Ievgen Nastenko

• Professor
• Professor (Associate) at National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

Pacing-induced cardiomyopathy is a notable issue in patients needing permanent ventricular pacing. Identifying risk groups early and swiftly preventing the ailment can reduce patient harm. However, current prognostic methods require clarity. We employed machine learning to develop predictive models using medical data. Three algorithms — decision tr...

Despite its ubiquity, stress can have long-term detrimental effects on an individual's psychophysical well-being. However, stress detection is a complex challenge because each person has unique characteristics and responses. The primary goal is to propose an automated stress

Exploration and analysis of changes in human bio-metrics, such as heart rate and blood pressure associated with exposure to traumatic events is the primary goal of this article. We aimed at answering the questions on whether there is a significant difference in biometrics observed in the peaceful and disaster times. Overall, we developed and tested...

Right ventricular pacing may impair left ventricular systolic function in patients with reduced left ventricular ejection fraction (LVEF). The aim. To determine the frequency of pacing-induced cardiomyopathy (PICM) in patients with permanent right ventricular pacing (at least 90%) and preserved LVEF (≥50%). To determine the risk factors for the occ...

The objective of this research is to predict the level of cognitive load of various degrees, using the physiological measurement from wearables and the subject's psychological and demographic traits. This paper focuses on combining machine learning and machine reasoning techniques that capture joint distributions of both the objective and subjectiv...

The authors propose an approach to the construction of classifiers in the class of Random Forest algorithms. A genetic algorithm is used to determine the optimal combination and composition of ensembles of features in the construction of forest trees. The principles of the group method of data handling are used to optimize the structure of the tree...

The development of information and computational technologies has brought prospects for solving problems of identifying and predicting the state of objects in a wide range of subject areas. Due to the emergence of large data sets, there is a demand for modern computer systems that can efficiently process data in intelligent analysis tasks. One such...

The current study considers the development of a 5-layer pipeline for identifying and classifying COVID-19-induced lung lesions. Such system is multilayer, built upon convolutional and fully connected neural networks and logistic self-organised forest built using the group method of data handling (GMDH) principles. This pipeline includes a mechanis...

The article presents the results of the comparative development of different variants of immunoaffinity sorbents for the purification of human IL-7, namely: Sepharose 6B and sol-gel materials based on tetraethoxysilane (TEOS). The optimal conditions for the synthesis of a chromatographic sorbent based on TEOS, which provide acceptable characteristi...

The given work is devoted to the modern developments in the field of medicine, namely medical image recognition by innovative algorithm called "Genetic-inductive Forest". The main purpose of creating such an algorithm is to improve already existing Machine Learning approaches in order to obtain more efficient results in recognition tasks. To test t...

The paper considers the process of induction heating of the extruder body, the temperature of which determines the degree of heating of the polymer mixture in the zone of loading the dry mixture. A mathematical model of this process is formulated taking into account radiant heat transfer in the gap between the inductor and the case. An iterative nu...

Background. Machine learning allows the application of various intelligent algorithms to produce diagnostic and/or prognostic models. Such models can be used to determine the functional state of the heart, which is diagnosed by speckle-tracking echocardiography. To determine in detail the condition of the patient's heart, a classification approach...

Today, in Ukraine the task of creating an informative system for personalized treatment strategy searching is quite relevant. Its appearance will help to solve the long-burning issue of the absence of clinical pharmacists in medical institutions. These specialists are necessary because doctors cannot make an independent decision regarding the patie...

Проблематика. Туберкульоз – це хронічне захворювання легень, яке виникає через бактеріальну інфекцію та входить до десятки основних причин смертності людини. Як частина системи автоматизованої діагностики виявлення туберкульозних уражень на комп’ютерних томограмах легень у автоматичному режимі є актуальною задачею. Мета. Вирішення проблеми сегмент...

Background. Group method of data handling is a rather underestimated tool for obtaining highly accurate predictive models. The first version of an artificial neural network (which is very popular in the world of machine learning) was obtained in 1965 by the Ukrainian scientist Aleksey Ivakhnenko, who just used the group method of data handling to t...

Background. Recent studies show that cardiovascular diseases, including coronary heart disease, are the leading causes of death and one of the main factors of disability worldwide. The detection of cases of this type of disease over the past 30 years has increased from 271 million to 523 million and the number of deaths – from 12.1 million to 18.6...

The article deals with the new possibilities in the development of diagnostic decision support systems on the example of normal and pathology states separation in diffuse liver diseases based on statistical features of ultrasound image texture. It is proposed to use the difference conversions of the original grayscale matric, which makes the result...

The paper describes principles of feature selection from Grey-Level Co-Occurrence matrix for the liver ultrasound images classification. These principles include the method of weeding out uninformative features which are least different in normal and pathology and forming an ensemble of the best features with the help of a genetic algorithm to spee...

The paper describes principles of forming a texture features’ ensemble for the liver ultrasound images classification. These principles include metrics for assessing the quality of ensemble, as well as the genetic algorithm for quick searching the best ensembles. The resulting ensembles were used to create models obtained by Random Forest Classifie...

Brain tumor is a relatively severe human disease type. Its timely diagnosis and tumor type definition are an actual task in modern medicine. Lately, the segmentation methods on 3D brain images (like computer and magnetic resonance tomography) are used for definition of a certain tumor type. Nevertheless, the segmentation is usually conducted manual...

This article discusses the use of texture analysis methods to obtain informative features that describe the texture of liver ultrasound images. In total, 317 liver ultrasound images were analyzed, which were provided by the Institute of Nuclear Medicine and Radiation Diagnostics of NAMS of Ukraine. The images were taken by three different sensors (...

The article deals with the construction of the norm-pathology states classifiers according to statistical features of the ultrasound images texture in diffuse liver diseases. A number of new features are proposed to distinguish the texture of classes. The classifiers are constructed using the Group Method of Data Handling (GMDH) using GMDH Shell DS...

The conventional approach for calculating individual optimal strategies assumes that the best control actions are determined for the same object that has been studied by monitoring or conducting active trials. However, the class of objects for which is impossible to organize repeated tests is widespread. An example is patients with a particular dis...

The classification problem where each object is given by a set of multidimensional measurements that is associated with an unknown dependence is considered. Intersection of sets that define objects from different classes is allowed. In this case, it is natural to found classification algorithms based on the difference between dependencies for the o...

Проблематика. Задача определения функциональной связи между биофизическими параметрами является составной частью актуальной проблемы поиска оптимального воздействия на биологический объект и в настоящее время не является полностью решенной. Одной из важных задач в этой области является разбиение исходного пространства признаков на такие области (кл...