Zhanas Baimagambet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhanas Baimagambet has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Kulzhan Berikkhanova
National Laboratory Astana, Nazarbayev University, Astana 010000, Kazakhstan
2 shared publications - Yeldar Baiken
PI National Laboratory Astana, Nazarbayev University, Astana, KAZAKHSTAN
2 shared publications - Aidana Bissen
School of Engineering and Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan
1 shared publication - Aliya Bekmurzayeva
Nazarbayev University
1 shared publication - Ardak Omarbekov
PI «National Laboratory Astana», Nazarbayev University, Astana 010000, Kazakhstan
1 shared publication Arshat Urazbaev
1 shared publication
Latest Publications
- Open Access
- 9 September 2026
- Published by MDPI AG in Pharmaceutics
- Vol. 18 (9) , 1131
Drug-Loaded Red Blood Cell–Derived Carriers for Targeted Delivery to Accelerate Tissue Regeneration
Background/Objectives: Diabetic foot ulcers are characterized by persistent inflammation, impaired angiogenesis, and delayed tissue regeneration. Epidermal growth factor (EGF) is an important regulator of wound repair; however, its therapeutic application may be limited by rapid degradation and poor retention within the wound environment. This study investigated the therapeutic efficacy of local administration of EGF and ceftriaxone using autologous red blood cell-derived carriers (RBCDCs) in an experimental model of diabetic wound healing in rats. Methods: Experiments were conducted on 30 albino Wistar rats (250 ± 20 g) with experimentally induced diabetic wounds. In the RBCDC treatment groups, separately prepared drug-loaded RBCDC formulations containing EGF or ceftriaxone were locally administered into the wound. The corresponding comparison groups received the same active agents in free form according to an identical treatment schedule, while an additional control group received topical Levomekol. Results: RBCDC-mediated administration of EGF and ceftriaxone significantly accelerated wound closure and was associated with earlier resolution of inflammation, granulation tissue maturation, re-epithelialization, collagen deposition, and angiogenesis compared with the corresponding free-drug formulations. On day 9, tissue EGF concentration was higher in the RBCDC (EGF + Ctx) group than in the corresponding free-drug group. Additional formulation characterization demonstrated ceftriaxone encapsulation and in vitro release from RBCDCs, as well as in vitro EGF release from EGF-loaded RBCDCs. Conclusions: Autologous RBCDCs represent a promising local drug-carrier platform for the administration of regenerative and antimicrobial agents in experimental diabetic wounds. Further studies are required to establish local pharmacokinetics, systemic exposure, carrier stability, and the mechanisms responsible for the observed therapeutic effects.
- 9 September 2026
- Published by MDPI AG in Pharmaceutics
- Vol. 18 (9) , 1131
Open AccessDrug-Loaded Red Blood Cell–Derived Carriers for Targeted Delivery to Accelerate Tissue Regeneration
Background/Objectives: Diabetic foot ulcers are characterized by persistent inflammation, impaired angiogenesis, and delayed tissue regeneration. Epidermal growth factor (EGF) is an important regulator of wound repair; however, its therapeutic application may be limited by rapid degradation and poor retention within the wound environment. This study investigated the therapeutic efficacy of local administration of EGF and ceftriaxone using autologous red blood cell-derived carriers (RBCDCs) in an experimental model of diabetic wound healing in rats. Methods: Experiments were conducted on 30 albino Wistar rats (250 ± 20 g) with experimentally induced diabetic wounds. In the RBCDC treatment groups, separately prepared drug-loaded RBCDC formulations containing EGF or ceftriaxone were locally administered into the wound. The corresponding comparison groups received the same active agents in free form according to an identical treatment schedule, while an additional control group received topical Levomekol. Results: RBCDC-mediated administration of EGF and ceftriaxone significantly accelerated wound closure and was associated with earlier resolution of inflammation, granulation tissue maturation, re-epithelialization, collagen deposition, and angiogenesis compared with the corresponding free-drug formulations. On day 9, tissue EGF concentration was higher in the RBCDC (EGF + Ctx) group than in the corresponding free-drug group. Additional formulation characterization demonstrated ceftriaxone encapsulation and in vitro release from RBCDCs, as well as in vitro EGF release from EGF-loaded RBCDCs. Conclusions: Autologous RBCDCs represent a promising local drug-carrier platform for the administration of regenerative and antimicrobial agents in experimental diabetic wounds. Further studies are required to establish local pharmacokinetics, systemic exposure, carrier stability, and the mechanisms responsible for the observed therapeutic effects.
