Yazar "Kaya, Hilal" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A novel approach to the diagnostic assessment of carpal tunnel syndrome based on the frequency domain of the compound muscle action potential
    (Walter De Gruyter Gmbh, 2020) Alcan, Veysel; Kaya, Hilal; Zinnuroglu, Murat; Karatas, Gulcin Kaymak; Canal, Mehmet Rahmi
    Conventional electrophysiological (EP) tests may yield ambiguous or false-negative results in some patients with signs and symptoms of carpal tunnel syndrome (CTS). Therefore, researchers tend to investigate new parameters to improve the sensitivity and specificity of EP tests. We aimed to investigate the mean and maximum power of the compound muscle action potential (CMAP) as a novel diagnostic parameter, by evaluating diagnosis and classification performance using the supervised Kohonen self-organizing map (SOM) network models. The CMAPs were analyzed using the fast Fourier transform (FFT). The mean and maximum power parameters were calculated from the power spectrum. A counter-propagation artificial neural network (CPANN), supervised Kohonen network (SKN) and XY-fused network (XYF) were compared to evaluate the classification and diagnostic performance of the parameters using the confusion matrix. The mean and maximum power of the CMAP were significantly lower in patients with CTS than in the normal group (p < 0.05), and the XYF network had the best total performance of classification with 91.4%. This study suggests that the mean and maximum power of the CMAP can be considered as less time-consuming parameters for the diagnosis of CTS without using additional EP tests which can be uncomfortable for the patient due to poor tolerance to electrical stimulation.
  • [ X ]
    Öğe
    DETERMINATION OF MALIGNANT MELANOMA BY ANALYSIS OF VARIATION VALUES
    (Murat Yakar, 2019) Esim, Ahmet Kürşat; Kaya, Hilal; Alcan, Veysel
    Melanoma is a serious disease associated with mutation-based cancer cells. Genetic structure and hereditary condition play important role to understand the underlying reasons of the diseases caused by Deoxiribole Nucleic Acid (DNA). In order to identify mutation carriers and to analyze disease, researchers tend to find various gene determinations methods. Nowadays, Next Generation Sequencing (NGS) is emerging as a valuable and powerful platform to detect gene-based diseases by entiring human genome. In this study, we aimed to propose a bioinformatics application workflow to distinguish between insertions/deletions and somatic/germline mutations, by using NGS methods. We carried this study out on a data set containing 100 human genomes data (20 training, 80 testing) for the detection of Malignant Melanoma. We found that the results of diagnosis performance were 92.50% accuracy, 94.03% precision, 96.92% sensitivity and 95.45% F1 score. These results show the potential for proposed application based on NGS to improve Melanoma detection. © 2019, Murat Yakar. All rights reserved.
  • [ X ]
    Öğe
    Development of Electronic Health Record System Based on Carpal Tunnel Syndrome
    (Gazi Univ, 2019) Talan, Mehmet Ibrahim; Canal, Mehmet Rahmi; Alcan, Veysel; Kaya, Hilal; Zinnuroglu, Murat
    Physical examination, clinical tests and electrophysiological methods are used in the diagnosis of carpal tunnel syndrome (CTS). However, in practice there are no standard clinical and electrophysiological tests for clinics and laboratories. Therefore, data fragmentation or incompatibilities may occur in Electronic Health Record (EHR) systems. Furthermore, secondary use and different biomedical research targets are not considered in these EHR systems. During routine documentation, incomplete, incorrect, inconsistent data entry and incorrect coding can be done. This study aimed to develop an EHR system that could be used in different clinics and centers in diagnosis of CTS, thus creating a standardized, high quality, predictive, preventive, personalized and real-time participatory CTS biomedical data warehouse. The CTS-based EHR system was developed using Microsoft Visual Studio C # programming language. Also during a new patient record, the system was supported by a clinical decision support system (CDS S) based on the data mining methods using WEKA program for pre-diagnosis of the CTS. This EHR system also allows clinical and electrophysiological test results as well as genetic and environmental variants to be integrated into a single database within the framework of precision medicine approachment. In addition, this system can provide a large scale accurate and complete data warehouse for secondary use purposes.
  • [ X ]
    Öğe
    New Optimized Deep Learning Application for COVID-19 Detection in Chest X-ray Images
    (Mdpi, 2022) Karim, Ahmad Mozaffer; Kaya, Hilal; Alcan, Veysel; Sen, Baha; Hadimlioglu, Ismail Alihan
    Due to false negative results of the real-time Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR) test, the complemental practices such as computed tomography (CT) and X-ray in combination with RT-PCR are discussed to achieve a more accurate diagnosis of COVID-19 in clinical practice. Since radiology includes visual understanding as well as decision making under limited conditions such as uncertainty, urgency, patient burden, and hospital facilities, mistakes are inevitable. Therefore, there is an immediate requirement to carry out further investigation and develop new accurate detection and identification methods to provide automatically quantitative evaluation of COVID-19. In this paper, we propose a new computer-aided diagnosis application for COVID-19 detection using deep learning techniques. A new technique, which receives symmetric X-ray data as the input, is presented in this study by combining Convolutional Neural Networks (CNN) with Ant Lion Optimization Algorithm (ALO) and Multiclass Naive Bayes Classifier (NB). Moreover, several other classifiers such as Softmax, Support Vector Machines (SVM), K-Nearest Neighbors (KNN) and Decision Tree (DT) are combined with CNN. The promising results of these classifiers are evaluated and presented for accuracy, precision, and F1-score metrics. NB classifier with Ant Lion Optimization Algorithm and CNN produced the best results with 98.31% accuracy, 100% precision and 98.25% F1-score and with the lowest execution time.