Ya. A. Borovets
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ya. A. Borovets has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Tatsiana V. Mokhort
Belarusian State Medical University
3 shared publications - Volha Vasilkova
Gomel State Medical University
3 shared publications - I. A. Vasyukhina
Republican Scientific and Practical Center for Radiation Medicine and Human Ecology
2 shared publications - Ivan Yu. Pchelin
Saint Petersburg State University
2 shared publications - L. E. Korotaeva
Republican Scientific and Practical Center for Radiation Medicine and Human Ecology
2 shared publications - Yuliya I. Yarets
Republican Research Center for Radiation Medicine and Human Ecology
2 shared publications
Latest Publications
- Open Access
- 17 October 2026
- Published by Pirogov National Medical and Surgical Center in Medical doctor and information technologies
- No. 3,p. 70-89
Transfer learning for classyfying otoscopic medical images in the diagnosis of ent diseases
Relevance. According to the Ministry of Health of the Russian Federation, more than 6% of the country's population consults an otorhinolaryngologist annually due to ear diseases. Given the high workload of specialists, the accelerated implementation of artificial intelligence (AI) methods to assist in diagnosis is necessary. Objective. To develop a prototype AI-based medical system (AI MS) for diagnosing ear diseases from otoscopic images (OIs), achieving a diagnostic accuracy of at least 95% on the test set through transfer learning techniques applied to pre-trained deep neural networks (NNs). Materials and methods. A labeled otoscopic image dataset representing five balanced diagnostic classes was selected and prepared from Kaggle.com. To effectively implement transfer learning of neural network models and prevent overfitting, a data preprocessing and augmentation pipeline was established. A custom web interface for NNM integration was developed, and the Grad-CAM method was applied to visualize diagnostic regions within the images. Results. The CNN models selected for transfer learning were ResNet18, ResNet50, EfficientNet-B0, and EfficientNet-B2. Based on experiments using "soft" augmentation of the training set, the diagnostic accuracy for five ear disease categories—listed in the order mentioned—was 95.3%, 96.1%, 97.8%, and 99.7%, respectively. The ResNet50 model with soft augmentation of the training set for 3 classes showed an overall test data accuracy of 97%. Heatmaps visualizing the diagnostic results using the Grad-CAM method are presented. Conclusion. Transfer learning, involving the adaptation of selected pre-trained architectures (ResNet18, ResNet50, EfficientNet-B0, and EfficientNet-B2) to the task of multiclass classification of ear diseases using balanced classes, enabled the achievement of the target accuracy for automated diagnosis. Conditions have been established for collaborative efforts with the Mogilev Regional Clinical Hospital (MRCH) to develop an AI-based medical system for diagnosing ear diseases.
- 17 October 2026
- Published by Pirogov National Medical and Surgical Center in Medical doctor and information technologies
- No. 3,p. 70-89
Open AccessTransfer learning for classyfying otoscopic medical images in the diagnosis of ent diseases
Relevance. According to the Ministry of Health of the Russian Federation, more than 6% of the country's population consults an otorhinolaryngologist annually due to ear diseases. Given the high workload of specialists, the accelerated implementation of artificial intelligence (AI) methods to assist in diagnosis is necessary. Objective. To develop a prototype AI-based medical system (AI MS) for diagnosing ear diseases from otoscopic images (OIs), achieving a diagnostic accuracy of at least 95% on the test set through transfer learning techniques applied to pre-trained deep neural networks (NNs). Materials and methods. A labeled otoscopic image dataset representing five balanced diagnostic classes was selected and prepared from Kaggle.com. To effectively implement transfer learning of neural network models and prevent overfitting, a data preprocessing and augmentation pipeline was established. A custom web interface for NNM integration was developed, and the Grad-CAM method was applied to visualize diagnostic regions within the images. Results. The CNN models selected for transfer learning were ResNet18, ResNet50, EfficientNet-B0, and EfficientNet-B2. Based on experiments using "soft" augmentation of the training set, the diagnostic accuracy for five ear disease categories—listed in the order mentioned—was 95.3%, 96.1%, 97.8%, and 99.7%, respectively. The ResNet50 model with soft augmentation of the training set for 3 classes showed an overall test data accuracy of 97%. Heatmaps visualizing the diagnostic results using the Grad-CAM method are presented. Conclusion. Transfer learning, involving the adaptation of selected pre-trained architectures (ResNet18, ResNet50, EfficientNet-B0, and EfficientNet-B2) to the task of multiclass classification of ear diseases using balanced classes, enabled the achievement of the target accuracy for automated diagnosis. Conditions have been established for collaborative efforts with the Mogilev Regional Clinical Hospital (MRCH) to develop an AI-based medical system for diagnosing ear diseases.
