Hayder A.H. Alawsi
Hayder A.H. Alawsi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Kuzmin
Southwest State University
2 shared publications - Andrey Butusov
Southwest State University
2 shared publications - Sergey Filist
Southwest State University
2 shared publications - A. Yu. Sukhomlinov
Southwest State University
1 shared publication - Elena Valeryevna Petrunina
Moscow Polytechnic University
1 shared publication L. V. Shulga
Southwest State University
1 shared publication
Latest Publications
- Open Access
- 28 June 2024
- Published by Southwest State University in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
- Vol. 14 (2) , 81-105
Multimodal risk classifier for cardiorespiratory diseases taking into account concomitant diseases and synergy effect
The purpose of the research is to develop a methodology for classifying complexly structured halftone images based on a multimodal approach using methods of morphological analysis, spectral analysis and neural network modeling.Methods. A method for classifying the contours of the boundaries of segments of a complexly structured image is described. The method is based on the fact that in chronic diseases of the pancreas, there is a violation of the integrity of the contour of its border and its waviness increases due to retractions and bulges caused by an alterative inflammatory process. The method includes the stages of normalization of ultrasound images and image segmentation with the selection of the contour of the object of interest. To classify the contour of a segment boundary, it is proposed to use Fourier analysis and neural network technologies. The method is illustrated using the example of classifying the contour of the border of the pancreas on its transcutaneous acoustic image.Results. Experimental studies of the proposed methods and means for classifying medical risk were carried out on diagnostic tasks according to the following classes: "chronic pancreatitis" – "without pathology". For experimental studies, video sequences of ultrasound images of the pancreas provided by an endoscopist were used. The purpose of the experimental studies was to analyze the classification quality indicators of image classifiers with class segments "Chronic pancreatitis" and "Without pathology". The training sample of video images (frames of video sequences) included 200 examples, one hundred from each class. The quality indicator "Sensitivity" of classification for two classes is 85,7%, the indicator "Specificity" is 87,1%.Conclusion. The use of the contour analysis method in classifiers of ultrasound images of the pancreas opens up new opportunities for accessible and objective diagnosis of pancreatic diseases, expanding the capabilities of intelligent clinical decision support systems.
- 28 June 2024
- Published by Southwest State University in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
- Vol. 14 (2) , 81-105
Open AccessMultimodal risk classifier for cardiorespiratory diseases taking into account concomitant diseases and synergy effect
The purpose of the research is to develop a methodology for classifying complexly structured halftone images based on a multimodal approach using methods of morphological analysis, spectral analysis and neural network modeling.Methods. A method for classifying the contours of the boundaries of segments of a complexly structured image is described. The method is based on the fact that in chronic diseases of the pancreas, there is a violation of the integrity of the contour of its border and its waviness increases due to retractions and bulges caused by an alterative inflammatory process. The method includes the stages of normalization of ultrasound images and image segmentation with the selection of the contour of the object of interest. To classify the contour of a segment boundary, it is proposed to use Fourier analysis and neural network technologies. The method is illustrated using the example of classifying the contour of the border of the pancreas on its transcutaneous acoustic image.Results. Experimental studies of the proposed methods and means for classifying medical risk were carried out on diagnostic tasks according to the following classes: "chronic pancreatitis" – "without pathology". For experimental studies, video sequences of ultrasound images of the pancreas provided by an endoscopist were used. The purpose of the experimental studies was to analyze the classification quality indicators of image classifiers with class segments "Chronic pancreatitis" and "Without pathology". The training sample of video images (frames of video sequences) included 200 examples, one hundred from each class. The quality indicator "Sensitivity" of classification for two classes is 85,7%, the indicator "Specificity" is 87,1%.Conclusion. The use of the contour analysis method in classifiers of ultrasound images of the pancreas opens up new opportunities for accessible and objective diagnosis of pancreatic diseases, expanding the capabilities of intelligent clinical decision support systems.
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 195-197
A Hybrid Risk Classifier for Community-Acquired Pneumonia with Descriptors Derived from the Analysis of the Synchrony of Systemic Rhythms and the Electrical Activity of the Respiratory Muscles
The aim of the study is to improve the quality of prediction and early diagnosis of community-acquired pneumonia based on methods and models of intellectual support for the analysis of the synchrony of systemic rhythms, extracted from cardiac signals and signals of the electrical activity of the respiratory muscles. Theoretical issues of prediction and early diagnosis of community-acquired pneumonia based on the analysis of systemic rhythms and their synchronicity parameters have been studied. For this, hierarchical systems of intelligent agents were used, the inputs of which are descriptors obtained from the analysis of the cardiovascular system, the respiratory system, as well as descriptors characterizing the synchronism of systemic rhythms in these systems. As a result of the study, a hybrid classifier was developed to determine the individual risk of community-acquired pneumonia, an automated system was developed to determine descriptors for intelligent agents included in the classifier, and experimental studies were carried out to predict the risk of community-acquired pneumonia using the developed automated complex.
