Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ruslan Sydorchuk has a total of 694 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Two-centre cohort study of the distal biliary system benign obstructions complicated by cholelithiasis in patients with cardiovascular-kidney-metabolic syndrome

    by O.V. Ivanko, M.M. Stets, V.V. Petrynych, O.O. Zhukovskyi, O.B. Rusak, R.I. Sydorchuk

    Background. Obesity, type 2 diabetes mellitus, and dyslipidemia as the hallmarks of cardiovascular-kidney-metabolic (CKM) syndrome alter hepatic cholesterol metabolism increasing cholesterol saturation in the bile and causing gallstone formation leading to biliary system obstructions. The purpose of the study is to analyse possible methodologies to prevent damage to the biliary tree in benign obstruction to improve the quality of life in the postoperative period in patients with CKM syndrome. Materials and methods. The two-centre study involved 3268 patients with CKM syndrome and cholelithiasis, including complicated cholelithiasis (912 patients, or 28 %). CKM syndrome was diagnosed via a multidisciplinary battery of baseline metrics. Choledocholithiasis was diagnosed using ultrasound, magnetic resonance cholangiopancreatography or intraoperative cholangiography. The study was conducted in accordance with the principles of the Good Clinical Practice, the Council of Europe Convention on Human Rights and Biomedicine. Results. Mean relative fat mass in the cohort was high (30.41 ± 1.09 %), with common comorbidities including ischemic heart disease, hypertension, type 2 diabetes, and peripheral vascular disease, indicating metabolic and vascular links to gallstone formation. Choledocholithiasis was detected in 64.9 % of patients. Post-transpapillary intervention complications included acute pancreatitis (12.8 %), bleeding (1.4 %), and perforation (0.6 %). Delayed laparoscopic surgery was performed in 64.9 %, with an 8.4 % conversion rate due to destructive changes. Metabolic markers varied significantly, especially bilirubin fractions. Conclusions. Obesity and metabolic syndrome are the important predisposing factor and valuable comorbidity in patients with cholelithiasis leading to mechanical jaundice, which accounts for majority of cases. Surgical treatment in an urgent manner remains constant — the combination of lithotripsy accompanied by choledochoscopy makes it possible to prevent damage to the hepatobiliary system and reduce length of stay with benign obstruction of the biliary tract. Proper and timely diagnosis of CKM syndrome and other metabolic conditions may significantly alleviate risk of unsuccessful treatment results and improve patients’ follow-up.

  • Open Access

    PERSONALIZED DIAGNOSTICS AND TREATMENT OF ACUTE SURGICAL AND UROLOGICAL PATHOLOGY (BASED ON THE RESULTS OF PLANNED RESEARCH)

    by V.P. Polyovyi, R.I. Sydorchuk, V.I. Zaitsev, O.V. Rotar, O.S. Fedoruk, K.A. Vladychenko, P.M. Volyanyuk, I.I. Ilyuk, R.P. Knut, A.S. Palianytsia, et al.