- Open Access
- 11 May 2026
- Published by Springer Nature in Research Square
MAGIC-CT: Multiorgan Annotation and Grounded Image Captioning in CT for Cancer
Computed Tomography (CT) imaging is a cornerstone of abdominal oncology, offering critical insights into tumor morphology and spread. While artificial intelligence (AI) holds promise for automating lesion detection, segmentation, and reporting, progress is hindered by the scarcity of multimodal datasets that pair 3D anatomical annotations with expert-curated clinical descriptions. We present MAGIC-CT, a contrast-enhanced CT dataset of 562 patients with abdominal tumors (liver cysts/cancer, lung metastases, lung cancer, kidney cysts, renal cancer, pancreatic cancer). All 562 patients have CT scans and 3D lesion/organ masks; a subset of 492 patients also have organ-wise, radiologist-authored reports (RU/KZ/EN) totaling 4,937 organ descriptions. The dataset spans 8 pathologies across 4 organs, with about 1,250 annotated lesions and about 500 lesion-linked textual findings, enabling training of multimodal systems that connect volumetric localization to clinical language. MAGIC-CT uniquely integrates volumetric lesion localization, quantitative metrics (e.g., tumor volume, angular involvement of vasculature), and rich semantic context (e.g., "cuff-like encasement of the celiac trunk"), addressing the lack of resources bridging radiological imaging, segmentation, and clinical language. This dataset is expected to enable advancements in AI-driven tumor characterization, automated report generation, and metastasis tracking, with implications for precision oncology. This dataset is openly available at Zenodo: \href{https://doi.org/10.5281/zenodo.18389015}{10.5281/zenodo.18389015}.
- 11 May 2026
- Published by Springer Nature in Research Square
Open AccessMAGIC-CT: Multiorgan Annotation and Grounded Image Captioning in CT for Cancer
Computed Tomography (CT) imaging is a cornerstone of abdominal oncology, offering critical insights into tumor morphology and spread. While artificial intelligence (AI) holds promise for automating lesion detection, segmentation, and reporting, progress is hindered by the scarcity of multimodal datasets that pair 3D anatomical annotations with expert-curated clinical descriptions. We present MAGIC-CT, a contrast-enhanced CT dataset of 562 patients with abdominal tumors (liver cysts/cancer, lung metastases, lung cancer, kidney cysts, renal cancer, pancreatic cancer). All 562 patients have CT scans and 3D lesion/organ masks; a subset of 492 patients also have organ-wise, radiologist-authored reports (RU/KZ/EN) totaling 4,937 organ descriptions. The dataset spans 8 pathologies across 4 organs, with about 1,250 annotated lesions and about 500 lesion-linked textual findings, enabling training of multimodal systems that connect volumetric localization to clinical language. MAGIC-CT uniquely integrates volumetric lesion localization, quantitative metrics (e.g., tumor volume, angular involvement of vasculature), and rich semantic context (e.g., "cuff-like encasement of the celiac trunk"), addressing the lack of resources bridging radiological imaging, segmentation, and clinical language. This dataset is expected to enable advancements in AI-driven tumor characterization, automated report generation, and metastasis tracking, with implications for precision oncology. This dataset is openly available at Zenodo: \href{https://doi.org/10.5281/zenodo.18389015}{10.5281/zenodo.18389015}.
