Development of Bioimpedance Spectroscopy Technology in Medical Decision Support Systems

Abstract

The purpose of research – development of bioimpedance spectroscopy methods to develop on their basis objective and realistically accessible criteria for assessing the severity and prognosis of diseases, as well as evaluating the effectiveness of treatment methods, developing criteria for the use of conservative therapy options and surgical interventions in severe patients.Methods. The proposed method involves the use of a recurrent modified Voigt model as a biomaterial segment impedance model. For each model of a biomaterial segment, a Cole plot is plotted in a given frequency range. At the stage of determining the parameters of each of the models, a recurrent procedure is performed, which is the solution of systems of nonlinear equations, starting from one link of the Voight model with a subsequent increase in their number at each iteration step, until the value of the approximation error by the Voight model of the Cole experimental plot reaches allowed value.Results. As a result of the study, fundamentally new results have been obtained that allow creating intelligent decision support systems for diagnosing socially significant diseases. A bioimpedance analysis model based on multifrequency bioimpedance measurement has been created, which makes it possible to decompose the biomaterial impedance into structural elements, on the basis of which to determine descriptors for neural network classifiers of medical risk. In the work, an analysis of classifier errors was carried out in classifying the risk of acute destructive pancreatitis, which showed that the maximum value of the quality indicators of various classifier models was 78%, the minimum was 62%, demonstrating close values to the quality indicators of the ultrasound diagnostic method.Conclusion. The use of multifrequency sensing and modified Voight models in neural network classifiers of medical risk makes it possible to build clinical decision support systems for diagnosing socially significant diseases, as well as the ability to improve classification quality indicators and expand the functionality of intelligent medical decision-making systems.