The textual document set has become an important and rapidly growing information source especially for the health sector. Many efforts are made to cope with medical text explosion and to obtain useful knowledge from it, and also predict diseases and anticipate the cure. Text mining and natural language processing are fast-growing areas of research, with numerous applications in medical, pharmaceutical, and scientific avenues. Text knowledge management oversees the storage, capture, and sharing of knowledge encoded in hospital reports, primarily chronic disease records. The main objective of this article is to present the design of a model to improve Boolean knowledge mapping by knowledge extraction from medical reports dealing with epidemiological surveillance. This model that the authors have developed in this article is conducted in two major phases. The first is the preprocessing phase that produces an index of words which is the vector binary representation in order to generate the categorization model based on the Boolean modeling inspired by the Boolean knowledge management guided by data mining (BKMDM) method. In the second phase, with the data mining techniques, they exploit the vector binary representation to improve and refine the Boolean knowledge mapping of SEMEP. They examine experiment performance of the proposed model and compare it with other results such as tacit and explicit knowledge of SEMEP. Finally, knowledge mapping can be used for decision making by health specialists or can help in research topics for improving the health system.