    Urgent surgical and urological diseases possess a leading position in the structure of pathologies. At the same time, the existing healthcare system, which is based on the use of therapeutic approaches that have proven effective in other patients, is insufficiently effective, prompting the development of personalized treatment tactics. Aim of the work – to summarize the results of the planned scientific research of the Department of General Surgery and Urology for 2022-2027, scientifically substantiate and improve existing and develop new methods of personalized diagnosis and treatment of acute surgical and urological pathology. Materials and methods. The study is combined (clinical-experimental, prospective, cohort). The experimental part was conducted on 280 white nonlinear rats using the method of polarization tomography of birefringence of the polycrystalline component of histological sections and blood films during modeling of peritonitis and abdominal sepsis of varying severity. The clinical block covers 1039 patients: 696 (66.99%) with acute abdominal pathology, 198 (19.06%) with non-abdominal surgical pathology (including 123 patients with diabetic foot syndrome – DFS), 145 (13.95%) patients with acute purulent-inflammatory diseases of the urinary system. For analysis and formation of personalized algorithms, methods of variation statistics, special software, and auxiliary artificial intelligence tools were used. Results. The polyetiological nature of urinary system lesions was confirmed with dominance of E. coli and S. aureus, but the pathogen was not identified in 13.48% of cases. In surgical treatment of DFS, the high technical effectiveness of balloon angioplasty (94.3%) was proven and the expansion of individual indications for revascularization was substantiated. According to polarization tomographic mapping of blood films of experimental animals, a scenario of necrotic destruction of optical anisotropy was revealed corresponding to the severity of peritonitis. The use of developed personalized approaches to determine the timing and stages of interventions allowed reducing the frequency of postoperative complications by 28.1% and shortening the length of hospital stay by 14.08%. Conclusions. The conducted scientific research allowed a comprehensive assessment of the main parameters of acute surgical and urological diseases, to develop new and improve existing methods of diagnosis and treatment. It was shown that acute surgical and urological diseases dominate in the structure of pathologies treated in the clinic of general surgery and urology. Integration of clinical, laboratory, and instrumental parameters into a single prognostic algorithm using AI tools can be the basis for optimizing treatment. The obtained data allow asserting that personalized diagnostic and therapeutic approaches have development potential and require active implementation.

  • Open Access

    Management of Prediction and Classifying of Wound Healing Results in Plastic and Reconstructive Surgery Based on Machine Learning Models

    by Larysa Sydorchuk, Ruslan Gumennyi, Miroslav Škoda, Andrii Sydorchuk, Yana Vyklyuk, Iryna Batih, Sai Praveen Daruvuri, Ruslan Sydorchuk, Maksym Sokolenko

    Postoperative wound healing complications present a major challenge in plastic and reconstructive surgery, prolonging recovery and impairing outcomes. Early risk identification is difficult due to complex interactions among clinical, laboratory, and molecular factors. This study developed and evaluated machine-learning (ML) models to predict wound healing outcomes and identify key complication predictors. Utilizing a dataset of 95 women and 76 variables (including hematological, biochemical, coagulation, and gene expression profiles), we evaluated several ML approaches, including Decision Tree, Extra Trees, Gaussian/Bernoulli Naive Bayes, Logistic Regression, and Support Vector Machine. Model performance was assessed via k-fold cross-validation, ROC analysis, and SHAP feature importance. Molecular markers (COL1A1, MMP9, MAPK1, MAPK8, IL10, and CCL2) emerged as the strongest predictors, whereas conventional clinical variables showed limited value. The models achieved high discriminative performance, with validation ROC–AUC values ranging from 0.903 to 0.913. Extra Trees and Gaussian Naive Bayes demonstrated the highest sensitivity for detecting complications (Recall = 0.820 ± 0.238 and 0.807 ± 0.246, respectively). These findings highlight the value of integrating molecular-genetic biomarkers with ML for personalized risk stratification and preventive care in reconstructive surgery.


  • Open Access

    Management of Prediction and Classifying of Wound Healing Results in Plastic and Reconstructive Surgery Based on Machine Learning Models

    by Larysa Sydorchuk, Ruslan Gumennyi, Škoda Miroslav, Sydorchuk Andrii, Vyklyuk Yana, Iryna Batih, Daruvuri Sai Praveen, Sydorchuk Ruslan, Sokolenko Maksym

    Postoperative wound healing complications present a major challenge in plastic and reconstructive surgery, prolonging recovery and impairing outcomes. Early risk identification is difficult due to complex interactions among clinical, laboratory, and molecular factors. This study developed and evaluated machine-learning (ML) models to predict wound healing outcomes and identify key complication predictors. Utilizing a dataset of 95 women and 76 variables (including hematological, biochemical, coagulation, and gene expression profiles), we evaluated several ML approaches, including Decision Tree, Extra Trees, Gaussian/Bernoulli Naive Bayes, Logistic Regression, and Support Vector Machine. Model performance was assessed via k-fold cross-validation, ROC analysis, and SHAP feature importance. Molecular markers (COL1A1, MMP9, MAPK1, MAPK8, IL10, and CCL2) emerged as the strongest predictors, whereas conventional clinical variables showed limited value. The models achieved high discriminative performance, with validation ROC–AUC values ranging from 0.903 to 0.913. Extra Trees and Gaussian Naive Bayes demonstrated the highest sensitivity for detecting complications (Recall = 0.820 ± 0.238 and 0.807 ± 0.246, respectively). These findings highlight the value of integrating molecular-genetic biomarkers with ML for personalized risk stratification and preventive care in reconstructive surgery.

