Formal System Development with KIV
FASE '00 Proceedings of the Third Internationsl Conference on Fundamental Approaches to Software Engineering: Held as Part of the European Joint Conferences on the Theory and Practice of Software, ETAPS 2000
Plan management in the medical domain
AI Communications
Combining task execution and background knowledge for the verification of medical guidelines
Knowledge-Based Systems
Verification of Medical Guidelines Using Background Knowledge in Task Networks
IEEE Transactions on Knowledge and Data Engineering
Checking the quality of clinical guidelines using automated reasoning tools
Theory and Practice of Logic Programming
Verification of Medical Guidelines using Task Execution with Background Knowledge
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Improving medical protocols by formal methods
Artificial Intelligence in Medicine
Authoring and verification of clinical guidelines: A model driven approach
Journal of Biomedical Informatics
| Hi-index | 0.00 |
We report our experience in a case study with constructing fully formalised knowledge models of realistic, specialised medical knowledge. We have taken a medical protocol in daily use by medical specialists, modelled this knowledge in a specific-purpose knowledge representation language, and finally formalised this knowledge representation in terms of temporal logic and parallel programs. The value of this formalisation process is that each successive formalisation step has contributed to improving the quality of the original medical protocol, and that the final formalisation allows us to provide machine-assisted proofs of properties that are satisfied by the original medical protocol (or, alternatively, precise arguments why the original protocol fails to satisfy certain desirable properties). We believe that this the first time that a significant body of medical knowledge (in our case: a protocol for the management of jaundice in newborns) has been formalised to the extent that it becomes amenable to automated theorem proving, and that this has actually lead to improvement of the original body of medical knowledge.