- 5 May 2026
- Published by Modestum Ltd in Electronic Journal of General Medicine
- Vol. 23 (3) , em732
ML in breast cancer IHC: Pilot evaluation on non-ideal slides in Kazakhstan
Objectives: Automation of quantitative analysis of breast cancer (BC) immunohistochemistry (IHC) specimens is important to optimize pathologists’ workflow and improve diagnostic reproducibility. This is especially important in low- and middle-income countries where there is a shortage of highly trained pathologists. However, existing approaches face challenges in implementing fully automated quantitative IHC due to the difficulty of both delineating tumor areas, including discrete areas, especially in IHC slides with poor quality. Moreover, accurate identification of invasive carcinoma areas and accurate quantification of positive and negative cells in the specimen are critical for quantitative analysis. Methods and results: This study presents a method to automatically identify types of carcinoma areas in whole slide IHC images of BC, focusing on quantifying IHC images on realms of Kazakhstan. The used model is a combination of morphological characteristics and boundary features, which provides high accuracy of segmentation of tumor zones of images of mild and low quality. We used several methods includes convolutional neural network based on the Keras framework, k-nearest neighbors machine learning methods, and self-developed image analysis methods. The developed model showed high accuracy, where the results corresponded to the diagnoses of pathologists. As expected, the method proved to be ineffective when applied to severely degraded slides, such as those with insufficient staining or inadequate washing. Slides of inferior quality were excluded from analysis, which negatively affected the statistical robustness. On slides of moderate quality, the reliability of nucleus segmentation dropped significantly. Conclusions: The combination of models we used showed high accuracy in differentiating BC cells between the basal-like subtype of BC and its invasiveness and recurrence in Kazakhstan. However, IHC specimens with low DPI or low-quality IHC need further optimizations and improvements in algorithm design. The main issue can be considered methodological differences between the approaches of AI and humans: AI operates in a large number of cases (more than 10,000), yet its accuracy is relatively low. In contrast, humans work with a much smaller number of cases but achieve a level of precision that AI cannot currently match. This discrepancy necessitates a revision of the methodology of IHC analysis for AI, including the development of new requirements, methods, and thresholds from scratch. This approach provides analysis of the entire area of the slide, increases the speed of interpretation of IHC results, and reduces human errors in diagnosis, especially in low- and middle-income countries.
- 5 May 2026
- Published by Modestum Ltd in Electronic Journal of General Medicine
- Vol. 23 (3) , em732
ML in breast cancer IHC: Pilot evaluation on non-ideal slides in Kazakhstan
Objectives: Automation of quantitative analysis of breast cancer (BC) immunohistochemistry (IHC) specimens is important to optimize pathologists’ workflow and improve diagnostic reproducibility. This is especially important in low- and middle-income countries where there is a shortage of highly trained pathologists. However, existing approaches face challenges in implementing fully automated quantitative IHC due to the difficulty of both delineating tumor areas, including discrete areas, especially in IHC slides with poor quality. Moreover, accurate identification of invasive carcinoma areas and accurate quantification of positive and negative cells in the specimen are critical for quantitative analysis. Methods and results: This study presents a method to automatically identify types of carcinoma areas in whole slide IHC images of BC, focusing on quantifying IHC images on realms of Kazakhstan. The used model is a combination of morphological characteristics and boundary features, which provides high accuracy of segmentation of tumor zones of images of mild and low quality. We used several methods includes convolutional neural network based on the Keras framework, k-nearest neighbors machine learning methods, and self-developed image analysis methods. The developed model showed high accuracy, where the results corresponded to the diagnoses of pathologists. As expected, the method proved to be ineffective when applied to severely degraded slides, such as those with insufficient staining or inadequate washing. Slides of inferior quality were excluded from analysis, which negatively affected the statistical robustness. On slides of moderate quality, the reliability of nucleus segmentation dropped significantly. Conclusions: The combination of models we used showed high accuracy in differentiating BC cells between the basal-like subtype of BC and its invasiveness and recurrence in Kazakhstan. However, IHC specimens with low DPI or low-quality IHC need further optimizations and improvements in algorithm design. The main issue can be considered methodological differences between the approaches of AI and humans: AI operates in a large number of cases (more than 10,000), yet its accuracy is relatively low. In contrast, humans work with a much smaller number of cases but achieve a level of precision that AI cannot currently match. This discrepancy necessitates a revision of the methodology of IHC analysis for AI, including the development of new requirements, methods, and thresholds from scratch. This approach provides analysis of the entire area of the slide, increases the speed of interpretation of IHC results, and reduces human errors in diagnosis, especially in low- and middle-income countries.
