Перегляд за Автор "Shpotak, M. O."

Зараз показуємо 1 - 3 з 3
  • Ескіз
    ДокументВідкритий доступ
    Application of k-Nearest Neighbors Method for Drug Concentraiton and Cardiotoxicity Classification Using Extracellular Field Potentials and Reconstructed Action Potentials of Cardiac Cells
    (КПІ ім. Ігоря Сікорського, 2024) Shpotak, M. O.; Ivanushkina, N. H.
    Micro-electrode array (MEA) systems are important for measuring extracellular field potentials (FP) of cardiac cells, which is a crucial step in cardiotoxicity assessment. However, without modification, the MEA system is only capable of recording FPs. This limits the number of parameters for cardiotoxicity assessment only to FP parameters, while the action potential (AP) parameters remain unused. To address this issue the MEA systems are often modified to use electroor optoporation to record the local extracellular APs (LEAPs), which allows to reliably quantify the AP morphology. As an alternative to MEA modification and cell membrane stimulation the AP can be reconstructed mathematically.This study explores how using additional parameters from reconstructed action potentials (RAPs), derived from FPs, can improve the accuracy of k-NN machine learning models for drug concentration and potential cardiotoxicity classification. The k-NN classifier was trained using combinations of FP and RAP parameters. The k-NN models were evaluated using five-fold stratified cross-validation and cross-channel validation. Their performances were compared using error rate, macro precision, macro recall and macro F1 score accuracy metrics. The results indicated that ncorporating RAP parameters into the feature set increased the F1 score of k-NN model for DMSO concentration classification by up to 10.78% compared to the training set with only FP features.
  • Ескіз
    ДокументВідкритий доступ
    Estimation of Multiple Cardiac Cells’ Action Potentials From Extracellular Field Potentials
    (КПІ ім. Ігоря Сікорського, 2023) Shpotak, M. O.; Ivanushkina, N. H.; Ivanko, K. O.; Prokopenko, Y. V.
    Modern biomedical technologies use a combination of microelectrode array (MEA) systems and artificially grown cells to study disease mechanisms and test drug effects. MEA systems measure extracellular field potentials (FPs) of cell cultures or tissues, but they cannot record intracellular action potentials (APs) without some modifications or additional devices, limiting the depth of electrophysiological analysis. One of the possible solutions to the inability of MEA systems to measure APs is to mathematically reconstruct them using recorded FPs. However, accurately reconstructing APs of multiple cells is challenging task, which is complicated by many factors such as the number of cells, synchronicity of their APs, identification of their electrophysiological parameters, and noise. This paper aims to address the mathematical problem of AP synchronicity, asynchronicity and partial synchronicity between multiple cells. In this study, mathematical techniques were employed to derive a system of equations capable of reconstructing the APs of N cells simultaneously, using the FPs recorded with N + 1 electrodes. The equations take into account the number of cells, synchronicity and variation of their APs and specific electrical properties of the cells and the medium. In numerical experiments the equations were applied to reconstruct APs from FPs for cases with different types of synchronicity in noise-free and noisy conditions. The reconstructed APs, when combined with recorded FPs, expand the number of electrophysiological characteristics available for cardiotoxicity assessment in MEA systems.
  • Ескіз
    ДокументВідкритий доступ
    Solving the Inverse Problem of Relationship Between Action Potentials and Field Potentials in Cardiac Cells
    (КПІ ім. Ігоря Сікорського, 2021) Ivanushkina, N. G.; Ivanko, K. O.; Shpotak, M. O.; Prokopenko, Y. V.
    Multiple electrode array (MEA) systems are the instrument platforms being used for cardiac extracellular electrophysiology investigation. Key applications of MEA technology are disease modeling and screening of drug effects. To solve these problems the efforts of many scientists are directed to signal processing and analysis of field potentials (FP) measured with MEA systems. However, it should be noted the complexity of interpretation of MEA information in non-invasive field potentials measurements of cardiac cells compared to invasive action potential (AP) recordings obtained using patch clamp technology. This study is devoted to the mathematical determination of the relationship between the signals of the electrical activity of cardiomyocytes: internal AP and external FP. Derivation of equations for transfer functions between AP and FP is based on field theory. This article provides a solution to the inverse problems of the relationship between AP and FP. Numerical experiments demonstrate the results of the inverse transformation of simulated field potentials signals. To denoise the potentials of the extracellular field of cardiomyocytes, the method combining wavelet transform and processing in eigensubspaces of cardiac cycles is used. The proposed method, based on transfer functions, can be used to determine AP parameters and expand the capabilities of data analysis in MEA systems for diagnosing heart disease and assessing cardiac toxicity during drug development.