  • Acute otitis media in children: molecular genetics approach (rs1061581), clinical and micro-social predictors (single-center cross-sectional case-control study)

    by Larysa Sydorchuk, Oleksii Sakovets, Andrii Sydorchuk, Iryna Batih, Sai Praveen Daruvuri, Ruslan Sydorchuk

    Acute otitis media (AOM) is the 2nd most frequent ENT diagnosis in early childhood. The aim of the study was to evaluate the clinical, anamnestic and micro-social predictors of AOM in children and its association with heat-shock protein gene (HSP70-2, rs1061581) polymorphism. A total of 95 children with AOM (7-18 years old) participated in the study. HSP70-2 (rs1061581) gene genotyping was performed by qPCR method. Risk factors were analyzed. The A-allele of the HSP70-2 gene is a predictor of a more severe AOM course in children and increases its risk and purulent ear discharge almost 2.5 times (p < 0.05), otorrhea - twofold. In preadolescence chronic hypertrophic or vasomotor rhinitis, adenoid vegetations of II-III degrees and non-obstructive diseases of the lower respiratory tract cause an AOM increase risk 3-6 times (p < 0.05). In adolescence, the probability of AOM increases with chronic persistence of hemolytic streptococcus in the oropharynx and broncho-obstructive diseases almost 10 times (p < 0.05). Early daycare attendance before the age of 3 elevates AOM likelihood more than 3 times (p = 0.001). Clinical and social predictors affect the severity of AOM in children depending on age. A-allele (rs1061581) associates with a more severe AOM course in children.

  • Open Access

    Genetic Modulation of Wound Healing Pathways and Postoperative Risk in Plastic and Reconstructive Surgery: A Cohort Study

    by Larysa Sydorchuk, Ruslan Gumennyi, Andrii Sydorchuk, Iryna Batih, Valentina Vasiuk, Ruslan Sydorchuk, Iryna Kamyshna, Pavlo Petakh, Iryna Halabitska, Oleksandr Kamyshnyi

    Objectives: The objective of the study was to investigate the mRNA expression of critical gene patterns, including IL-6, CCL2, IL-10, MAPK1, MAPK8, MMP9, COL1A1, COL3A1, and TGFB1, and their associations with adverse postoperative outcomes in reconstructive and plastic surgery patients, depending on age. Methods: A total of 95 women participated in this prospective longitudinal cohort study and underwent reconstructive/plastic surgery. The mean age was 35.48 ± 6.61 years (range: 19–57). mRNA expression of IL-6, CCL2, IL-10, MAPK1, MAPK8, MMP9, COL1A1, COL3A1, and TGFB1 genes was evaluated in peripheral blood leukocytes using a PCR-based method with reverse transcription of cDNA. Results: The risk of postoperative complications significantly increased with elevated expression levels of IL-6 and COL3A1 (7.5-fold, p = 0.007), CCL2 (6.2-fold, p = 0.012), and MAPK1 (25.5-fold, p < 0.001). Increased expression of MAPK8, IL-10, and MMP9 was associated with a 13.2-fold higher risk (p < 0.001). The strongest association was observed for COL1A1 overexpression, which increased complication risk by 58.33-fold (p < 0.001). Risk stratification using the Molecular Complication Risk Index (MCRI), incorporating weighted gene contributions, identified an unfavorable molecular profile predominantly among women aged ≥ 40 years. Receiver operating characteristic analysis confirmed the model’s discriminative ability (AUC = 0.78; 95% CI 0.68–0.87), with an optimal cut-off value of MCRI ≥ 8.5 (sensitivity 76%, specificity 71%, p < 0.05). Conclusions: The transcriptional activity of IL-6, CCL2, IL-10, MAPK1, MAPK8, MMP9, COL1A1, COL3A1, and TGFB1 is associated with postoperative wound healing risk. Women aged over 40 years are at the highest risk of complications. Implementation of the MCRI model may enable early identification of high-risk patients, support targeted preventive strategies, and improve personalized surgical planning.


