Қазақ ұлттық қыздар педагогикалық университеті / Казахский национальный женский педагогический университет

Постоянный URI для этого сообществаhttps://cris.qyzpu.kz/handle/123456789/1

Просмотр

Результаты поиска

Показано: 1 - 10 из 14

Некоторые метрики заблокированы вашими
настройками согласия
Using The Machine Learning Method in Portable ECG Monitoring System to Identify Diagnostically Complex Heart Diseases
(2023-06-29)
Aidana K. Yerkebay
;
Zhadyra N. Alimbayeva
;
Chingiz A. Alimbayev
;
Aiman K. Ozhikenova
;
Nurlan A. Bayanbay
Due to the high level of disability and death caused by heart diseases worldwide, the problem of combating cardiovascular diseases is becoming more and more important and relevant. In fact, one of the leading causes of death worldwide has long been cardiovascular disease, according to the World Health Organization. Among heart diseases, the most dangerous to life is myocardial infarction. In connection with the rapid morbidity, early diagnosis of this disease is one of the topical problems of modern public health care. At present, although there is a wide range of different statistical, math methods and computer tools for the processing of cardiological information, the task of increasing the accuracy of methods for the analysis of electrocardiograms and diagnostic tools in this field of study remained relevant. Taking into account the imperfect tools and systems for diagnosing heart diseases, as well as the human factor, the lack of a method that can help doctors to diagnose myocardial infarction early requires the development of new diagnostic information methods. This article presents a neural network analysis methodology for diagnosing myocardial infarction based on the joint analysis of direct and reverse signs of myocardial infarction from electrocardiographic information obtained from a portable cardiac analyzer.
Цитирования (OpenAlex) 2Цитирования (OpenCitations) 1
Некоторые метрики заблокированы вашими
настройками согласия
Development of an atrioventricular block prediction of method for portable heart monitoring system
(Kharkiv State Academy of Physical Culture, 2022-06-30)
Ainur Bekbay
;
Zhadyra N. Alimbayeva
;
Chingiz A. Alimbayev
;
Nurlan A. Bayanbay
;
Кassymbek Ozhikenov
The object of the study is a portable system that allows real-time monitoring of the state of the heart for the timely provision of medical care. The task of detecting atrioventricular (AV) blocks in the conditions of free motor activity of the patient is being solved. To develop a method for detecting AV block, models of the electrical activity of the heart were used to take into account the spatiotemporal organization of the process of spreading excitation, analyze the dynamics of the behavior of the cardiovascular systems (CVS) for any value of the period of atrial excitation, and assess the degree of fitness of the CVS. The proposed method made it possible to determine the heart rate (HR) at which the development of AV block is possible. AV block of the III degree – heart rate 304 bpm; AV block of the II degree with the loss of half of the impulses – heart rate 260 bpm; AV block II degree with loss of individual impulses – heart rate 234 bpm; AV block of the 1st degree – heart rate 200 bpm. Prediction of AV block allows assessing the degree of “training” of the patient’s heart. The obtained quantitative results are consistent with the heart rate values known to modern health care. The developed method was implemented on the basis of a portable ECG monitoring system previously developed by the authors. Tests of the portable ECG monitoring system indicate an increase in the sensitivity and specificity of diagnosing cardiac arrhythmia and confirm the achievement of the goal of this study: improving the efficiency of diagnostics and expanding the functionality of the portable ECG monitoring system
Цитирования (OpenAlex) 1
Некоторые метрики заблокированы вашими
настройками согласия
МАШИНАЛЫҚ ОҚЫТУ ӘДІСІНІҢ КӨМЕГІМЕН ЖҮРЕК АУРУЫН БОЛЖАУ
(Mukhametzhan Tynyshbayev ALT University, 2022-10-28)
Zhadyra N. Alimbayeva
;
Кassymbek Ozhikenov
;
Айдана Еркебай
;
Chingiz A. Alimbayev
;
Aiman K. Ozhikenova
Мүгедектік пен өлім деңгейінің жоғары болуына байланысты жүрек-қан тамырлары ауруларын дер кезінде анықтау маңызды мәселе болып отыр. Бұл мақалада машиналық оқыту алгоритмдерін қолданып электрокардиосигналды өңдеу арқылы жүрек ауруын болжауға зерттеу жүргізілген. Жалпы, зерттеу барысында әртүрлі машиналық оқыту алгоритмдерімен 50000-нан астам сандық эксперимент жүргізілді. Салыстырмалы талдау негізінде машиналық оқытудың үлгілері мен әдістері таңдалып, ең жоғары жақсы көрсеткіш нәтиже берді. Зерттеуге келесі әдістер қолданылды: тірек векторлық машинасы, шешімдер ағашы, Байес классификаторы, логистикалық регрессия, k-жақын көршілер, кездейсоқ орман, терең нейрондық желілер. Таңдалған модельдер параметрлерді анықтау және тиімді қолдану үшін ұсынылды.
