Abstract
The aim of the study is to improve the quality of prediction and early diagnosis of community-acquired pneumonia based on methods and models of intellectual support for the analysis of the synchrony of systemic rhythms, extracted from cardiac signals and signals of the electrical activity of the respiratory muscles. Theoretical issues of prediction and early diagnosis of community-acquired pneumonia based on the analysis of systemic rhythms and their synchronicity parameters have been studied. For this, hierarchical systems of intelligent agents were used, the inputs of which are descriptors obtained from the analysis of the cardiovascular system, the respiratory system, as well as descriptors characterizing the synchronism of systemic rhythms in these systems. As a result of the study, a hybrid classifier was developed to determine the individual risk of community-acquired pneumonia, an automated system was developed to determine descriptors for intelligent agents included in the classifier, and experimental studies were carried out to predict the risk of community-acquired pneumonia using the developed automated complex.