Section: Application Domains
The Kasimir Project
Participants : Fadi Badra, Julien Cojan, Jean Lieber, Thomas Meilender, Amedeo Napoli.
The Kasimir research project holds on decision support and knowledge management for the treatment of cancer [83] . This is a multidisciplinary research project in which participate researchers in computer science (Orpailleur), experts in oncology (“Centre Alexis Vautrin” in Vandœuvre-lès-Nancy), Oncolor (a healthcare network in Lorraine involved in oncology), and Hermès (an association for the sharing of resources in informatics for medicine). For a given cancer localization, a treatment is based on a protocol similar to a medical guideline, and is built according to evidence-based medicine principles. For most of the cases (about 70% ), a straightforward application of the protocol is sufficient and provides a solution, i.e. a treatment, that can be directly reused. A case out of the 30% remaining cases is “out of the protocol”, meaning that either the protocol does not provide a treatment for this case, or the proposed solution raises difficulties, e.g. contraindication, treatment impossibility, etc. For a case “out of the protocol”, oncologists try to adapt the protocol. Actually, considering the complex case of breast cancer, oncologists discuss such a case during the so-called “breast cancer therapeutic decision meetings”, including experts of all specialties in breast oncology, e.g. chemotherapy, radiotherapy, and surgery. In addition, protocol adaptations are studied from the ergonomics and computer science viewpoints. These adaptations can be used to propose evolutions of the protocol based on a confrontation with actual cases. The idea is then to make suggestions for protocol evolutions based on frequently performed adaptations.
Adaptation plays a central role in knowledge-intensive CBR, where a target problem is solved by adapting the solution of a source case. The adaptation process is based on adaptation knowledge that –for the main part– is domain-dependent, and thus needs to be acquired for a new application of CBR. While the acquisition of ontologies is one important issue that is widely explored in the semantic web community, the acquisition of decision and adaptation knowledge has not been so deeply explored, though this kind of knowledge can be useful in numerous situations. Accordingly, this is the goal of adaptation knowledge acquisition (AKA) to mine a case base, to extract adaptation knowledge units, and to make these units operational. The AKA process is aimed at feeding a knowledge server embedded in the Kasimir semantic portal, that includes an OWL-based formalisms for representing medical ontologies, decision protocols (the case base), and adaptation knowledge [75] . Web services associated to the CBR process are developed, and several protocols are implemented.