  • Open Access

    Machine Learning Models in Classifying, Predicting and Managing COVID-19 Severity

    by Larysa Sydorchuk, Maksym Sokolenko, Miroslav Škoda, Denys Nevinskyi, Yaroslav Vyklyuk, Ruslan Sydorchuk, Alina Sokolenko, Ludmila Sokolenko, Andrii Sydorchuk, Oleksandr Sokolenko

    For machine-learning analysis, a dataset consisting of 226 observations with 68 features obtained from 257 COVID-19 patients was used. To identify the most effective models for predicting COVID-19 severity, an extensive evaluation of available classifiers from the Scikit-learn library with default hyperparameter settings was conducted, including lo-gistic regression, k-nearest neighbors, decision trees, ensemble algorithms (random forest, gradient boosting, bagging), naïve Bayes classifiers, support vector machines, and others. Model performance was assessed using Accuracy and AUC-ROC, with a focus on max-imizing AUC-ROC to ensure optimal class discrimination. Optimal hyperparameters for each model were defined as those yielding the highest mean AUC-ROC value during 5-fold cross-validation. Ensemble methods such as ExtraTreesClassifier (Accuracy: 0.974 ± 0.022) and RandomForestClassifier (Accuracy: 0.960 ± 0.035) demonstrated ROC curves approaching that of an ideal classifier (upper-left corner of the plot), confirming their ex-cellent performance in predicting COVID-19 severity. Simpler models, including Ber-noulliNB (Accuracy: 0.956 ± 0.037) and DecisionTreeClassifier (Accuracy: 0.938 ± 0.043), also showed high classification quality. Analysis of misclassification patterns revealed that ExtraTreesClassifier, HistGradientBoostingClassifier, BaggingClassifier, and Gradi-entBoostingClassifier made no errors across any class. The poorest performance was ob-served with LinearDiscriminantAnalysis, which generated 11 misclassifications, followed by CalibratedClassifierCV, and LogisticRegressionCV.

  • Open Access

    Management of Severe COVID-19 Diagnosis Using Machine Learning

    by Larysa Sydorchuk, Maksym Sokolenko, Miroslav Škoda, Daniel Lajcin, Yaroslav Vyklyuk, Ruslan Sydorchuk, Alina Sokolenko, Dmytro Martjanov

    COVID-19 remains a global health challenge, with severe cases often leading to complications and fatalities. The objective of this study was to assess supervised machine learning algorithms for predicting severe COVID-19 based on demographic, clinical, biochemical, and genetic variables, with the aim of identifying the most informative prognostic markers. For Machine Learning (ML) analysis, we utilized a dataset comprising 226 observations with 68 clinical, biochemical, and genetic features collected from 226 patients with confirmed COVID-19 (54—moderate, 142—severe and 30 with mild disease). The target variable was disease severity (mild, moderate, severe). The feature set included demographic variables (age, sex), genetic markers (single-nucleotide polymorphisms (SNPs) in FGB (rs1800790), NOS3 (rs2070744), and TMPRSS2 (rs12329760)), biochemical indicators (IL-6, endothelin-1, D-dimer, fibrinogen, among others), and clinical parameters (blood pressure, body mass index, comorbidities). The target variable was disease severity. To identify the most effective predictive models for COVID-19 severity, we systematically evaluated multiple supervised learning algorithms, including logistic regression, k-nearest neighbors, decision trees, random forest, gradient boosting, bagging, naïve Bayes, and support vector machines. Model performance was assessed using accuracy and the area under the receiver operating characteristic curve (AUC-ROC). Among the predictors, IL-6, presence of depression/pneumonia, LDL cholesterol, AST, platelet count, lymphocyte count, and ALT showed the strongest correlations with severity. The highest predictive accuracy, with negligible error rates, was achieved by ensemble-based models such as ExtraTreesClassifier, HistGradientBoostingClassifier, BaggingClassifier, and GradientBoostingClassifier. Notably, decision tree models demonstrated high classification precision at terminal nodes, many of which yielded a 100% probability for a specific severity class.