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 195-197
A Hybrid Risk Classifier for Community-Acquired Pneumonia with Descriptors Derived from the Analysis of the Synchrony of Systemic Rhythms and the Electrical Activity of the Respiratory Muscles
The aim of the study is to improve the quality of prediction and early diagnosis of community-acquired pneumonia based on methods and models of intellectual support for the analysis of the synchrony of systemic rhythms, extracted from cardiac signals and signals of the electrical activity of the respiratory muscles. Theoretical issues of prediction and early diagnosis of community-acquired pneumonia based on the analysis of systemic rhythms and their synchronicity parameters have been studied. For this, hierarchical systems of intelligent agents were used, the inputs of which are descriptors obtained from the analysis of the cardiovascular system, the respiratory system, as well as descriptors characterizing the synchronism of systemic rhythms in these systems. As a result of the study, a hybrid classifier was developed to determine the individual risk of community-acquired pneumonia, an automated system was developed to determine descriptors for intelligent agents included in the classifier, and experimental studies were carried out to predict the risk of community-acquired pneumonia using the developed automated complex.
- 5 July 2023
- Published by Voronezh Institute of High Technologies in МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ
- Vol. 11 (3(42)) , 16-17
Neural fuzzy networks for remote monitoring systems for outpatients with respiratory diseases
В статье предложен решающий модуль для контроля функционального состояния системы дыхания, обеспечивающий интеллектуальную поддержку при принятии решений медицинским персоналом по госпитализации пациента. Для контроля степени тяжести внебольничной пневмонии на основе интернет-технологий разработан гибридный многоагентный классификатор со структурой, включающий сегменты факторов риска, связанные со «своей» системой нечеткого логического вывода, и метаклассификатор, предназначенный для агрегации решений этих систем, позволяющий осуществлять мониторинг функционального состояния системы дыхания пациента в удаленном интерактивном режиме. Разработана пятислойная нечеткая сеть, предназначенная для классификации степени тяжести внебольничной пневмонии по входному вектору, основанная на алгоритме Мамдани-Ларсена, позволяющая оценить степень тяжести внебольничной пневмонии на шкале 0–1 по сегменту факторов риска, используемому в традиционных шкалах риска пневмонии. Синтезирован нейронечеткий классификатор тяжести внебольничной пневмонии, построенный на основе шкалы риска пневмонии CRB-65. Сформирована база нечетких решающих правил системы нечеткого логического вывода и определены функции принадлежности для входных и выходных переменных в выбранном сегменте факторов риска. Апробация нейронечеткой модели гибридного классификатора степени тяжести внебольничной пневмонии проведена на экспериментальной группе из 200 пациентов, больных внебольничной пневмонией различной степени тяжести. Модель классификатора на контрольной выборке продемонстрировала диагностическую чувствительность 90 % и диагностическую специфичность 86 %. Осуществлено сопоставление результатов полученной модели риска внебольничной пневмонии с результатами экспертного оценивания и результатами, полученными на известных регрессионных моделях. Показатели качества классификации синтезированного нейронечеткого классификатора позволяют рекомендовать его для телекоммуникационных систем дистанционного мониторинга степени тяжести внебольничной пневмонии. The article proposes a decisive module for monitoring the functional state of the respiratory system, which provides intellectual support in making decisions by medical personnel regarding the hospitalization of a patient. To control the severity of community-acquired pneumonia, a hybrid multi-agent classifier has been developed based on Internet technologies with a structure that includes segments of risk factors associated with “its own” fuzzy inference system. A metaclassifier has been designed to aggregate the solutions of these systems, which allows monitoring the functional state of the patient breathing system in remote interactive mode. Based on the Mamdani-Larsen algorithm, a five-layer fuzzy network has been developed for classifying the severity of community-acquired pneumonia according to the input vector, which allows estimating the severity of community-acquired pneumonia on a 0–1 scale according to the segment of risk factors used in traditional pneumonia risk scales. A neuro-fuzzy classifier of community-acquired pneumonia severity based on the CRB-65 pneumonia risk scale was synthesized. The base of fuzzy decision rules of the fuzzy inference system is formed and the membership functions for input and output variables in the selected segment of risk factors are determined. The neuro-fuzzy model of a hybrid classifier of the severity of community-acquired pneumonia was tested using an experimental group of 200 patients with community-acquired pneumonia of varying severity. The classifier model on the control sample demonstrated a diagnostic sensitivity of 90 % and diagnostic specificity of 86 %. The results of the obtained risk model for community-acquired pneumonia were compared with the results of expert evaluation and the results obtained on known regression models. The quality indicators of the classification of the synthesized neuro-fuzzy classifier make it possible to recommend it for telecommunication systems for remote monitoring of community-acquired pneumonia severity.
