Pub Date : 2022-06-23DOI: 10.2174/18750362-v15-e220623-2021-14
Nityendra Shukla, N. Srivastava, Aditya Trivedi, P. Seth, P. Srivastava
Osteoarthritis (OA) is a degenerative joint disease which is the leading cause for physical disability among the adult population and yet the mechanisms responsible for the development and progression are not well understood. Since it has no curative solutions, treatment is limited to symptomatic targeting and improving quality of life. There is a lack of disease-modifying therapeutics and non-surgical intervention options to prevent the progression of disease. Risk factors range from systemic (e.g. age, sex, genetics, obesity) to biochemical (e.g. joint injury, muscle weakness, sport). The prevalence of OA is ever increasing due to the ageing global population and the obesity epidemic. Since OA exhibits strong genetic predisposition and a complex pathogenesis, we applied an in silico network biology approaches to identify a candidate gene using a protein-protein interaction (PPI) network of OA, which may be an important aspect of disease pathogenesis and assist us in furthering our understanding of the development and progression of the disease as well as identify a drug-lead for the treatment of joint-pain associated with OA and improving quality of life in patients without lasting side effects. Our findings suggest that phytochemical compounds may be promising candidates for multi-target application against OA and will assist in development of new molecules.
{"title":"In-silico Identification of Novel Drug Target for Osteoarthritis using Network Biology Approaches","authors":"Nityendra Shukla, N. Srivastava, Aditya Trivedi, P. Seth, P. Srivastava","doi":"10.2174/18750362-v15-e220623-2021-14","DOIUrl":"https://doi.org/10.2174/18750362-v15-e220623-2021-14","url":null,"abstract":"Osteoarthritis (OA) is a degenerative joint disease which is the leading cause for physical disability among the adult population and yet the mechanisms responsible for the development and progression are not well understood. Since it has no curative solutions, treatment is limited to symptomatic targeting and improving quality of life. There is a lack of disease-modifying therapeutics and non-surgical intervention options to prevent the progression of disease. Risk factors range from systemic (e.g. age, sex, genetics, obesity) to biochemical (e.g. joint injury, muscle weakness, sport). The prevalence of OA is ever increasing due to the ageing global population and the obesity epidemic. Since OA exhibits strong genetic predisposition and a complex pathogenesis, we applied an in silico network biology approaches to identify a candidate gene using a protein-protein interaction (PPI) network of OA, which may be an important aspect of disease pathogenesis and assist us in furthering our understanding of the development and progression of the disease as well as identify a drug-lead for the treatment of joint-pain associated with OA and improving quality of life in patients without lasting side effects. Our findings suggest that phytochemical\u0000 compounds may be promising candidates for multi-target application against OA and will assist in development of new molecules.","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47868198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-25DOI: 10.2174/1875036202114010144
P. Navarrete, María José Garzón, Sheila Lorente-Pozo, Salvador Mena-Mollá, M. Vento, F. Pallardó, J. Beltrán-García, R. Osca-Verdegal, E. García-López, J. García-Giménez
Neonatal sepsis is a heterogeneous condition affecting preterm infants whose underlying mechanisms remain unknown. The analysis of changes in the DNA methylation pattern can contribute to improving the understanding of molecular pathways underlying disease pathophysiology. Methylation EPIC 850K BeadChip technology is an excellent tool for genome-wide methylation analyses and the detection of differentially methylated regions (DMRs). The aim is to identify DNA methylation traits in complex diseases, such as neonatal sepsis, using data from Methylation EPIC 850K BeadChip arrays. Two different bioinformatic methods, DMRcate (a supervised approach) and mCSEA (an unsupervised approach), were used to identify DMRs using EPIC data from leukocytes of neonatal septic patients. Here, we describe with detail the implementation of both methods as well as their applicability, briefly discussing the results obtained for neonatal sepsis. Differences in methylation levels were observed in neonatal sepsis patients. Moreover, differences were identified between the two subsets of the disease: Early-Onset neonatal Sepsis (EOS) and Late-Onset Neonatal Sepsis (LOS). This approach by using DMRcate and mCSA helped us to gain insight into the intricate mechanisms that may drive EOS and LOS development and progression in newborns.
