international conference on Process Support and Knowledge Representation in Health Care
Hi-index | 0.00 |
Diseases develop and change over time. Much of the distinction between pathophysiological complexes rests on the temporal relations of their component events. Therefore, knowledge bases that fail to capture the temporal component of the course of disease omit useful diagnostic knowledge. Expert systems that cannot reason with temporal knowledge are impaired in distinguishing between hypotheses and therefore have to explore much larger problem-spaces than would a human or temporally sophisticated expert system. Temporally naive expert systems are also limited in the extent to which they follow human diagnostic style and provide reasonable automated explanations and diagnostic questions. The Temporal Utility Package (TUP) is a domain independent utility that is signed for use with a wide variety of knowledge representations. TUP can represent points, intervals, qualitative and quantitative temporal relations, groups of points, common temporal "yardsticks," and alternate temporal contexts. TUP employs a form of constraint propagation to make temporal inferences. As the inference computation grows rapidly with the number of points, TUP enables temporal deductions to be performed locally by "chunking" the temporal data base. The knowledge structures of the application domain can be used to automatically guide this "chunking" process. Certain aspects of TUP''s performance may be their parallel in human cognition. THRIPHT is a prototype expert system that demonstrates TUP''s application and the role of temporal reasoning in different phases of the diagnostic process: data gathering, hypothesis evocation, elaboration, instantiation, and hypothesis ranking. TUP and THRIPHT together illustrate why temporal reasoning is necessary for successful second generation medical expert systems, and how to provide this capability.