Open AccessBiomaterial impedance model for medical risk classifiers in in vivo experiments
Author(s) -
А. В. Мирошников,
О. В. Шаталова,
В. В. Жилин
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1801/1/012045
Subject(s) - biomaterial , task (project management) , computer science , artificial intelligence , population , artificial neural network , machine learning , biomedical engineering , pattern recognition (psychology) , engineering , medicine , environmental health , systems engineering
As a result of the study, fundamentally new results were obtained that allow creating intelligent decision support systems for the classification of medical risk. A bioimpedance analysis model has been created based on multifrequency bioimpedance measurement, which allows decomposition of the biomaterial impedance into structural elements. On the basis of the proposed model, descriptors were formed, intended for classifiers executed on trained neural networks. To obtain descriptors, multifrequency sounding of the biomaterial was carried out, on the basis of which Cole’s graphs were constructed. Using iterative algorithms and these graphs, Voit models of biomaterial impedance were obtained. The parameters of these models are used as descriptors for the trained classifiers. In modern healthcare, the task of long-term monitoring of a person’s condition is almost always associated with either his hospitalization, which is unacceptable both for the working-age population and in some cases for sick people, or with the rent of expensive monitoring systems for a period not exceeding, as a rule, 24 x hours, which is not always enough for diagnostic tasks.