{"title":"Use of Two Complementary Bioinformatic Approaches to Identify Differentially Methylated Regions in Neonatal Sepsis","authors":"P. Navarrete, María José Garzón, Sheila Lorente-Pozo, Salvador Mena-Mollá, M. Vento, F. Pallardó, J. Beltrán-García, R. Osca-Verdegal, E. García-López, J. García-Giménez","doi":"10.2174/1875036202114010144","DOIUrl":"https://doi.org/10.2174/1875036202114010144","url":null,"abstract":"\u0000 \u0000 Neonatal sepsis is a heterogeneous condition affecting preterm infants whose underlying mechanisms remain unknown. The analysis of changes in the DNA methylation pattern can contribute to improving the understanding of molecular pathways underlying disease pathophysiology. Methylation EPIC 850K BeadChip technology is an excellent tool for genome-wide methylation analyses and the detection of differentially methylated regions (DMRs).\u0000 \u0000 \u0000 \u0000 The aim is to identify DNA methylation traits in complex diseases, such as neonatal sepsis, using data from Methylation EPIC 850K BeadChip arrays.\u0000 \u0000 \u0000 \u0000 Two different bioinformatic methods, DMRcate (a supervised approach) and mCSEA (an unsupervised approach), were used to identify DMRs using EPIC data from leukocytes of neonatal septic patients. Here, we describe with detail the implementation of both methods as well as their applicability, briefly discussing the results obtained for neonatal sepsis.\u0000 \u0000 \u0000 \u0000 Differences in methylation levels were observed in neonatal sepsis patients. Moreover, differences were identified between the two subsets of the disease: Early-Onset neonatal Sepsis (EOS) and Late-Onset Neonatal Sepsis (LOS).\u0000 \u0000 \u0000 \u0000 This approach by using DMRcate and mCSA helped us to gain insight into the intricate mechanisms that may drive EOS and LOS development and progression in newborns.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43322839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/18750362021140100138
V. Starenkiy, S. Artiukh, M. Ugryumov, V. Strilets, Serhii Chernysh, D. Chumachenko
More than 500,000 new cases of squamous cell carcinoma of the head and neck (SCCHN) are registered annually in the world. 7,036 new cases of the disease were registered in Ukraine during 2018, about 35% of patients did not live even a year from the date of diagnosis as a modern standard for the treatment of patients with inoperable locally advanced SCCHN, chemoradiation treatment in the classical dose fractionation mode with chemo modification with cisplatin is used by specialists. The objective of this study is to analyze the effectiveness of chemoradiation treatment with cisplatin and 5-fluorouracil in the treatment of patients with SCCHN using modern mathematical models. During the investigation we assessed the effectiveness of treatment in 108 patients with locally advanced SCCHN (stages III, IVa, IVb). The results of calculating the probabilities of complications were obtained using the method of multivariate classification based on the radial basis ANN. Analyzing the groups with different methods of chemo modification, we can conclude that the method of chrono-modulated radiochemotherapy with 5-fluorouracil and the chemoradiation therapy with cisplatin were almost equal in efficiency, namely 77% and 73.5%, respectively (p=0.35). Using the chemoradiation therapy with 5-fluorouracil in the treatment of patients with low somatic status and elderly patients is more expedient in contrast to the methods using cisplatin. The advantage of selection of mentioned treatment method is also confirmed by the results of calculating the average complication risks using the method of multivariate classification based on a radial-basis neural network.