- Open Access
- 1 January 2026
- Published by Wiley in Journal of Nursing Management
- Vol. 2026 (1) , e6082303
Registered Nurse Workload and Resident Outcomes in Nursing Homes: A Scoping Review of Workforce Sustainability and Nursing Management
Aim: To map RN workload, staffing indicators, resident outcomes, workforce sustainability and nursing‐management context in nursing homes. Background: Staffing ratios and hours per resident day (HPRD) quantify staffing but not role complexity, interruptions, supervisory demands, resident acuity, continuity or work environment. Evaluation: Following JBI guidance and PRISMA‐ScR, five databases were searched using an RN‐specific strategy and updated on 4 September 2026. Following source‐level eligibility reassessment and reconciliation of the updated search, 20 studies meeting the RN‐specific resident‐outcome criteria formed the primary synthesis. Seven studies that did not meet these criteria but provided relevant workforce or nursing‐management evidence were retained as a separately labelled contextual evidence layer and excluded from the primary synthesis and PRISMA included‐study count. Primary studies underwent full data charting, whereas contextual studies underwent restricted extraction for interpretive purposes only. Key Issues: Evidence was predominantly observational. Greater RN availability and more favourable work environments were generally associated with better resident outcomes, although findings varied by outcome, timing, staffing configuration and organisational context. Conclusions: RN workload is multidimensional and cannot be reduced to staffing ratios alone. Current evidence does not establish a universal RN staffing threshold or support causal conclusions across nursing‐home settings. Implications for Nursing Management: Managers should interpret staffing metrics alongside resident acuity, staffing continuity, workload intensity, skill mix, agency use and work‐environment indicators.
- 1 January 2026
- Published by Wiley in Journal of Nursing Management
- Vol. 2026 (1) , e6082303
Open AccessRegistered Nurse Workload and Resident Outcomes in Nursing Homes: A Scoping Review of Workforce Sustainability and Nursing Management
Aim: To map RN workload, staffing indicators, resident outcomes, workforce sustainability and nursing‐management context in nursing homes. Background: Staffing ratios and hours per resident day (HPRD) quantify staffing but not role complexity, interruptions, supervisory demands, resident acuity, continuity or work environment. Evaluation: Following JBI guidance and PRISMA‐ScR, five databases were searched using an RN‐specific strategy and updated on 4 September 2026. Following source‐level eligibility reassessment and reconciliation of the updated search, 20 studies meeting the RN‐specific resident‐outcome criteria formed the primary synthesis. Seven studies that did not meet these criteria but provided relevant workforce or nursing‐management evidence were retained as a separately labelled contextual evidence layer and excluded from the primary synthesis and PRISMA included‐study count. Primary studies underwent full data charting, whereas contextual studies underwent restricted extraction for interpretive purposes only. Key Issues: Evidence was predominantly observational. Greater RN availability and more favourable work environments were generally associated with better resident outcomes, although findings varied by outcome, timing, staffing configuration and organisational context. Conclusions: RN workload is multidimensional and cannot be reduced to staffing ratios alone. Current evidence does not establish a universal RN staffing threshold or support causal conclusions across nursing‐home settings. Implications for Nursing Management: Managers should interpret staffing metrics alongside resident acuity, staffing continuity, workload intensity, skill mix, agency use and work‐environment indicators.
