Publications by authors named "S P Shchelykalina"

3 Publications

  • Page 1 of 1

Technology of Two-dimensional Bioimpedance Analysis of the Human Body Composition.

J Electr Bioimpedance 2021 Jan 2;12(1):17-25. Epub 2021 Jul 2.

Department of Analysis of Population Health Statistics, Central Public Health Research Institute of the Ministry of Health of Russia, Moscow, Russia.

The BIA primary result sheets as a rule contain one-dimensional graphical scales with a selected area of normal values. In 1994, Piccoli . proposed BIVA, an alternative form of BIA data presentation, where two bioimpedance parameters are considered simultaneously as tolerance ellipses: resistance and reactance normalized to height. The purpose of this study is to develop an approach to data analysis in body composition bioimpedance research in two-dimensional representations. The data of 1.124.668 patients aged 5 to 85 years who underwent a bioimpedance study in Russian Health Centers from 2009 to 2015 were used. Statistical programming in the R Studio environment was carried out to estimate two-dimensional distribution densities of pairs of body composition parameters for each year of life. The non-Gaussian distribution is found in most parameters of bioimpedance analysis of body composition for most ages (Lilliefors test, p-value << 0.0001). The slices of the actual two-dimensional distribution pairs of body composition parameters had an irregular shape. The authors of the article propose using the actually observed distribution for populations where numerous bioimpedance studies have already been carried out. Such technology can be called two-dimensional bioimpedance analysis of human body composition (2DBIA). The 2DBIA approach is clearer for practitioners and their patients due to the use of body composition parameters in addition to electrical impedance parameters.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
January 2021

[Artificial intelligence for diagnosis of vertebral compression fractures using a morphometric analysis model, based on convolutional neural networks].

Probl Endokrinol (Mosk) 2020 Oct 24;66(5):48-60. Epub 2020 Oct 24.

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies.

Background: Pathological low-energy (LE) vertebral compression fractures (VFs) are common complications of osteoporosis and predictors of subsequent LE fractures. In 84% of cases, VFs are not reported on chest CT (CCT), which calls for the development of an artificial intelligence-based (AI) assistant that would help radiology specialists to improve the diagnosis of osteoporosis complications and prevent new LE fractures.

Aims: To develop an AI model for automated diagnosis of compression fractures of the thoracic spine based on chest CT images.

Materials And Methods: Between September 2019 and May 2020 the authors performed a retrospective sampling study of ССТ images. The 160 of results were selected and anonymized. The data was labeled by seven readers. Using the morphometric analysis, the investigators received the following metric data: ventral, medial and dorsal dimensions. This was followed by a semiquantitative assessment of VFs degree. The data was used to develop the Comprise-G AI mode based on CNN, which subsequently measured the size of the vertebral bodies and then calculates the compression degree. The model was evaluated with the ROC curve analysis and by calculating sensitivity and specificity values.

Results: Formed data consist of 160 patients (a training group - 100 patients; a test group - 60 patients). The total of 2,066 vertebrae was annotated. When detecting Grade 2 and 3 maximum VFs in patients the Comprise-G model demonstrated sensitivity - 90,7%, specificity - 90,7%, AUC ROC - 0.974 on the 5-FOLD cross-validation data of the training dataset; on the test data - sensitivity - 83,2%, specificity - 90,0%, AUC ROC - 0.956; in vertebrae demonstrated sensitivity - 91,5%, specificity - 95,2%, AUC ROC - 0.981 on the cross-validation data; for the test data sensitivity - 79,3%, specificity - 98,7%, AUC ROC - 0.978.

Conclusions: The Comprise-G model demonstrated high diagnostic capabilities in detecting the VFs on CCT images and can be recommended for further validation.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
October 2020

Monitoring of body fluid redistribution using segmental bioimpedance during rotation on a short-radius centrifuge.

Physiol Meas 2020 05 7;41(4):044006. Epub 2020 May 7.

Department of Experimental Physiology, Institute of Biomedical Problems, Russian Academy of Sciences, Moscow, Russia.

Objective: The creation of artificial gravity on board a space station is one of the promising methods for preventing health problems during space missions; a short-radius centrifuge (SRC) is the model of such a method on Earth. Our goal was to evaluate the sensitivity of bioimpedance polysegmental measurements for monitoring of the body regions' blood-filling redistribution and to analyze the dynamics of blood-filling redistribution during rotation in three SRC rotation modes.

Approach: Nine healthy male volunteers have been observed under three SRC rotation modes with a maximum acceleration of 2.05 standard Earth gravity (g), 2.47 g, 2.98 g along the body vertical axis towards the legs with a rotation radius of 235 cm. The 5 kHz electrical resistance was evaluated using a bioimpedance analyzer in a polysegmental mode.

Main Results: Twenty-five correct records were made, of which four records were incomplete since the tests had to be stopped because the subjects were not feeling well. There was a blood-filling decrease in the head region; resistance increased to +15.4% ± 4.1% in the first SRC rotation mode. The electrical resistance of the leg regions decreased to -16.5% ± 2.3%. Slowdown of the SRC led to the reverse changes in resistance. The blood redistribution in the head and leg regions was independent of the mode of SRC rotation during the first 30 min, and varied on average by +10% and -15% respectively.

Significance: Bioimpedance monitoring is promising for detection and prediction of blood circulation changes during rotation on the SRC.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
May 2020