Искусственная нейронная сеть для ранней диагностики сахарного диабета 2 типа

Abstract

The article is devoted to the development of computer systems based on artificial neural network for the early diagnosis of type 2 diabetes by treating the experimental data glycemic oral glucose tolerance test. The problem of classification status diagnostics object in the processing of its clinical data by methods of artificial intelligence. A rationale for the choice of architecture and learning algorithm of artificial neural network to solve the problem of classification. To determine the statistical significance of differences obtained estimates of the probabilities found the exact boundaries of the confidence intervals for them with a predetermined level of confidence.