- Open Access
- 4 December 2025
- Published by MDPI AG in Biosensors
- Vol. 15 (12) , 796
Digging into the Solubility Factor in Cancer Diagnosis: A Case of Soluble CD44 Protein
The detection of soluble proteins in biological fluids, as a form of liquid biopsy, is a promising tool for cancer diagnosis and prognosis, as it is less invasive than traditional diagnostic methods. CD44 is one of the most recognized markers of cancer stem cells, a small subset of cells responsible for cancer initiation, progression, and metastasis. Given the importance of CD44 as a cancer biomarker, several review articles explore the diagnostic and therapeutic value of cell-surface CD44. In addition to being a membrane-anchored protein, CD44 is also shed from the cell surface and can be found in various biological fluids. However, the role of soluble CD44 in cancer has not been comprehensively discussed in recent reviews. Measuring soluble CD44 in various biological liquids can provide a practical and valuable tool for cancer diagnosis and treatment monitoring. Therefore, this review comprehensively discusses the role of soluble CD44 as a marker in various cancer types, including serum, saliva, urine, and other fluids. In particular, its role as an early cancer biomarker and as a predictive and prognostic biomarker in several cancers is discussed. This work also provides an overview of a wide range of analytical techniques used to detect soluble CD44. The value of cells expressing CD44 versus soluble CD44 as a biomarker is also compared. The review concludes with a perspective on future directions, emphasizing the shift toward non-invasive analytical methods and the need for standardization of detection, including multiple biomarkers during evaluation, to improve the accuracy of cancer diagnosis.
- 4 December 2025
- Published by MDPI AG in Biosensors
- Vol. 15 (12) , 796
Open AccessDigging into the Solubility Factor in Cancer Diagnosis: A Case of Soluble CD44 Protein
The detection of soluble proteins in biological fluids, as a form of liquid biopsy, is a promising tool for cancer diagnosis and prognosis, as it is less invasive than traditional diagnostic methods. CD44 is one of the most recognized markers of cancer stem cells, a small subset of cells responsible for cancer initiation, progression, and metastasis. Given the importance of CD44 as a cancer biomarker, several review articles explore the diagnostic and therapeutic value of cell-surface CD44. In addition to being a membrane-anchored protein, CD44 is also shed from the cell surface and can be found in various biological fluids. However, the role of soluble CD44 in cancer has not been comprehensively discussed in recent reviews. Measuring soluble CD44 in various biological liquids can provide a practical and valuable tool for cancer diagnosis and treatment monitoring. Therefore, this review comprehensively discusses the role of soluble CD44 as a marker in various cancer types, including serum, saliva, urine, and other fluids. In particular, its role as an early cancer biomarker and as a predictive and prognostic biomarker in several cancers is discussed. This work also provides an overview of a wide range of analytical techniques used to detect soluble CD44. The value of cells expressing CD44 versus soluble CD44 as a biomarker is also compared. The review concludes with a perspective on future directions, emphasizing the shift toward non-invasive analytical methods and the need for standardization of detection, including multiple biomarkers during evaluation, to improve the accuracy of cancer diagnosis.
- 1 January 2025
- Published by Engineered Science Publisher in Engineered Science
Revolutionizing Breast Cancer Detection with Artificial Intelligence and Machine Learning Breakthroughs in Imaging and Diagnosis: Literature Review
This review unveils artificial intelligence / machine learning innovations transforming breast cancer imaging, elevating diagnostic precision, efficiency, and personalized oncology outcomes.
- 1 January 2025
- Published by Engineered Science Publisher in Engineered Science
Revolutionizing Breast Cancer Detection with Artificial Intelligence and Machine Learning Breakthroughs in Imaging and Diagnosis: Literature Review
This review unveils artificial intelligence / machine learning innovations transforming breast cancer imaging, elevating diagnostic precision, efficiency, and personalized oncology outcomes.