32 results
Search Results
Now showing 1 - 10 of 32
Article Citation - WoS: 21Citation - Scopus: 35Deep Learning-Based Computer-Aided Diagnosis (cad): Applications for Medical Image Datasets(Mdpi, 2022) Kadhim, Yezi Ali; Khan, Muhammad Umer; Mishra, AlokComputer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the best optimal features while reducing the amount of data. Lastly, diagnosis prediction (classification) is achieved using learnable classifiers. The novel framework for the extraction and selection of features is based on deep learning, auto-encoder, and ACO. The performance of the proposed approach is evaluated using two medical image datasets: chest X-ray (CXR) and magnetic resonance imaging (MRI) for the prediction of the existence of COVID-19 and brain tumors. Accuracy is used as the main measure to compare the performance of the proposed approach with existing state-of-the-art methods. The proposed system achieves an average accuracy of 99.61% and 99.18%, outperforming all other methods in diagnosing the presence of COVID-19 and brain tumors, respectively. Based on the achieved results, it can be claimed that physicians or radiologists can confidently utilize the proposed approach for diagnosing COVID-19 patients and patients with specific brain tumors.Book Part Citation - Scopus: 2Molecular Mimicry Study Between Peptides of SARS-CoV-2 and Neutrophil Extracellular Traps-Related Proteins(Elsevier, 2024) Adiguzel,Y.; Shoenfeld,Y.Background Neutrophil extracellular traps (NETs) are observed in both COVID-19 pathology and autoimmune disorders, and molecular mimicry is a mechanism that can lead to an autoimmune response. Methods Similar sequences between SARS-CoV-2 proteins and 5 proteins (plasminogen receptor KT: PLRKT, myeloperoxidase: MPO, proteinase 3: PR-3, neutrophil elastase: NE, matrix metalloproteinase 9: MMP-9) that are present in NETs were searched. Human and SARS-CoV-2 sequence pairs were identified. Those among the identified sequence pairs, which are predicted as strong-binding peptides or epitopes of the same selected MHC class I and class II alleles, were predicted. Results In the case of MHC class I alleles, similar PLRKT and SARS-CoV-2 peptide sequences with high predicted-affinities to HLA-A*24:02, HLA-B*08:01, and HLA-B*15:01; similar MPO and SARS-CoV-2 peptide sequences with strong predicted-affinities to HLA-A*01:01, HLA-A*26:01, and HLA-B*15:01; and similar MMP-9 and SARS-CoV-2 peptide sequences with elevated predicted-affinities to HLA-B*39:01 were predicted. In the case of MHC class II alleles, similar PLRKT and SARS-CoV-2 peptide sequences with high predicted-affinities to HLA-DPA1*02:01/DPB1*01:01 were predicted. Conclusion This work is a proof-of-concept study, which revealed the potential involvement of molecular mimicry in NET pathology within susceptible individuals, in the case of being infected with SARS-CoV-2, leading to autoimmunity. © 2024 Elsevier B.V. All rights reserved.Review Citation - WoS: 7Citation - Scopus: 9A Survey of Covid-19 Diagnosis Using Routine Blood Tests With the Aid of Artificial Intelligence Techniques(Mdpi, 2023) Habashi, Soheila Abbasi; Koyuncu, Murat; Alizadehsani, RoohallahSevere Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.Article Citation - Scopus: 18Pulmonary rehabilitation principles in SARS-COV-2 infection (COVID-19): The revised guideline for the acute, subacute, and post-COVID-19 rehabilitation(Turkish Society of Physical Medicine and Rehabilitation, 2021) Aytür,Y.K.; Köseoglu,B.F.; Taşkıran,Ö.Ö.; Gökkaya,N.K.O.; Delialioğlu,S.Ü.; Tur,B.S.; Tıkız,C.Coronavirus disease 2019 (COVID-19) is a contagious infection disease, which may cause respiratory, physical, psychological, and generalized systemic dysfunction. The severity of disease ranges from an asymptomatic infection or mild illness to mild or severe pneumonia with respiratory failure and/or death. COVID-19 dramatically affects the pulmonary system. This clinical practice guideline includes pulmonary rehabilitation (PR) recommendations for adult COVID-19 patients and has been developed in the light of the guidelines on the diagnosis and treatment of COVID-19 provided by the World Health Organization and Republic of Turkey, Ministry of Health, recently published scientific literature, and PR recommendations for COVID-19 regarding basic principles of PR. This national guideline provides suggestions regarding the PR methods during the clinical stages of COVID-19 and post-COVID-19 with its possible benefits, contraindications, and disadvantages. © 2021 All right reserved by the Turkish Society of Physical Medicine and RehabilitationBook Part Citation - Scopus: 2Novel Covid-19 Recognition Framework Based on Conic Functions Classifier(Springer Science and Business Media Deutschland GmbH, 2022) Karim,A.M.; Mishra,A.The new coronavirus has been declared as a global emergency. The first case was officially declared in Wuhan, China, during the end of 2019. Since then, the virus has spread to nearly every continent, and case numbers continue to rise. The scientists and engineers immediately responded to the virus and presented techniques, devices and treatment approaches to fight back and eliminate the virus. Machine learning is a popular scientific tool and is applied to several medical image