{"title":"A Method for Assessing the Risks of Complications in Chemoradiation Treatment of Squamous Cell Carcinoma of the Head and Neck","authors":"V. Starenkiy, S. Artiukh, M. Ugryumov, V. Strilets, Serhii Chernysh, D. Chumachenko","doi":"10.2174/18750362021140100138","DOIUrl":"https://doi.org/10.2174/18750362021140100138","url":null,"abstract":"\u0000 \u0000 More than 500,000 new cases of squamous cell carcinoma of the head and neck (SCCHN) are registered annually in the world. 7,036 new cases of the disease were registered in Ukraine during 2018, about 35% of patients did not live even a year from the date of diagnosis as a modern standard for the treatment of patients with inoperable locally advanced SCCHN, chemoradiation treatment in the classical dose fractionation mode with chemo modification with cisplatin is used by specialists.\u0000 \u0000 \u0000 \u0000 The objective of this study is to analyze the effectiveness of chemoradiation treatment with cisplatin and 5-fluorouracil in the treatment of patients with SCCHN using modern mathematical models.\u0000 \u0000 \u0000 \u0000 During the investigation we assessed the effectiveness of treatment in 108 patients with locally advanced SCCHN (stages III, IVa, IVb). The results of calculating the probabilities of complications were obtained using the method of multivariate classification based on the radial basis ANN.\u0000 \u0000 \u0000 \u0000 Analyzing the groups with different methods of chemo modification, we can conclude that the method of chrono-modulated radiochemotherapy with 5-fluorouracil and the chemoradiation therapy with cisplatin were almost equal in efficiency, namely 77% and 73.5%, respectively (p=0.35).\u0000 \u0000 \u0000 \u0000 Using the chemoradiation therapy with 5-fluorouracil in the treatment of patients with low somatic status and elderly patients is more expedient in contrast to the methods using cisplatin. The advantage of selection of mentioned treatment method is also confirmed by the results of calculating the average complication risks using the method of multivariate classification based on a radial-basis neural network.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46886437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/1875036202114010036
I. Izonin, S. Babichev
The development of biological systems over billions of years has made them very difficult to understand. Biologists and clinical scientists try to understand various biological processes using different tools. However, vast amounts of data for analysis, complex multi-parameter interconnections between the data of a particular set, and hidden relationships between them significantly affect its processing and analysis. The latest advances in Artificial Intelligence (AI), mainly text mining, data mining, artificial neural networks, fuzzy logic, machine learning, and others, can significantly improve the processing of such data. In particular, it creates potential opportunities for doing high-impact investigations that can solve real-world tasks in the system biology branch. The peculiarities of biological data are that it has different types, formats, structures, and huge volumes, which significantly complicates its processing and analysis. Such processing should include models, methods, and tools for efficient storage and retrieval of various types of data; an effective conversion and consolidation of the data of multiple formats; fast optimization and transfer; reliable intellectual analysis to obtain valuable information; as well as informative data visualizations for future visual analysis or better human perception. All this necessitates combining existing and developing new, faster, and precision AI technics for future information discovery and knowledge engineering from such data.
