Serhii Volodymyrovych Artiukh

Serhii Volodymyrovych Artiukh

Auto-generated profile, based on publicly available information

Serhii Volodymyrovych Artiukh

Державна установа «Інститут медичної радіології та онкології ім. С.П. Григорʼєва Національної академії медичних наук України», Харків, Україна

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 January 2018 in Scientific Reports
Verified
Journal Article
Open access
PDF file
GOGráinne O’bRien
Gráinne O’bRien
LCLourdes Cruz-Garcia
Lourdes Cruz-Garcia
MMMatthäus Majewski
Matthäus Majewski
JGJakub Grepl
Jakub Grepl
MAMichael Abend
Michael Abend
Christophe BadieChristophe Badie
Christophe Badie
Previous investigations in gene expression changes in blood after radiation exposure have highlighted its potential to provide biomarkers of exposure. Here, FDXR transcriptional changes in blood were investigated in humans undergoing a range of external radiation exposure procedures covering several orders of magnitude (cardiac fluoroscopy, diagnostic computed tomography (CT)) and treatments (total body and local radiotherapy). Moreover, a method was developed to assess the dose to the blood using physical exposure parameters. FDXR expression was significantly up-regulated 24 hr after radiotherapy in most patients and continuously during the fractionated treatment. Significance was reached even after diagnostic CT 2 hours post-exposure. We further showed that no significant differences in expression were found between ex vivo and in vivo samples from the same patients. Moreover, potential confounding factors such as gender, infection status and anti-oxidants only affect moderately FDXR transcription. Finally, we provided a first in vivo dose-response showing dose-dependency even for very low doses or partial body exposure showing good correlation between physically and biologically assessed doses. In conclusion, we report the remarkable responsiveness of FDXR to ionising radiation at the transcriptional level which, when measured in the right time window, provides accurate in vivo dose estimates.

26 May 2022 in Cancers
Verified
Journal Article
Open access
PDF file
LCLourdes Cruz-Garcia
Lourdes Cruz-Garcia
FNFarah Nasser
Farah Nasser
GOGrainne O’brien
Grainne O’brien
JGJakub Grepl
Jakub Grepl
VVVolodymyr Vinnikov
Volodymyr Vinnikov
Christophe BadieChristophe Badie
Christophe Badie
External beam radiation therapy leads to cellular activation of the DNA damage response (DDR). DNA double-strand breaks (DSBs) activate the ATM/CHEK2/p53 pathway, inducing the transcription of stress genes. The dynamic nature of this transcriptional response has not been directly observed in vivo in humans. In this study we monitored the messenger RNA transcript abundances of nine DNA damage-responsive genes (CDKN1A, GADD45, CCNG1, FDXR, DDB2, MDM2, PHPT1, SESN1, and PUMA), eight of them regulated by p53 in circulating blood leukocytes at different time points (2, 6–8, 16–18, and 24 h) in cancer patients (lung, neck, brain, and pelvis) undergoing radiotherapy. We discovered that, although the calculated mean physical dose to the blood was very low (0.038–0.169 Gy), an upregulation of Ferredoxin reductase (FDXR) gene transcription was detectable 2 h after exposure and was dose dependent from the lowest irradiated percentage of the body (3.5% whole brain) to the highest, (up to 19.4%, pelvic zone) reaching a peak at 6–8 h. The radiation response of the other genes was not strong enough after such low doses to provide meaningful information. Following multiple fractions, the expression level increased further and was still significantly up-regulated by the end of the treatment. Moreover, we compared FDXR transcriptional responses to ionizing radiation (IR) in vivo with healthy donors’ blood cells exposed ex vivo and found a good correlation in the kinetics of expression from the 8-hours time-point onward, suggesting that a molecular transcriptional regulation mechanism yet to be identified is involved. To conclude, we provided the first in vivo human report of IR-induced gene transcription temporal response of a panel of p53-dependant genes. FDXR was demonstrated to be the most responsive gene, able to reliably inform on the low doses following partial body irradiation of the patients, and providing an expression pattern corresponding to the % of body exposed. An extended study would provide individual biological dosimetry information and may reveal inter-individual variability to predict radiotherapy-associated adverse health outcomes.