- Open Access
- 3 January 2023
- Published by Gomel State Medical University in Health and Ecology Issues
- Vol. 19 (4) , 48-55
Clinical significance of the T(-344)C polymorphism of the aldosterone synthase gene (CYP11B2) in the prognosis of cardiorenal syndrome in diabetes mellitus
Objective. To evaluate the role of the T(-344)C polymorphism of CYP11B2 gene in the development of cardiorenal syndrome (CRS) in diabetes mellitus (DM).Materials and methods. 270 patients with type 1 and type 2 diabetes aged over 25 years were examined. All patients underwent molecular genetic analysis using deoxyribonucleic acid isolated from whole venous blood.Results. The TT genotype was associated with the risk of developing CRS manifestations such as left ventricular hypertrophy (odds ratio (OR) 2.64; 95% CI (0.93–4.19), chronic heart failure (OR 4.26; 95% CI (2.26 - 8.06), subclinical atherosclerosis (OR 4.04; 95% CI (1.89 - 8.58), chronic kidney disease (CKD) (OR 10.77; 95% CI (3.56 - 32.61), and the CT genotype (OR 3.28; 95% CI (1.02 – 10.59) with CKD risk..Conclusion. There are pathogenetic associations between renin-angiotensin-aldosterone system, cardiovascular complications and a decrease of renal function. Further research is needed for a deep understanding of the complex pathogenetic mechanisms of the development and progression of cardiovascular and renal pathology.
- 3 January 2023
- Published by Gomel State Medical University in Health and Ecology Issues
- Vol. 19 (4) , 48-55
Open AccessClinical significance of the T(-344)C polymorphism of the aldosterone synthase gene (CYP11B2) in the prognosis of cardiorenal syndrome in diabetes mellitus
Objective. To evaluate the role of the T(-344)C polymorphism of CYP11B2 gene in the development of cardiorenal syndrome (CRS) in diabetes mellitus (DM).Materials and methods. 270 patients with type 1 and type 2 diabetes aged over 25 years were examined. All patients underwent molecular genetic analysis using deoxyribonucleic acid isolated from whole venous blood.Results. The TT genotype was associated with the risk of developing CRS manifestations such as left ventricular hypertrophy (odds ratio (OR) 2.64; 95% CI (0.93–4.19), chronic heart failure (OR 4.26; 95% CI (2.26 - 8.06), subclinical atherosclerosis (OR 4.04; 95% CI (1.89 - 8.58), chronic kidney disease (CKD) (OR 10.77; 95% CI (3.56 - 32.61), and the CT genotype (OR 3.28; 95% CI (1.02 – 10.59) with CKD risk..Conclusion. There are pathogenetic associations between renin-angiotensin-aldosterone system, cardiovascular complications and a decrease of renal function. Further research is needed for a deep understanding of the complex pathogenetic mechanisms of the development and progression of cardiovascular and renal pathology.