{"title":"Advances in Text and Data Mining of Biological Data: Models, Methods and Applications","authors":"I. Izonin, S. Babichev","doi":"10.2174/1875036202114010036","DOIUrl":"https://doi.org/10.2174/1875036202114010036","url":null,"abstract":"The development of biological systems over billions of years has made them very difficult to understand. Biologists and clinical scientists try to understand various biological processes using different tools. However, vast amounts of data for analysis, complex multi-parameter interconnections between the data of a particular set, and hidden relationships between them significantly affect its processing and analysis. The latest advances in Artificial Intelligence (AI), mainly text mining, data mining, artificial neural networks, fuzzy logic, machine learning, and others, can significantly improve the processing of such data. In particular, it creates potential opportunities for doing high-impact investigations that can solve real-world tasks in the system biology branch. The peculiarities of biological data are that it has different types, formats, structures, and huge volumes, which significantly complicates its processing and analysis. Such processing should include models, methods, and tools for efficient storage and retrieval of various types of data; an effective conversion and consolidation of the data of multiple formats; fast optimization and transfer; reliable intellectual analysis to obtain valuable information; as well as informative data visualizations for future visual analysis or better human perception. All this necessitates combining existing and developing new, faster, and precision AI technics for future information discovery and knowledge engineering from such data.","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47122910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/18750362021140100130
A. Nechyporenko, R. Radutny, V. Alekseeva, G. Titova, V. Gargin
Application of automated analysis currently occupies a leading position in every field of science and technology. The aim of our study was to provide a complex automatic determination of morphological parameters for bone tissue in human paranasal sinuses. The study involved 50 patients aged 20 to 60, male and female without signs of inflammatory or other pathological processes in the paranasal sinuses (PNSs). Bone density in a high-contrast image of the section can be determined by fluctuations in colour intensity. Before cleaning, the image is blurred using the Gaussian function. As a result of this operation, the images become less clear and small details merge. An algorithm known as the Connie Border Detector has found widespread use. The curves denoting the contours can run vertically, horizontally or diagonally at different angles. Detection of the direction of curves passing vertically and horizontally is not complicated, and for curves of the diagonal direction, the Sobel operator is used, with the vertical direction Gy and horizontal Gx as the value of the first derivative. Selection of areas of bone tissue requires the assessment of brightness gradient along the long side of the area. For clarity, this operation was shown graphically. Within the scope of this work, we have developed a method for an automatic comprehensive assessment of the morphological structure of the PNSs walls with the measurement of bone density and thickness.
{"title":"Complex Automatic Determination of Morphological Parameters for Bone Tissue in Human Paranasal Sinuses","authors":"A. Nechyporenko, R. Radutny, V. Alekseeva, G. Titova, V. Gargin","doi":"10.2174/18750362021140100130","DOIUrl":"https://doi.org/10.2174/18750362021140100130","url":null,"abstract":"\u0000 \u0000 Application of automated analysis currently occupies a leading position in every field of science and technology.\u0000 The aim of our study was to provide a complex automatic determination of morphological parameters for bone tissue in human paranasal sinuses.\u0000 \u0000 \u0000 \u0000 The study involved 50 patients aged 20 to 60, male and female without signs of inflammatory or other pathological processes in the paranasal sinuses (PNSs).\u0000 \u0000 \u0000 \u0000 Bone density in a high-contrast image of the section can be determined by fluctuations in colour intensity. Before cleaning, the image is blurred using the Gaussian function. As a result of this operation, the images become less clear and small details merge. An algorithm known as the Connie Border Detector has found widespread use.\u0000 The curves denoting the contours can run vertically, horizontally or diagonally at different angles. Detection of the direction of curves passing vertically and horizontally is not complicated, and for curves of the diagonal direction, the Sobel operator is used, with the vertical direction Gy and horizontal Gx as the value of the first derivative. Selection of areas of bone tissue requires the assessment of brightness gradient along the long side of the area. For clarity, this operation was shown graphically.\u0000 \u0000 \u0000 \u0000 Within the scope of this work, we have developed a method for an automatic comprehensive assessment of the morphological structure of the PNSs walls with the measurement of bone density and thickness.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44188500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/18750362021140100108
Zeina Rayan, Marco Alfonse, Abdel-badeeh M. Salem
As sepsis is one of the life-threatening diseases, predicting sepsis with high accuracy could help save lives. Efficiency and accuracy of predicting sepsis can be enhanced through optimal feature selection. In this work, a support vector machine model is proposed to automatically predict a patient’s risk of sepsis based on physiological data collected from the ICU. The support vector machine algorithm that uses the extracted features has a great impact on sepsis prediction, which yields the accuracy of 0.73. Predicting sepsis can be accurately performed using the main vital signs and support vector machine.