23 February 2022 in RADIOELECTRONIC AND COMPUTER SYSTEMS
Verified
Journal Article
Closed access
PDF file
VSViktoriia Strilets
Viktoriia Strilets
VDVolodymyr Donets
Volodymyr Donets
MUMykhaylo Ugryumov
Mykhaylo Ugryumov
SASergii Artiuch
Sergii Artiuch
RZRoman Zelenskyi
Roman Zelenskyi
TGTamara Goncharova
Tamara Goncharova
Medical data processing is one of the priority machine learning areas. Usually, data obtained in the process of medical patient monitoring are complex and have a different nature. Solving the problem of clustering, classification, or forecasting problem these data requires the creation of new methods or improvement of existing methods to improve the decision accuracy and effectiveness. The classical clustering approaches and the c-means fuzzy clustering method were analyzed. Based on the multiagent systems theory, it is proposed to use in the c-means method the separate rules for selecting elites when forming clusters and selecting the best of them in accordance with the chosen intra-cluster distance measures. The result of solving such a problem is the number of clusters, as well as the number of elements in them. The method quality was tested on Fisher iris data set using three measures of intra-cluster distance: Mahalanobis distance, Mahalanobis distance considering the membership function, and Kullbak-Leibler entropy. The highest accuracy of 98% was obtained for the distance measured by the Kullbak-Leibler entropy. Therefore, this measure was chosen to solve the clustering problem of medical monitoring data for prostate disease. Medical monitoring data were divided into four classes of patient states: “healthy persons”, “non-metastatic patients”, “metastatic patients” and “hormone-resistant patients”. The accuracy of clustering according to medical data was 95,6%. In addition to accuracy, the confusion matrix, ROC- and LF-curves were used to assess the method quality. The minimum value of the ROC-curve was 0.96 for Fisher's irises and 0.95 for medical monitoring data, which characterizes the high quality of the proposed clustering method. The loss function value is also quite small (-0.056 and -0.0176 for each considered data set), which means that the optimal cluster number and the distribution of data over them are obtained. Based on the obtained results analysis, the proposed method can be recommended for use in medical information and diagnostic decision support systems for clustering monitoring data.

30 March 2023 in Innovative technologies and scientific solutions for industries
Verified
Journal Article
Open access
PDF file
DSDmytro Shevchenko
Dmytro Shevchenko
MUMykhaylo Ugryumov
Mykhaylo Ugryumov
SASergii Artiukh
Sergii Artiukh
The subject matter of the article is models, methods and information technologies of monitoring data aggregation. The goal of the article is to determine the best deep learning model for reducing the dimensionality of dynamic systems monitoring data. The following tasks were solved: analysis of existing dimensionality reduction approaches, description of the general architecture of vanilla and variational autoencoders, development of their architecture, development of software for training and testing of autoencoders, conducting research on the performance quality of autoencoders for the problem of dimensionality reduction. The following models and methods were used: data processing and preparation, data dimensionality reduction. The software was developed using the Python language. Scikit-learn, Pandas, PyTorch, NumPy, argparse and others were used as auxiliary libraries. Obtained results: the work presents a classification of models and methods for dimensionality reduction, general reviews of vanilla and variational autoencoders, which include a description of the models, their properties, loss functions and their application to the problem of dimensionality reduction. Custom autoencoder architectures were also created, including visual representations of the autoencoder architecture and descriptions of each component. The software for training and testing autoencoders was developed, the dynamic system monitoring data set, and the steps for pre-training the data set were described. The metric for evaluating the quality of models is also described; the configuration of autoencoders and their training are considered. Conclusions: The vanilla autoencoder recovers the data much better than the variational one. Looking at the fact that the architectures of the autoencoders are the same, except for the peculiarities of the autoencoders, it can be noted that a vanilla autoencoder compresses data better by keeping more useful variables for later recovery from the bottleneck. Additionally, by training on different bottleneck sizes, you can determine the size at which the data is recovered best, which means that the most important variables are preserved. Looking at the results in general, the autoencoders work effectively for the dimensionality reduction task and the data recovery quality metric shows that they recover the data well with an error of 3–4 digits after 0. In conclusion, the vanilla autoencoder is the best deep learning model for aggregating monitoring data of dynamic systems.