- Open Access
- 30 June 2021
- Published by Gomel State Medical University in Health and Ecology Issues
- No. 2,p. 79-85
Diagnostic value of cystatin C for the early diagnosis of diabetic nephropathy
Objective:to assess the clinical significance of cystatin C in the early diagnosis of diabetic nephropathy.Materials and methods.We examined 449 patients with type 1 and type 2 diabetes mellitusolder than 25 years. The laboratory examination of the patients included the measurement of cystatin, creatinine in the blood serum, GFR calculation according to the CKD-EPI equation, and the determination of albuminuria levels.Results.The role of cystatin C as a reliable marker of diabetic nephropathy has been demonstrated: the level of cystatin C ≥ 0.72 mg/L with sensitivity of 90.8 %, specificity of 88.9 %, was associated with a decline of renal function in the diabetic patients (ROC AUC = 0.951).Conclusion.The determination of the level of cystatin C, alone or in conjunction with creatinine, will help to more accurately diagnose GFR and assess the risk of mortality and renal complications in patients with diabetes mellitus.
- 30 June 2021
- Published by Gomel State Medical University in Health and Ecology Issues
- No. 2,p. 79-85
Open AccessDiagnostic value of cystatin C for the early diagnosis of diabetic nephropathy
Objective:to assess the clinical significance of cystatin C in the early diagnosis of diabetic nephropathy.Materials and methods.We examined 449 patients with type 1 and type 2 diabetes mellitusolder than 25 years. The laboratory examination of the patients included the measurement of cystatin, creatinine in the blood serum, GFR calculation according to the CKD-EPI equation, and the determination of albuminuria levels.Results.The role of cystatin C as a reliable marker of diabetic nephropathy has been demonstrated: the level of cystatin C ≥ 0.72 mg/L with sensitivity of 90.8 %, specificity of 88.9 %, was associated with a decline of renal function in the diabetic patients (ROC AUC = 0.951).Conclusion.The determination of the level of cystatin C, alone or in conjunction with creatinine, will help to more accurately diagnose GFR and assess the risk of mortality and renal complications in patients with diabetes mellitus.
- Open Access
- 1 January 2020
- Published by Scientia Publishing House LTD in Juvenis scientia
- Vol. 6 (2) , 36-43
EVALUATION OF THE LEVELS OF FIBROBLAST GROWTH FACTOR (FGF-23) AND INFLAMMATION MARKERS IN PATIENTS WITH TYPE 2 DIABETES MELLITUS AND DIFFERENT STAGES OF CHRONIC KIDNEY DISEASE
Recently, inflammatory and regulatory mechanisms that are involved in the onset and progression of angiopathies in diabetes mellitus (DM), including diabetic kidney disease (DKD), have been studied. In this study, we assessed the levels of fibroblast growth factor-23 (FGF-23) and inflammatory markers in patients with type 2 DM and different stages of chronic kidney disease (CKD). We investigated 64 patients with type 2 DM aged 34-84 years. The results showed significant changes in the levels of FGF-23, tumour necrosis factor alpha (TNF-alpha), C-reactive protein (CRP), high-sensitivity C-reactive protein (hsCRP), and interleukin-6 (IL-6) with the progression of CKD in patients with type 2 diabetes. Multiple regression analysis demonstrated the presence of an independent interconnection between serum levels of FGF-23 and creatinine.
- 1 January 2020
- Published by Scientia Publishing House LTD in Juvenis scientia
- Vol. 6 (2) , 36-43
Open AccessEVALUATION OF THE LEVELS OF FIBROBLAST GROWTH FACTOR (FGF-23) AND INFLAMMATION MARKERS IN PATIENTS WITH TYPE 2 DIABETES MELLITUS AND DIFFERENT STAGES OF CHRONIC KIDNEY DISEASE
Recently, inflammatory and regulatory mechanisms that are involved in the onset and progression of angiopathies in diabetes mellitus (DM), including diabetic kidney disease (DKD), have been studied. In this study, we assessed the levels of fibroblast growth factor-23 (FGF-23) and inflammatory markers in patients with type 2 DM and different stages of chronic kidney disease (CKD). We investigated 64 patients with type 2 DM aged 34-84 years. The results showed significant changes in the levels of FGF-23, tumour necrosis factor alpha (TNF-alpha), C-reactive protein (CRP), high-sensitivity C-reactive protein (hsCRP), and interleukin-6 (IL-6) with the progression of CKD in patients with type 2 diabetes. Multiple regression analysis demonstrated the presence of an independent interconnection between serum levels of FGF-23 and creatinine.