{"title":"Predicting Sepsis in the Intensive Care Unit (ICU) through Vital Signs using Support Vector Machine (SVM)","authors":"Zeina Rayan, Marco Alfonse, Abdel-badeeh M. Salem","doi":"10.2174/18750362021140100108","DOIUrl":"https://doi.org/10.2174/18750362021140100108","url":null,"abstract":"\u0000 \u0000 As sepsis is one of the life-threatening diseases, predicting sepsis with high accuracy could help save lives.\u0000 \u0000 \u0000 \u0000 Efficiency and accuracy of predicting sepsis can be enhanced through optimal feature selection. In this work, a support vector machine model is proposed to automatically predict a patient’s risk of sepsis based on physiological data collected from the ICU.\u0000 \u0000 \u0000 \u0000 The support vector machine algorithm that uses the extracted features has a great impact on sepsis prediction, which yields the accuracy of 0.73.\u0000 \u0000 \u0000 \u0000 Predicting sepsis can be accurately performed using the main vital signs and support vector machine.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48758348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/1875036202114010039
V. Sheketa, M. Pasieka, S. Chupakhina, N. Pasieka, Uliana Ketsyk-Zinchenko, Y. Romanyshyn, Olha Yanyshyn
Automation of business documentation workflow in medical practice substantially accelerates and improves the process and results in better service development. Efficient use of databases, data banks, and document-oriented storage (warehouses data), including dual-purpose databases, enables performing specific actions, such as adding records, introducing changes into them, performing an either ordinary or analytical search of data, as well as their efficient processing. With the focus on achieving interaction between the distributed and heterogeneous applications and the devices belonging to the independent organizations, the specialized medical client application has been developed, as a result of which the quantity and quality of information streams of data, which can be essential for effective treatment of patients with breast cancer, have increased. The application has been developed, allowing automating the management of patient records, taking into account the needs of medical staff, especially in managing patients’ appointments and creating patient’s medical records in accordance with the international standards currently in force. This work is the basis for the smoother integration of medical records and genomics data to achieve better prevention, diagnosis, prediction, and treatment of breast cancer (oncology). Since relevant standards upgrade the functioning of health care information technology and the quality and safety of patient’s care, we have accomplished the global architectural scheme of the specific medical automation system through harmonizing the medical services specified by the HL7 international.
{"title":"Information System for Screening and Automation of Document Management in Oncological Clinics","authors":"V. Sheketa, M. Pasieka, S. Chupakhina, N. Pasieka, Uliana Ketsyk-Zinchenko, Y. Romanyshyn, Olha Yanyshyn","doi":"10.2174/1875036202114010039","DOIUrl":"https://doi.org/10.2174/1875036202114010039","url":null,"abstract":"\u0000 \u0000 Automation of business documentation workflow in medical practice substantially accelerates and improves the process and results in better service development.\u0000 \u0000 \u0000 \u0000 Efficient use of databases, data banks, and document-oriented storage (warehouses data), including dual-purpose databases, enables performing specific actions, such as adding records, introducing changes into them, performing an either ordinary or analytical search of data, as well as their efficient processing. With the focus on achieving interaction between the distributed and heterogeneous applications and the devices belonging to the independent organizations, the specialized medical client application has been developed, as a result of which the quantity and quality of information streams of data, which can be essential for effective treatment of patients with breast cancer, have increased.\u0000 \u0000 \u0000 \u0000 The application has been developed, allowing automating the management of patient records, taking into account the needs of medical staff, especially in managing patients’ appointments and creating patient’s medical records in accordance with the international standards currently in force. This work is the basis for the smoother integration of medical records and genomics data to achieve better prevention, diagnosis, prediction, and treatment of breast cancer (oncology).\u0000 \u0000 \u0000 \u0000 Since relevant standards upgrade the functioning of health care information technology and the quality and safety of patient’s care, we have accomplished the global architectural scheme of the specific medical automation system through harmonizing the medical services specified by the HL7 international.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47829434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/1875036202114010051