recognition problems, involving tumour recognition, cancer detection, organ transplantation and COVID-19 diagnosis. It is proved that machine learning presents robust, fast and accurate results in various medical image recognition problems. Generally, machine learning-based frameworks consist of two stages: feature extraction and classification. In the feature extraction, overwhelmingly unsupervised learning techniques are applied to reduce the input data’s size. This step extracts appropriate features by reducing the computational time and increasing the performance of the classifiers. A classifier is the second step that aims to categorise the input. Within the proposed step, the unsupervised part relies on the feature extraction by using local binary patterns (LBP), followed by feature selection relying on factor analysis technique. The LBP is a kind of visual descriptor, mainly applied for image recognition problem. The aim of using LBP is to analyse the input COVID-19 image and extract salient features. Furthermore, factor analysis is a statistical technique applied to define variability among observed variables in less unnoticed variables named factors. The factor analysis applied to the LBP wavelet aims to select sensitive features from input data (LBP output) and reduce the size input. In the last stage, conic functions classifier is applied to classify two sets of data, categorising the extracted features by using LBP and factor analysis as positive or negative COVID-19 cases. The proposed solution aims to diagnose COVID-19 by using LBP and factor analysis, based on conic functions classifier. The conic functions classifier presents remarkable results compared with these popular classifiers and state-of-the-art studies presented in the literature. © 2022, Springer Nature Switzerland AG.Article Citation - WoS: 5Citation - Scopus: 8A Novel Hybrid Machine Learning-Based System Using Deep Learning Techniques and Meta-Heuristic Algorithms for Various Medical Datatypes Classification(Mdpi, 2024) Kadhim, Yezi Ali; Guzel, Mehmet Serdar; Mishra, AlokMedicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep learning techniques, which were based on a convolutional neural network (CNN) or autoencoder, to extract features and combine them with the next step of the meta-heuristic algorithm in order to select optimal features using the particle swarm optimization (PSO) algorithm. This combination sought to reduce the dimensionality of the datasets while maintaining the original performance of the data. This is considered an innovative method and ensures highly accurate classification results across various medical datasets. Several classifiers were employed to predict the diseases. The COVID-19 dataset found that the highest accuracy was 99.76% using the combination of CNN-PSO-SVM. In comparison, the brain tumor dataset obtained 99.51% accuracy, the highest accuracy derived using the combination method of autoencoder-PSO-KNN.Article Investigation of Sars-Cov Antibody Levels After Covid-19 Vaccine in Chronic Hepatitis B Patients(Aepress Sro, 2024) Kinikli, Sami; Afsar, Fatma Elcin; Dursun, Ali Dogan; Aksoy, Altan; Karahan, Gizem; Cesur, Salih; Urtimur, UfukAIM: The aim was to compare SARS-CoV-2 IgG antibody levels in chronic hepatitis B patients and healthcare personnel selected as the control group and to determine factors such as age, gender, vaccine type, and number of vaccines that may affect the antibody levels. MATERIALS AND METHODS: 87 chronic hepatitis B (CHB) patients followed in Ankara Training and Research Hospital Infectious Diseases Clinic and Mamak State Hospital Infectious Diseases outpatient clinic and 89 healthcare personnel selected as the control group were included in the study. SARS-CoV-2 IgG antibody levels in the serum samples of patients and healthcare personnel who received the COVID-19 vaccine were studied with the ELISA method in the Microbiology Laboratory of Ankara Training and Research Hospital, using a commercial ELISA kit (Abbott, USA) in line with the recommendations of the manufacturer. In the study, SARS-CoV-2 IgG levels were compared in CHB patients and healthcare personnel. In addition, the relationship between SARS-CoV-2 antibody level, gender, average age, natural history of the disease, number of vaccinations, vaccine type (Coronavac TM vaccine alone, BNT162b2 vaccine alone or Coronavac TM and BNT162b2 vaccine (heterologous vaccination)), treatment duration of CHB was investigated. Statistical analyses were made in the SPSS program. A value of p <= 0.05 was considered statistically significant. FINDINGS: A total of 167 people, including 87 CKD patients and 80 healthcare personnel as the control group, were included in the study. SARS-CoV-2 IgG antibody levels were detected above the cut-off level in the entire study group, regardless of the vaccine type. No difference was detected in SARS-CoV-2 IgG titers after COVID-19 vaccination between CHB patients and healthcare personnel. There was a statistically significant difference in SARS-CoV-2 IgG antibody levels among individuals participating in the study according to vaccine types. Compared to those who received Coronavac TM vaccine alone, the average SARS-CoV-2 IgG level was found to be statistically significantly higher in those who