The processing of the diagnostic data in a medical information-analytical system using a network of neuro modules with relearning

Abstract

The article describes the automated informational and analytical system of a decision support in neural network diagnosis of diseases. The operation of the system is based on multi-level method of accounting management, analysis, generalization and exchange of experience between hierarchically organized geographically distributed medical centers. The Selecting of necessary settings for relearning of networks is carried out with the participation of a physician and includes learning procedures, modification and filtering parameters used as input for the further learning of local and regional neural network modules. The procedure of relearning the network of adaptive neural network modules is based on information. The developed system allows considering regional factors of diseases and individual characteristics of diagnosed parameters of patients in the diagnosis of diseases.