Akmeiir E. Kaliyeva
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Akmeiir E. Kaliyeva has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Akmaral Baspakova
Department of Epidemiology, West Kazakhstan Marat Ospanov Medical University, Aktobe, Kazakhstan
3 shared publications - Saulesh Seitzhanovna Kurmangaliyeva
Department of Microbiology, Virology and Immunology, West Kazakhstan Marat Ospanov Medical University, Aktobe, Kazakhstan
2 shared publications - Aigerim A. Umbetova
Department for Scientific Work, West Kazakhstan Marat Ospanov Medical University, Aktobe, Kazakhstan
1 shared publication Aizhan Alkaubayeva
Department of Internal Diseases, Kazakh National Medical University Named After S.D. Asfendiyarov Almaty
1 shared publicationDiana Kunzharikova
Department of Epidemiology, West Kazakhstan Marat Ospanov Medical University, Aktobe, 030012
1 shared publicationGulden Yelgondina
Dean's Office, School of General Medicine-2, Asfendiyarov Kazakh National Medical University, Almaty, Kazakhstan
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Wolters Kluwer Health in West Kazakhstan Medical Journal
- Vol. 68 (4) , 399-415
Machine-learning-based Screening for Diabetes Using Population-level Sociodemographic, Behavioral, and Anthropometric Factors
A BSTRACT: Introduction: Scalable population-based screening tools are needed to identify individuals at high risk of undiagnosed or existing diabetes. Machine-learning approaches can capture complex nonlinear relationships among routinely collected risk factors and may improve screening-oriented risk stratification. Methods: We developed a supervised machine-learning model to predict diabetes status using a population-based cross-sectional dataset from West Kazakhstan derived from the WHO STEPwise survey (2021–2022). The analytical dataset included 4800 adults aged 18–69 years. Diabetes was defined according to standardized clinical and self-reported criteria, yielding a prevalence of 15.4% (739/4800). Predictor variables included sociodemographic, behavioral, and anthropometric characteristics, including age, sex, education, marital status, employment status, smoking, alcohol consumption, physical inactivity, high salt intake, body mass index (BMI), and waist circumference. A class-weighted Random Forest classifier was trained using stratified data splitting to preserve the original class distribution. Model performance was primarily assessed using precision–recall analysis, together with receiver operating characteristic–area under curve, calibration analysis, comparisons with baseline models, and repeated cross-validation. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The model generated probability-based estimates of diabetes status for screening-oriented risk stratification. Despite the class imbalance and relatively low prevalence of diabetes, the model achieved an average precision of approximately 0.31, indicating meaningful discriminative performance. SHAP analysis identified age, BMI, and waist circumference as the strongest contributors to the predicted probability of diabetes. The model was implemented as an interactive web-based tool providing real-time probability estimates for screening and educational purposes rather than diagnostic decision-making. Conclusion: This explainable Random Forest model, based on routinely collected population-level risk factors, may support screening-oriented diabetes risk stratification in community settings. Its implementation as an interactive web-based tool enables transparent, real-time risk estimation for preventive and educational purposes. Further external validation and probability recalibration are warranted before clinical implementation requiring reliable absolute risk estimates.
- 1 September 2026
- Published by Wolters Kluwer Health in West Kazakhstan Medical Journal
- Vol. 68 (4) , 399-415
Open AccessMachine-learning-based Screening for Diabetes Using Population-level Sociodemographic, Behavioral, and Anthropometric Factors
A BSTRACT: Introduction: Scalable population-based screening tools are needed to identify individuals at high risk of undiagnosed or existing diabetes. Machine-learning approaches can capture complex nonlinear relationships among routinely collected risk factors and may improve screening-oriented risk stratification. Methods: We developed a supervised machine-learning model to predict diabetes status using a population-based cross-sectional dataset from West Kazakhstan derived from the WHO STEPwise survey (2021–2022). The analytical dataset included 4800 adults aged 18–69 years. Diabetes was defined according to standardized clinical and self-reported criteria, yielding a prevalence of 15.4% (739/4800). Predictor variables included sociodemographic, behavioral, and anthropometric characteristics, including age, sex, education, marital status, employment status, smoking, alcohol consumption, physical inactivity, high salt intake, body mass index (BMI), and waist circumference. A class-weighted Random Forest classifier was trained using stratified data splitting to preserve the original class distribution. Model performance was primarily assessed using precision–recall analysis, together with receiver operating characteristic–area under curve, calibration analysis, comparisons with baseline models, and repeated cross-validation. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The model generated probability-based estimates of diabetes status for screening-oriented risk stratification. Despite the class imbalance and relatively low prevalence of diabetes, the model achieved an average precision of approximately 0.31, indicating meaningful discriminative performance. SHAP analysis identified age, BMI, and waist circumference as the strongest contributors to the predicted probability of diabetes. The model was implemented as an interactive web-based tool providing real-time probability estimates for screening and educational purposes rather than diagnostic decision-making. Conclusion: This explainable Random Forest model, based on routinely collected population-level risk factors, may support screening-oriented diabetes risk stratification in community settings. Its implementation as an interactive web-based tool enables transparent, real-time risk estimation for preventive and educational purposes. Further external validation and probability recalibration are warranted before clinical implementation requiring reliable absolute risk estimates.