received BNT162b2 vaccine alone or heterologous vaccination with Coronavac TM + BNT162b2 vaccine. There was no difference between the groups in terms of age, gender, number of vaccinations, natural transmission of the disease, and duration of antiviral therapy in the CHD patient group. CONCLUSION: As a result, SARS-CoV-2 IgG antibody levels above the cut-off value were achieved with Coronavac TM and BNT162b2 vaccines in both CHD patients and healthy control groups. however, both CHD patients and healthcare personnel had higher antibody levels than those who received BNT162b2 alone or those who received heterologous vaccination had higher antibody levels than those with Coronavac TM alone. Therefore, if there are no contraindications, BNT162b2 vaccine may be preferred in CHB and health personnel (Tab. 2, Ref. 14) .Article Health Capital and a Sustainable Economic-Growth Nexus: a High-Frequency Analysis During Covid-19(Mdpi, 2024) Sungur, Nazli Ceylan; Akdogan, Ece C.; Gokten, SonerThe recent COVID-19 pandemic effectively concretized the vitality of health expenditure and the economic-growth nexus, and the threat of new pandemics make re-examining this relationship a necessity. Consequently, this paper focuses on this nexus for developed OECD countries, paying particular attention to the effects of the COVID-19 pandemic. The use of stock indices as proxy variables for health expenditure and economic growth enabled the examination of this nexus by using high-frequency data and financial econometric techniques, specifically via rolling correlation and bivariate GARCH analyses. The data span 1170 observations between 15 May 2018 and 11 November 2022. Since the research period overlaps with the outbreak of Ukraine-Russia war, additional insights are obtained regarding the effects of the war as well. It was found that an increase in health expenditure leads to a delayed increase in economic growth even in the short term, and this relationship mainly develops during crises such as epidemics, wars, supply chain breakdowns, etc., for developed OECD countries. Given the aging population of developed countries, which will probably deteriorate the health status of those countries in the near future, the increasing political tensions around the globe and the considerations of a global recession highlight the importance and the inevitability of investments in health capital for developed countries as well.Book Part Perspectives on Molecular Mimicry Between Human, Sars-Cov and Plasmodium Species Through a Probabilistic and Evolutionary Insight(Elsevier, 2024) Adiguzel,Y.; Shoenfeld,Y.This chapter examines potential molecular mimicry between similar peptide sequences and shared 6mers of five selected proteins and the proteomes of both SARS-CoV-2 and five Plasmodium species that infect humans (P. falciparum, P. malariae, P. vivax, P. knowlesi, and P. ovale). Human proteins are plasminogen receptor (KT), neutrophil collagenase (neutrophil collagenase isoform 2), myeloperoxidase precursor, mitochondrial peptide methionine sulfoxide reductase isoform a precursor, and myeloblastin precursor. The chapter eventually focuses on a probabilistic and evolutionary insight into molecular mimicry. © 2024 Elsevier B.V. All rights reserved.Article Breast Cancer Management During the Covid Pandemic(Coll Physicians & Surgeons Pakistan, 2024) Sariyildiz, Gulcin Turkmen; Ayhan, Fikriye FigenObjective: To explore the impact of COVID-19 among both the newly diagnosed patients and patients under follow-up for breast cancer by focusing on patients' accessibility to management and comparing the distribution of them before and during pandemic. Study Design: Single -centric retrospective study. Place and Duration of the Study: Department of General Surgery and Department of Physical Medicine and Rehabilitation, Atilim University, Medicana International Ankara Hospital, Ankara, Turkiye, from March 2018 to 2022. Methodology: The data were collected to analyse numbers and distributions of physician visits regarding breast cancer. Results: The mean age of patients was 55.98 +/- 12.60 years. The percentages of newly diagnosed cases showed similarity (7.37% vs. 9.79%) before and during the pandemic (p = 0.18). The number of imaging studies decreased by 53.33% in patients under follow-up (p = 0.006), despite screening tests showed a similar trend (p = 0.145). General surgery visits marked up (+44.6%), in contrast to plastic surgery visits (-42.04%, p <0.001). Patients' admissions decreased in many COVID-19 related clinics (pulmonology, emergency, internal medicine, and intensive care), but cardiology (+96.59%) and rehabilitation (+75%) admissions increased during the pandemic (p <0.001). The number of medical oncology and radiation oncology visits did not change (p >0.05). Conclusion: Total number of physician visits was similar before and during the pandemic despite the changing distribution. While COVID-19 led to markedly rising trends of surgical, cardiological, and rehabilitative management in patients with breast cancer, falling trends were seen in other specialities except oncology which showed a plateau during two years. The falling trends of visits to pulmonology, emergency, internal medicine, and intensive care clinics may be explained by crowded COVID-19 cases.