Некоторые метрики заблокированы вашими
настройками согласия
Wearable ECG Device and Machine Learning for Heart Monitoring
(Multidisciplinary Digital Publishing Institute, 2024-06-28)
Zhadyra N. Alimbayeva
;
Chingiz A. Alimbayev
;
Кassymbek Ozhikenov
;
Nurlan A. Bayanbay
;
Aiman K. Ozhikenova
With cardiovascular diseases (CVD) remaining a leading cause of mortality, wearable devices for monitoring cardiac activity have gained significant, renewed interest among the medical community. This paper introduces an innovative ECG monitoring system based on a single-lead ECG machine, enhanced using machine learning methods. The system only processes and analyzes ECG data, but it can also be used to predict potential heart disease at an early stage. The wearable device was built on the ADS1298 and a microcontroller STM32L151xD. A server module based on the architecture style of the REST API was designed to facilitate interaction with the web-based segment of the system. The module is responsible for receiving data in real time from the microcontroller and delivering this data to the web-based segment of the module. Algorithms for analyzing ECG signals have been developed, including band filter artifact removal, K-means clustering for signal segmentation, and PQRST analysis. Machine learning methods, such as isolation forests, have been employed for ECG anomaly detection. Moreover, a comparative analysis with various machine learning methods, including logistic regression, random forest, SVM, XGBoost, decision forest, and CNNs, was conducted to predict the incidence of cardiovascular diseases. Convoluted neural networks (CNN) showed an accuracy of 0.926, proving their high effectiveness for ECG data processing.
Цитирования (OpenAlex) 55Цитирования (OpenCitations) 30
Некоторые метрики заблокированы вашими
настройками согласия
AN EARLY WARNING SYSTEM FOR HOSPITALS USING A WEARABLE ECG DEVICE AND MACHINE LEARNING
(Mukhametzhan Tynyshbayev ALT University, 2024-09-26)
Zhadyra N. Alimbayeva
;
Chingiz A. Alimbayev
;
Dilfuza Akhmedova
;
Кassymbek Ozhikenov
;
Zhansulu Ualieva
According to the World Health Organization, many clinical errors in medical practice occur due to incomplete or untimely access to patient information. The introduction of nurse call systems significantly improves communication between medical staff and patients, increases response efficiency and patient satisfaction. Traditional nurse call systems based on patients' manual requests for medical care are insufficient to prevent unforeseen medical situations. This article proposes a new approach based on the wearable ECG devices developed by the authors for monitoring the cardiovascular system of patients. This approach uses machine learning techniques to analyze data from wearable ECG devices, which allows timely detection of dangerous patient conditions and necessary medical interventions. The proposed early warning system for hospitals performs various important functions, such as continuous recording of the electrical activity of the heart, preprocessing data to reduce noise and improve accuracy, extracting key parameters for further analysis, forming diagnostic indicators and a comprehensive assessment of the condition of the heart to identify potential anomalies.
Некоторые метрики заблокированы вашими
настройками согласия
ЦИФРОВОЙ ЭСТЕЗИОМЕТР ДЛЯ ОЦЕНКИ ЧУВСТВИТЕЛЬНОСТИ ПОЛОСТИ РТА
(Mukhametzhan Tynyshbayev ALT University, 2025-06-03)
Akzhol Nurdanali
;
Chingiz A. Alimbayev
;
Кassymbek Ozhikenov
;
Zhadyra N. Alimbayeva
;
Сана Абылгазинова
Съемные зубные протезы играют важную роль в восстановлении как функции, так и эстетики у пациентов с потерей зубов. Обеспечение надлежащего соответствия между протезом, анатомией полости рта и чувствительностью слизистой оболочки имеет решающее значение для комфорта пациента и эффективности протеза. Частой причиной дискомфорта и последующего отторжения этих протезов является боль, испытываемая под ними. Для решения этой проблемы в процессе изготовления применяется мягкая подкладка из эластичного материала, которая равномерно распределяет давление, оказываемое протезом. Правильный выбор толщины подкладки имеет важное значение, поскольку она напрямую влияет на комфорт и эффективность протеза. В настоящее время этот выбор во многом зависит от клинического опыта стоматолога и субъективной обратной связи пациента. В этом исследовании мы представляем новое устройство, предназначенное для объективной оценки чувствительности полости рта, что облегчает оптимизацию толщины мягкой подкладки в съемных зубных протезах. Были разработаны два лабораторных прототипа с использованием микроконтроллеров STM32f103c8t6 и Arduino Nano, каждый из которых включал различные методики измерения.