I. Fedorchenko, A. Oliinyk, Alexander Stepanenko, Tetiana Fedoronchak, A. Kharchenko, D. Goncharenko
Modern medicine depends on technical advances in the field of medical instrumentation and the development of medical software. One of the most important tasks for doctors is determination of the exact boundaries of tumors and other abnormal formations in the tissues of the human body. The paper considers the problems and methods of machine classification and recognition of radiographic images, as well as the improvement of artificial neural networks used to increase the quality and accuracy of detection of abnormal structures on chest radiographs. A modified genetic method for the optimization of parameters of the model on the basis of a convolutional neural network was developed to solve the problem of recognition of diagnostically significant signs of pneumonia on an X-ray of the lungs. The fundamental difference between the proposed genetic method and existing analogs is in the use of a special mutation operator in the form of an additive convolution of two mutation operators, which reduces neural network training time and also identifies "oneighborhood of solutions" that is most suitable for investigation. A comparative evaluation of the effectiveness of the proposed method and known methods was given. It showed an improvement in accuracy of solving the problem of finding signs of pathology on an X-ray of the lungs. Practical use of the developed method will reduce complexity, increase reliability of search, accelerate the process of diagnosis of diseases and reduce a part of errors and repeated inspections of patients.
{"title":"Development of a Genetic Method for X-ray Images Analysis based on a Neural Network Model","authors":"I. Fedorchenko, A. Oliinyk, Alexander Stepanenko, Tetiana Fedoronchak, A. Kharchenko, D. Goncharenko","doi":"10.2174/1875036202114010051","DOIUrl":"https://doi.org/10.2174/1875036202114010051","url":null,"abstract":"\u0000 \u0000 Modern medicine depends on technical advances in the field of medical instrumentation and the development of medical software. One of the most important tasks for doctors is determination of the exact boundaries of tumors and other abnormal formations in the tissues of the human body.\u0000 \u0000 \u0000 \u0000 The paper considers the problems and methods of machine classification and recognition of radiographic images, as well as the improvement of artificial neural networks used to increase the quality and accuracy of detection of abnormal structures on chest radiographs.\u0000 \u0000 \u0000 \u0000 A modified genetic method for the optimization of parameters of the model on the basis of a convolutional neural network was developed to solve the problem of recognition of diagnostically significant signs of pneumonia on an X-ray of the lungs. The fundamental difference between the proposed genetic method and existing analogs is in the use of a special mutation operator in the form of an additive convolution of two mutation operators, which reduces neural network training time and also identifies \"oneighborhood of solutions\" that is most suitable for investigation.\u0000 \u0000 \u0000 \u0000 A comparative evaluation of the effectiveness of the proposed method and known methods was given. It showed an improvement in accuracy of solving the problem of finding signs of pathology on an X-ray of the lungs.\u0000 \u0000 \u0000 \u0000 Practical use of the developed method will reduce complexity, increase reliability of search, accelerate the process of diagnosis of diseases and reduce a part of errors and repeated inspections of patients.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42961604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/1875036202114010087
Z. Nytrebych, V. Il'kiv, O. Malanchuk
The process of ultrasound oscillations in a relaxed environment, provided that the profiles of the acoustic wave at three time moments are known, is modeled by a three-point problem for the partial differential equation of the third order in time. This equation as a partial case contains a hyperbolic equation of the third order, which is widely used in ultrasound diagnostics. The differential-symbol method is applied to study a three-point in-time problem. The advantage of this method is the possibility to obtain a solution of the problem only through operations of differentiation. We propose the formula to construct the analytic solution of the problem, which describes the process of ultrasound oscillations propagation in a relax environment. Due to this, the profile of the ultrasonic wave is known at any time and at an arbitrary point of space. The class of quasi-polynomials is distinguished as a class of uniqueness solvability of a three-point problem. Using the proposed method, it is possible to analyze the influence of the main parameters of ultrasound diagnostics problems on the propagation of acoustic oscillations in a relaxed environment. The research example of a specific three-point problem is given.
