ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 1. Vol. 26. 2020

DOI: 10.17587/it.26.46-55

Y. E. Lvovich, DSc., Professor, e-mail: office@vivt.ru, Voronezh Institute of High Technologies, Russian Federation, 394043, Voronezh, I. L. Kashirina, DSc., Professor, e-mail: kash.irina@mail.ru, M. V. Demchenko, Post-Graduate Student, e-mail: masha-vrn@yandex.ru, Voronezh State University Russian Federation, 394036, Voronezh

The Use of Machine Learning Methods to Study Markers of Atherosclerosis of the Great Arteries

This study is devoted to the deep investigation of the main atherosclerosis markers and their predictors using the different machine learning methods. The main goal of the investigation is to find the most efficient markers and predictors, which would allow to identify the presence of this disease with the high accuracy. The dataset under consideration is based on the real patients characteristics, including blood pressure values, clinical, anthropometrical and social features. Such methods as classification trees, multilayered neural networks and Kohonen maps are used for solving the considered problem of binary classification. Accuracy, precision, recall (sensitivity) and true negative rate (specifity) are the main metrics, which are used to evaluate the quality of the resulting classification models. Classification trees method allowed not only to generate the most interpretable models, but also to order the main predictors by their importance, and the most important predictors were then passed as inputs to the multilayered neural networks. The base backpropagation algorithm, used by default for learning the network, has been modified to use the misclassification costs, which allowed to increase the quality of the classification for the unbalanced dataset. In order to show the common rules found in the dataset, the Kohonen maps were build for each of the main atherosclerosis markers. All the developed classification models can be considered as instruments of the non-invasive atherosclerosis diagnostics.
Keywords: machine learning, neural networks, multilayered perceptron, classification trees, Kohonen maps, atherosclerosis, binary classification, medical diagnostics, sensitivity, specifity

P. 46–55

To the contents