- Open Access
- 25 June 2025
- Published by Knowledge E DMCC in Journal of Environmental Treatment Techniques
- Vol. 13 (2) , 136-148
Study of Bioethanol Accumulation in Dairy Whey Using Immobilized Yeast Cells
Dairy whey, that is a byproduct from cheese production, is not only an environmental challenge, but also an energy renewable enabler. This study investigates the accumulation of bioethanol in dairy whey using immobilized yeast cells. The aim was to test the ethanol production by the immobilized yeast cultures onto different sorbents. Yeast strains Saccharomyces cerevisiae AI1, Kluyveromyces marxianus AC1, and Rhodotorula lactose SR were employed singly and in co-cultures and immobilized onto sodium alginate, polyvinyl alcohol, and carrageenan matrices. Sodium alginateentrapped yeast cells lost their ethanol-accumulating power whereas polyvinyl alcoholand carrageenan-immobilized yeast cells exhibited good bioethanol productivity. The highest ethanol yields were attained from S. cerevisiae AI1 were 2.55% and 2.42% after 48 hours, while K. marxianus AC1 produced 2.25% and 2.62% under the same conditions. These results demonstrate that immobilized yeast cell technology offers a promising approach for sustainable bioethanol production from dairy industry.
- 25 June 2025
- Published by Knowledge E DMCC in Journal of Environmental Treatment Techniques
- Vol. 13 (2) , 136-148
Open AccessStudy of Bioethanol Accumulation in Dairy Whey Using Immobilized Yeast Cells
Dairy whey, that is a byproduct from cheese production, is not only an environmental challenge, but also an energy renewable enabler. This study investigates the accumulation of bioethanol in dairy whey using immobilized yeast cells. The aim was to test the ethanol production by the immobilized yeast cultures onto different sorbents. Yeast strains Saccharomyces cerevisiae AI1, Kluyveromyces marxianus AC1, and Rhodotorula lactose SR were employed singly and in co-cultures and immobilized onto sodium alginate, polyvinyl alcohol, and carrageenan matrices. Sodium alginateentrapped yeast cells lost their ethanol-accumulating power whereas polyvinyl alcoholand carrageenan-immobilized yeast cells exhibited good bioethanol productivity. The highest ethanol yields were attained from S. cerevisiae AI1 were 2.55% and 2.42% after 48 hours, while K. marxianus AC1 produced 2.25% and 2.62% under the same conditions. These results demonstrate that immobilized yeast cell technology offers a promising approach for sustainable bioethanol production from dairy industry.
- Open Access
- 20 March 2025
- Published by Knowledge E DMCC in Journal of Environmental Treatment Techniques
- Vol. 13 (1) , 52-61
Patient Satisfaction with Laboratory Services: Current Trends and Strategies for Quality Improvement
Objectives patient satisfaction with the quality of laboratory services is a pivotal dimension in ensuring health care quality because it can affect the accuracy of diagnostic results, clinical decision-making, and overall trust in the health system. This review analyzes several critical factors that shape the perceptions of patients, including turnaround time, test accuracy, physician communication, easy access to services, and efficient delivery. The paper then considers trends such as automation, artificial intelligence, telemedicine and digital health integration, and how these new systems are affecting laboratory service quality and the patient experience. Additionally, this review explores mechanisms for quality improvement with a focus on accreditation and continuous quality management systems, ongoing professional education, and mechanisms to integrate patient feedback into systems level reform. Although substantial progress has been made, challenges, including workforce shortages, regulatory variability, and inequities in access to high-quality laboratory services, remain. Evidence-based interventions and patient-centered approaches are used to address these issues with the goal of improving service delivery and healthcare outcomes. This paper offers two important messages to those who influence and guide national policy, healthcare decisions, and development of clinical laboratories across the nation as we strive to change practice to meet new demand.
- 20 March 2025
- Published by Knowledge E DMCC in Journal of Environmental Treatment Techniques
- Vol. 13 (1) , 52-61
Open AccessPatient Satisfaction with Laboratory Services: Current Trends and Strategies for Quality Improvement
Objectives patient satisfaction with the quality of laboratory services is a pivotal dimension in ensuring health care quality because it can affect the accuracy of diagnostic results, clinical decision-making, and overall trust in the health system. This review analyzes several critical factors that shape the perceptions of patients, including turnaround time, test accuracy, physician communication, easy access to services, and efficient delivery. The paper then considers trends such as automation, artificial intelligence, telemedicine and digital health integration, and how these new systems are affecting laboratory service quality and the patient experience. Additionally, this review explores mechanisms for quality improvement with a focus on accreditation and continuous quality management systems, ongoing professional education, and mechanisms to integrate patient feedback into systems level reform. Although substantial progress has been made, challenges, including workforce shortages, regulatory variability, and inequities in access to high-quality laboratory services, remain. Evidence-based interventions and patient-centered approaches are used to address these issues with the goal of improving service delivery and healthcare outcomes. This paper offers two important messages to those who influence and guide national policy, healthcare decisions, and development of clinical laboratories across the nation as we strive to change practice to meet new demand.