- 5 July 2023
- Published by Voronezh Institute of High Technologies in МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ
- Vol. 11 (3(42)) , 16-17
Neural fuzzy networks for remote monitoring systems for outpatients with respiratory diseases
В статье предложен решающий модуль для контроля функционального состояния системы дыхания, обеспечивающий интеллектуальную поддержку при принятии решений медицинским персоналом по госпитализации пациента. Для контроля степени тяжести внебольничной пневмонии на основе интернет-технологий разработан гибридный многоагентный классификатор со структурой, включающий сегменты факторов риска, связанные со «своей» системой нечеткого логического вывода, и метаклассификатор, предназначенный для агрегации решений этих систем, позволяющий осуществлять мониторинг функционального состояния системы дыхания пациента в удаленном интерактивном режиме. Разработана пятислойная нечеткая сеть, предназначенная для классификации степени тяжести внебольничной пневмонии по входному вектору, основанная на алгоритме Мамдани-Ларсена, позволяющая оценить степень тяжести внебольничной пневмонии на шкале 0–1 по сегменту факторов риска, используемому в традиционных шкалах риска пневмонии. Синтезирован нейронечеткий классификатор тяжести внебольничной пневмонии, построенный на основе шкалы риска пневмонии CRB-65. Сформирована база нечетких решающих правил системы нечеткого логического вывода и определены функции принадлежности для входных и выходных переменных в выбранном сегменте факторов риска. Апробация нейронечеткой модели гибридного классификатора степени тяжести внебольничной пневмонии проведена на экспериментальной группе из 200 пациентов, больных внебольничной пневмонией различной степени тяжести. Модель классификатора на контрольной выборке продемонстрировала диагностическую чувствительность 90 % и диагностическую специфичность 86 %. Осуществлено сопоставление результатов полученной модели риска внебольничной пневмонии с результатами экспертного оценивания и результатами, полученными на известных регрессионных моделях. Показатели качества классификации синтезированного нейронечеткого классификатора позволяют рекомендовать его для телекоммуникационных систем дистанционного мониторинга степени тяжести внебольничной пневмонии. The article proposes a decisive module for monitoring the functional state of the respiratory system, which provides intellectual support in making decisions by medical personnel regarding the hospitalization of a patient. To control the severity of community-acquired pneumonia, a hybrid multi-agent classifier has been developed based on Internet technologies with a structure that includes segments of risk factors associated with “its own” fuzzy inference system. A metaclassifier has been designed to aggregate the solutions of these systems, which allows monitoring the functional state of the patient breathing system in remote interactive mode. Based on the Mamdani-Larsen algorithm, a five-layer fuzzy network has been developed for classifying the severity of community-acquired pneumonia according to the input vector, which allows estimating the severity of community-acquired pneumonia on a 0–1 scale according to the segment of risk factors used in traditional pneumonia risk scales. A neuro-fuzzy classifier of community-acquired pneumonia severity based on the CRB-65 pneumonia risk scale was synthesized. The base of fuzzy decision rules of the fuzzy inference system is formed and the membership functions for input and output variables in the selected segment of risk factors are determined. The neuro-fuzzy model of a hybrid classifier of the severity of community-acquired pneumonia was tested using an experimental group of 200 patients with community-acquired pneumonia of varying severity. The classifier model on the control sample demonstrated a diagnostic sensitivity of 90 % and diagnostic specificity of 86 %. The results of the obtained risk model for community-acquired pneumonia were compared with the results of expert evaluation and the results obtained on known regression models. The quality indicators of the classification of the synthesized neuro-fuzzy classifier make it possible to recommend it for telecommunication systems for remote monitoring of community-acquired pneumonia severity.