Yazar "Kelesoglu, Saban" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Flow-Mediated Vasodilatation which is diagnostic method of endothelial dysfunctions change in atrial septal defect patients before and after closure of the ASD
    (2020) Elcik, Deniz; Karadavut, Serhat; Dogan, Ali; Kelesoglu, Saban; Cetinkaya, Zeki; Tuncay, Aydin
    Aim: Atrial septal defect secondary pulmonary hypertension causes disruption of the endothelial structure, resulting in an increase in vasoconstrictor mediators and a decrease in vasodilator mediators. These changes on the endothelial system alter the flow in the pulmonary vein and the systemic vein bed. This also has an effect on flow mediated vasodilatation. Our purpose in this study is to evaluate the endothelial dysfunction after atrial septal defect closure via flow mediated vasodilatation. Material and Methods: Total 51 patients with pre and one mount after post treatment secundum-type atrial septal defect and 40 healthy volunteers were prospectively enrolled. Atrial septal defect was treated with transcathater closure procedure. Flow mediated vasodilatation was measured to evaluate endothelial function prior to and one month after the defect was closured.Results: Flow-mediated vasodilatation values were significantly higher in an atrial septal defect′s patient than in the healthy volunteer (11.2 ± 1.01 m/s vs. 12.7 ± 1.18 m/s, P 0.001). Flow-mediated vasodilatation values were significantly reduced at the follow-up one month after the procedure compared to baseline. Moreover, there was a significant negative correlation between pulmonary arterial pressure values and flow-mediated vasodilatation (r=-0.347; p=0.013) in the pretreatment group.Conclusion: Flow-mediated vasodilatation values were significantly lower in the right cardiac chambers, and the systolic pulmonary arterial pressure was improved. This result has shown us that atrial septal defect closure may benefit from endothelial dysfunction.
  • Küçük Resim Yok
    Öğe
    High-performance classification of STEMI and NSTEMI by automatic feature selection from ECG signals: a triple approach
    (Springer London Ltd, 2025) Latifoglu, Fatma; Icer, Semra; Guven, Aysegul; Zhusupova, Aigul; Avsarogullari, Omer Levent; Kelesoglu, Saban; Kalay, Nihat
    Acute Myocardial Infarction (AMI) remains a major health problem globally despite advances in diagnosis and treatment. Although electrocardiography (ECG) is a popular diagnostic tool, it can be difficult to interpret due to signal variability and pathology-related changes. This study proposes a triple approach to classify Healthy Controls (HC), ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) by applying the triple method to 12-lead ECG signals. The proposed method includes automatic feature and ECG derivation selection using Particle Swarm Optimisation (PSO), Least Absolute Shrinkage and Selection Operator (LASSO) and Linear Regression (LR) and signal decomposition using Variational Mode Decomposition (VMD). Classification is performed using machine learning algorithms such as Artificial Neural Network (ANN), K-nearest neighbours (KNN), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). The proposed method is evaluated using both the original clinical dataset and the PTB-XL database. As a result of the evaluation, high classification performance was achieved for both the clinical dataset (Accuracy: 100%) and the open-source PTB-XL dataset (Accuracy: 99.60%). The results obtained in this study demonstrate the potential for fast and reliable diagnosis. The proposed work contributes to addressing the challenge of distinguishing between STEMI and NSTEMI, which is crucial for the treatment of AMI patients.