{"title":"Mathematical Model of the Process of Ultrasonic wave Propagation in a Relax Environment with its Given Profiles at three Time Moments","authors":"Z. Nytrebych, V. Il'kiv, O. Malanchuk","doi":"10.2174/1875036202114010087","DOIUrl":"https://doi.org/10.2174/1875036202114010087","url":null,"abstract":"\u0000 \u0000 The process of ultrasound oscillations in a relaxed environment, provided that the profiles of the acoustic wave at three time moments are known, is modeled by a three-point problem for the partial differential equation of the third order in time. This equation as a partial case contains a hyperbolic equation of the third order, which is widely used in ultrasound diagnostics.\u0000 \u0000 \u0000 \u0000 The differential-symbol method is applied to study a three-point in-time problem. The advantage of this method is the possibility to obtain a solution of the problem only through operations of differentiation.\u0000 \u0000 \u0000 \u0000 We propose the formula to construct the analytic solution of the problem, which describes the process of ultrasound oscillations propagation in a relax environment. Due to this, the profile of the ultrasonic wave is known at any time and at an arbitrary point of space. The class of quasi-polynomials is distinguished as a class of uniqueness solvability of a three-point problem.\u0000 \u0000 \u0000 \u0000 Using the proposed method, it is possible to analyze the influence of the main parameters of ultrasound diagnostics problems on the propagation of acoustic oscillations in a relaxed environment. The research example of a specific three-point problem is given.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47669621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-19DOI: 10.2174/1875036202114010063
S. Dolgikh
The analysis of epidemiological data at an early phase of an epidemiological situation, when the confident correlation of contributing factors to the outcome has not yet been established, may present a challenge for conventional methods of data analysis. This study aimed to develop approaches for the early analysis of epidemiological data that can be effective in the areas with less labeled data. An analysis of a combined dataset of epidemiological statistics of national and subnational jurisdictions, aligned at approximately two months after the first local exposure to COVID-19 with unsupervised machine learning methods, including principal component analysis and deep neural network dimensionality reduction, to identify the principal factors of influence was performed. The approach and methods utilized in the study allow to clearly separate milder background cases from those with the most rapid and aggressive onset of the epidemics. The findings can be used in the evaluation of possible epidemiological scenarios and as an effective modeling approach to identify possible negative epidemiological scenarios and design corrective and preventative measures to avoid the development of epidemiological situations with potentially severe impacts.
{"title":"Unsupervised Clustering in Epidemiological Factor Analysis","authors":"S. Dolgikh","doi":"10.2174/1875036202114010063","DOIUrl":"https://doi.org/10.2174/1875036202114010063","url":null,"abstract":"\u0000 \u0000 The analysis of epidemiological data at an early phase of an epidemiological situation, when the confident correlation of contributing factors to the outcome has not yet been established, may present a challenge for conventional methods of data analysis.\u0000 \u0000 \u0000 \u0000 This study aimed to develop approaches for the early analysis of epidemiological data that can be effective in the areas with less labeled data.\u0000 \u0000 \u0000 \u0000 An analysis of a combined dataset of epidemiological statistics of national and subnational jurisdictions, aligned at approximately two months after the first local exposure to COVID-19 with unsupervised machine learning methods, including principal component analysis and deep neural network dimensionality reduction, to identify the principal factors of influence was performed.\u0000 \u0000 \u0000 \u0000 The approach and methods utilized in the study allow to clearly separate milder background cases from those with the most rapid and aggressive onset of the epidemics.\u0000 \u0000 \u0000 \u0000 The findings can be used in the evaluation of possible epidemiological scenarios and as an effective modeling approach to identify possible negative epidemiological scenarios and design corrective and preventative measures to avoid the development of epidemiological situations with potentially severe impacts.\u0000","PeriodicalId":38956,"journal":{"name":"Open Bioinformatics Journal","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46557824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：