25 September 2020 in Український радіологічний та онкологічний журнал
Verified
Journal Article
Open access
PDF file
OKO. O. Kyrylova
O. O. Kyrylova
ВСВ. П. Старенький
В. П. Старенький
SAS. V. Artiukh
S. V. Artiukh
NPN. E. Prokhach
N. E. Prokhach
TKT. H. Kiian
T. H. Kiian
Background. Being diagnosed with cancer is a dramatically stressful condition for a human. Radiation therapy (RT), which is an essential of combination antineoplastic treatment, can cause physical and emotional state changes. Realizing these changes is an additional stress factor that results in impaired life quality of a cancer patient as well refusal to undergo further treatment. At present, there is no distinct system of providing psychological aid for cancer patients in Ukraine. Purpose. To carry out analysis and generalization of research literature data in terms of providing psychological aid for cancer patients at RT stage and to present own findings of psychological study enrolling 55 female patients diagnosed with endometrial cancer at RT stage at SO «Grigoriev Institute for Medical Radiology and Oncology» within the period from 2015 to 2018. Materials and methods. The literature review involved available contributions obtained via literature search in domestic (Vernadsky National Library of Ukraine) and foreign databases (Scopus, Web of Science Core Collection, PubMed, BMC, ScienceDirect, Wiley Online Library, RNB). Fifty-five patients with endometrial cancer of stage I–II (T1b-c N0 M0 – T2a -b N0 M0) underwent clinical and laboratory examination. The diagnosis of adenocarcinoma was confirmed by means of a histologic study. All patients underwent panhysterectomy and postsurgery course of distant gamma-therapy on “РОКУС-АМ” device by split fractionation. Fifteen patients were provided with psychological correction at RT stage. In order to assess life quality, SF-36 (Health Status Survey) was used. An assessment of the severity of psychosomatic disorders in patients with endometrial cancer was made by means of EORTC QLQ-C30 survey. Results. The paper analyzes psychological aid provided to oncology patients at radiation therapy stage in Ukraine and overseas. It presents the peculiarities of patients’ psychological responses during irradiation and possible consequences of higher mental function impairment. The targets of psychological correction and factors influencing life quality of a patient have been considered as well as the effectiveness of psychotherapeutic interventions outcomes of different approaches has been provided. The study states that, currently, medical and psychological follow-up of cancer patients does not consist only in reassuring talk and drug correcting of their psychological state aimed to reduce distress, anxiety and depression level, but also in psychocorrection, psychoeducation, the access to psychotherapeutic groups, individual psychotherapy. The efficiency of applying own developed schemes of medical and psychological correction of emotional state of women with EC is presented, the use of which has made it possible to reduce the manifestations of sleep disorders, cognitive function and fatigue. Conclusions. Following a differentiated strategy when choosing methods of psychological aid for oncology patients and their families at radiation therapy stage via psychocorrection of emotional, cognitive and behavioral spheres, psychoeducation or psychotherapeutic interventions will make it possible to significantly improve their psychological status and quality of life.

30 September 2024 in Український радіологічний та онкологічний журнал
Verified
Journal Article
Open access
PDF file
VSV.P. Starenkyі
V.P. Starenkyі
LАL.Y. Аnishchenkо
L.Y. Аnishchenkо
LPL.а. Pisnia
L.а. Pisnia
ICI.YU. Chernіavskіy
I.YU. Chernіavskіy
SAS.V. Artiukh
S.V. Artiukh
Background. In emergency situations of a military nature, medical institutions at all levels, especially specialized (radiological) medical facilities, are tasked with providing qualified assistance to the affected population. The effectiveness of these measures depends not only on the promptness, equipment, and training of operational teams but also on adherence to radiation safety standards, which differ from peacetime norms in terms of the scale of combined radiation injuries, injury criteria, and the methods of implementing measures. At the same time, against the backdrop of the multi-criteria uncertainty of possible radiological scenarios, there is no scientific justification for the necessary connections between the features of radiation safety and specific organizational and technical tasks within the system of overall readiness of medical institutions. Purpose – scientifically justify the potential readiness of a medical institution to act during a special period to provide qualified assistance to the population with combined radiation injuries, based on a systematic analysis of the features of the radiation safety system during military emergencies. Materials and Methods. In this paper, an attempt is made to assess the readiness of a medical and preventive institution to take action in emergency situations of a military nature by applying the method of analysis of hierarchies by T. Saati, adapted for the relevant tasks. Results. The conducted analysis of generalized weight coefficients and priorities in percentages (%) for each element of the hierarchical structure (Fig. 3) shows that more than 50% of «actions» are related to the effective provision of personnel safety and the effective delivery of medical care («Dia-1» and «Dia-2»). These components should receive key attention in the practical training of healthcare facility personnel and involved individuals through special training for emergency actions during special periods. Conclusions. This work attempts to assess the readiness of a medical institution to act in military emergencies by applying the Analytic Hierarchy Process (AHP) method by T. Saaty, adapted for the relevant tasks.