Abstract
CBR is a reasoning paradigm that instead of relying on general rules or models chooses the specific knowledge contained into already solved instances of problems. The quality of case-based reasoning method depends primarily on a good representation of cases in the retrieve step and the richness of knowledge base. The basis for using the case-based reasoning process is to support the formalization of reasoning procedures for collaborative medical acts. We proposed an approach is to help resolving the difficulty of determining the best treatment for the disease and to get best practices. This research describes a model for knowledge engineering using the taxonomic reasoning of ontology modeling and semantic similarity to . In addition to being a valuable support in the procedure of medical decision making, this model can be used to strengthen significant collaborations and traceability that are important for the development of proper deployment of medical applications. Adequate mechanisms for information management with traceability of the reasoning are also essential in the fields of epidemiology and public health. The proposed approach is illustrated with an example from the Breast Cancer. The proposed approach consists of a knowledge base (ontology and instances) and several modules such as querying, reasoning, diagnosing, and recommending treatments. We made a primary evaluation to evaluate the diagnosing accuracy by entering information about a number of persons infected with Breast Cancer disease and evaluate the results. Also, we evaluate the recommending treatments according to a human expert oncology by comparing his recommended treatments of a patient with a doctor’s prescription who treated that patient, then with the approach recommendations to that patient. The approach achieved a rate of accuracy in the results of diagnosing the Breast Cancer disease of 86%, a rate of accuracy in the results of the recommending treatments of 75%.
Type