  • Open Access

    Management of Severe COVID-19 Diagnosis Using Machine Learning

    by Larysa Sydorchuk, Maksym Sokolenko, Miroslav Škoda, Daniel Lajcin, Yaroslav Vyklyuk, Ruslan Sydorchuk, Alina Sokolenko, Dmytro Martjanov

    For Machine Learning (ML) analysis, we utilized a dataset comprising 226 observations with 68 clinical, biochemical, and genetic features collected from 257 patients with confirmed COVID-19 (197 with moderate-to-severe disease and 60 with mild disease). The feature set included demographic variables (age, sex), genetic markers (single-nucleotide polymorphisms (SNPs) in FGB (rs1800790), NOS3 (rs2070744), and TMPRSS2 (rs12329760)), biochemical indicators (IL-6, endothelin-1, D-dimer, fibrinogen, among others), and clinical parameters (blood pressure, body mass index, comorbidities). The target variable was disease severity. To identify the most effective predictive models for COVID-19 severity, we systematically evaluated multiple supervised learning algorithms, including logistic regression, k-nearest neighbors, decision trees, random forest, gradient boosting, bagging, naïve Bayes, and support vector machines. Model performance was assessed using accuracy and the area under the receiver operating characteristic curve (AUC-ROC). Among the predictors, IL-6, presence of depression/pneumonia, LDL cholesterol, AST, platelet count, lymphocyte count, and ALT showed the strongest correlations with severity. The highest predictive accuracy, with negligible error rates, was achieved by ensemble-based models such as ExtraTreesClassifier, HistGradientBoostingClassifier, BaggingClassifier, and GradientBoostingClassifier. Notably, decision tree models demonstrated high classification precision at terminal nodes, many of which yielded a 100% probability for a specific severity class.


  • Open Access

    Illya Ilyich Mechnykov – from zoologist to microbiologist and to the discovery of phagocytosis

    by Svyatoslav Deineka, Leonid Sydorchuk, Andriy Mikheev, Ruslan Sydorchuk, Igor Sydorchuk, Святослав Дейнека, Леонід Сидорчук, Андрій Міхєєв, Ігор Сидорчук

    The article is dedicated to the 180th anniversary of the birth of Ilya Mechnikov – one of the most prominent scientists of the world level, whose name has forever entered the history of science. Born on Ukrainian land, he made an invaluable contribution to the development of biology and medicine, in particular in the field of immunology. His research laid the foundations of the modern understanding of the immune system, and the Nobel Prize he received in 1908 was a recognition of his genius. Ilya Mechnikov is not only the pride of Ukraine but also a symbol of how talent and perseverance can change the world. His contribution to science remains relevant today, and his life is an example of how the love of knowledge can overcome any borders. Absolutely! Here’s the English translation of the summary, aiming for a C2 level of proficiency. Objective of the Article: To meticulously examine the trajectory of life and the seminal scientific contributions of Ilya Ilyich Mechnikov, the distinguished Ukrainian scientist and Nobel laureate, with a particular emphasis on his formative period and activities within Ukraine. Novelty: The study offers a systematic consolidation of information pertaining to Mechnikov’s Ukrainian sojourn and his intellectual genesis as a scientist. It underscores the pivotal significance of this foundational phase in shaping his subsequent groundbreaking discoveries that resonated globally. Methodology: The research employs a comprehensive analytical approach, scrutinizing biographical data, scholarly publications, historical records, contemporary accounts, and pertinent literary sources. Conclusions: Mechnikov’s Ukrainian heritage and the intellectual milieu of Kharkiv and Odesa were instrumental in his development as a scientist. His pioneering discoveries in the fields of immunity and microbiology hold fundamental and enduring significance for the global scientific community