Некоторые метрики заблокированы вашими
настройками согласия
Comparative Analysis of Deep Learning Architectures for Osteoporosis Detection in Knee Radiographs: From Custom CNN to Transfer Learning
(2026-01-01)
Assiya Boltaboyeva
;
Zhanel Baigarayeva
;
Баглан Иманбек
;
Кassymbek Ozhikenov
;
Zhadyra N. Alimbayeva
Osteoporosis is a systemic skeletal disorder affecting millions worldwide, characterized by decreased bone mineral density and increased fracture risk. Early and accurate detection from knee radiographs remains clinically challenging due to the subtlety of trabecular changes and limited availability of annotated datasets. This study presents a comparative analysis of three deep learning architectures — a custom Convolutional Neural Network (CNN), ResNet50 with partial fine-tuning, and EfficientNet-B3 with full fine-tuning — for binary classification of knee X-ray images into Normal and Osteoporosis categories. Methods. The Osteoporosis Knee X-ray Dataset (372 images) was used as the benchmark. All models were trained with Contrast-Limited Adaptive Histogram Equalization (CLAHE)-based contrast enhancement, geometric and occlusion augmentations, and a class-weighted cross-entropy loss function to address class imbalance. Early stopping and L2 regularization were applied to improve generalization. Results. Experimental results demonstrate that EfficientNet-B3 achieved the highest overall performance with an accuracy of 80.00%, recall of 89.74%, and F1-score of 82.35%, making it the most suitable model for clinical screening where sensitivity is prioritized. Custom CNN attained the highest Receiver Operating Characteristic – Area Under the Curve of 87.75%, indicating strong discriminative capacity despite its compact architecture. Conclusions. ResNet50 with partial fine-tuning showed competitive precision (76.32%) and Area Under the Curve (86.89%). These findings provide insights into the trade-offs between model complexity, transfer learning strategy, and diagnostic performance for small-scale medical imaging tasks.
Некоторые метрики заблокированы вашими
настройками согласия
Development and Pilot Evaluation of a Wearable 12-Lead ECG System for Multilead Feature Analysis in Individuals with Different Glycemic Status
(Multidisciplinary Digital Publishing Institute, 2026-03-04)
Chingiz A. Alimbayev
;
Zhadyra N. Alimbayeva
;
Кassymbek Ozhikenov
;
Kairat Karibayev
;
Zhansila Orynbay
Type 2 diabetes mellitus and prediabetes often develop silently and may remain undiagnosed for years. This is particularly relevant in regions where laboratory-based screening is not always readily accessible. Against this background, the present work explores whether multilead electrocardiography can provide physiologically meaningful markers potentially associated with disturbances in glucose metabolism. We developed and tested an upgraded wearable 12-lead ECG system capable of synchronized multichannel recording under controlled conditions. ECG signals were acquired in sitting and standing positions, with a sampling frequency of 500 Hz and a recording duration of one minute per posture. The hardware architecture included a high resolution analog front-end and wireless data transmission; the accompanying software provided acquisition control, preprocessing, visualization, and data storage within a unified framework. Signal processing focused on the extraction of rhythm-related and morphological parameters, with particular attention to ventricular repolarization indices. QT interval, heart rate-corrected QT (QTc), and QT dispersion (QTd) were calculated across leads, as these parameters are known to reflect heterogeneity of repolarization and autonomic influences on myocardial electrophysiology. The analysis was structured to ensure reproducible boundary detection and systematic feature formation rather than isolated parameter measurement. The study had a pilot character and included a limited and unbalanced sample (healthy n = 10; prediabetes n = 1; T2DM n = 1). For this reason, the results are presented descriptively and should be regarded as preliminary observations. In representative cases, differences in QT-related indices were noted between categories of glycemic status; however, the potential influence of age, sex, and other confounders cannot be excluded. A pilot expert comparison of T-wave end detection demonstrated close agreement between the automated algorithm and cardiologist assessment (mean ΔTend approximately -1 to -2 ms; MAE 10-24 ms). Diagnostic performance metrics such as ROC/AUC, sensitivity, and specificity were not calculated at this stage, as validation in a larger cohort with biochemical confirmation (HbA1c, OGTT) is required. The study demonstrates the technical feasibility of combining synchronized 12-lead wearable acquisition with structured multilead repolarization analysis. The proposed system should therefore be considered a research platform intended to support further clinical validation and methodological development rather than a finished screening solution.
Цитирования (OpenAlex) 2
Некоторые метрики заблокированы вашими
настройками согласия
Electrocardiographic Signatures of Dysglycaemia: Mechanistic Foundations, Digital Biomarkers, and Artificial Intelligence for Non-Invasive Diabetes Risk Stratification
(Multidisciplinary Digital Publishing Institute, 2026-03-18)
Chingiz A. Alimbayev
;
Zhadyra N. Alimbayeva
;
Kassymbek Ozhikenov
;
Kairat Karibayev
;
Zhansila Orynbay
Diabetes mellitus is projected to affect more than 1.3 billion people worldwide by 2050, with millions remaining undiagnosed or in a prediabetic state. Cardiovascular complications account for nearly half of diabetes-related deaths, highlighting the need for scalable tools capable of identifying metabolic dysregulation before irreversible cardiac damage develops. This review synthesizes current mechanistic, clinical, and computational evidence linking diabetes to cardiac electrophysiological remodeling and examines electrocardiography (ECG) as a non-invasive modality for early detection of dysglycaemia. Chronic hyperglycaemia, insulin resistance, oxidative stress, microvascular dysfunction, and cardiac autonomic neuropathy collectively contribute to measurable ECG alterations, including QT/QTc prolongation, increased QT dispersion, changes in Tp–e indices, and reduced heart rate variability. These changes often precede overt cardiovascular disease and correlate with glycaemic burden and diabetes duration. Recent advances in signal processing and artificial intelligence have expanded the diagnostic potential of ECG. Both classical machine learning approaches and large-scale deep learning models demonstrate that ECG contains latent signatures associated with incident type 2 diabetes and glycaemic status. Despite promising results, heterogeneity in study design, limited representation of prediabetes, and lack of standardized validation frameworks remain major barriers to clinical translation. Prospective, multi-ethnic studies are needed to establish ECG-based screening as a reliable component of early diabetes detection strategies.
Цитирования (OpenAlex) 1
Некоторые метрики заблокированы вашими
настройками согласия
Prediction of Percutaneous Coronary Intervention from Clinical and ECG Data Using Machine Learning: A Retrospective Single-Center Observational Study
(Multidisciplinary Digital Publishing Institute, 2026-05-06)
Zhadyra N. Alimbayeva
;
Chingiz A. Alimbayev
;
Kassymbek Ozhikenov
;
Kairat Karibayev
;
Aiman K. Ozhikenova
The aim of this study was to evaluate the feasibility of predicting percutaneous coronary intervention (PCI) based on clinical, laboratory, and electrocardiographic data available at various stages of hospitalization. A retrospective single-center study was conducted, including 137 patients with suspected coronary artery disease. The fact that PCI was performed during the current hospitalization was considered as the endpoint. Taking into account the temporary availability of data, three sets of signs were formed: basic (SAFE), including indicators available at admission; clinical (CLINICAL); and extended (EXTENDED), supplemented with glycemic parameters. Logistic regression, random forest, and gradient boosting were used to build the models. The assessment was carried out using repeated stratified cross-validation (5 × 10). The main metrics were ROC-AUC, PR-AUC, accuracy and F1-measure. The models demonstrated moderate predictive ability. The basic model (SAFE) showed a ROC-AUC of 0.734 ± 0.092, while the best results were achieved using an extended model based on a random forest (ROC-AUC 0.755 ± 0.079). The addition of glycemic parameters provided a moderate improvement in prediction quality. In the logistic regression, the most significant predictor was the presence of type 2 diabetes mellitus (OR = 7.36; p < 0.001). The results indicate the potential for using non-invasive data to assess the likelihood of PCI in the early stages of hospitalization. However, the models show moderate accuracy and require further validation on larger and more independent samples.

Қазақ ұлттық қыздар педагогикалық университеті / Казахский национальный женский педагогический университет

Просмотр

Фильтры

Настройки

Сортировать по

результатов на странице

Результаты поиска

QyzPU CRIS

Университет

Данные