Browsing by Author "Bayrak, Tuncay"

Now showing 1 - 9 of 9

Classification of Patients with Heart Failure
(2014) Bayrak, Tuncay; Ogul, Hasan; https://orcid.org/0000-0001-6826-4350; U-4603-2019
Echocardiography is imaging of anatomy and physiology of heart with high frequency sound waves by using ultrasonic transducers. The signals obtained by using this method are defined as echocardiogram. In this way, the function of heart can be investigated and any abnormal case is determined according to many parameters. In this study, the classification was realized, according to 7 of features obtained from echocardiogram signals belong to 74 of patient in Machine Learning Repository (UCI) database. Naive Bayes was determined as the best classification method for this dataset and 63% sensitivity, 84% specificity, and an accuracy value of 77% has been reached. In conclusion, this study presents an investigation of determination of which features are significant in death based on heart failure.
Construction of A Bilirubin Biosensor Based on an Albumin-Immobilized Quartz Crystal Microbalance
(2017) Kocakulak, Mustafa; Bayrak, Tuncay; Saglam, Sinan; 0000-0001-6826-4350; AAE-3731-2020
Bilirubin, a bile pigment, is associated with several diseases and systemic pathologies. The measurement of bilirubin is important for diagnosis and therapy, and many expensive methods are used to measure the bilirubin amount in blood. In this study, a new bilirubin biosensor using quartz crystal microbalances immobilized with albumin is proposed. To measure the effectiveness of the biosensor, a series of experiments was realized with various concentrations of bilirubin, including 1 mg/dL, 2 mg/dL, 5 mg/dL and 10 mg/dL. Comparing blood gas analyzers, laboratory analyzers, skin test devices and nonchemical photometric devices, blood gas analyzers have a range of 0.5-35 mg/dL, laboratory analyzers have a range of 0-30 mg/dL, skin test devices could be used up to 11.7 mg/dL, and nonchemical photometric devices could be evaluated as reliable up to 14.6 mg/dL. The low limit range of the bilirubin detection is between 0.099 mg/dL and 0.146 mg/dL for some special commercial bilirubin measurement devices. Nevertheless, this study presents measurements with a high sensitivity and includes the advantage of reusability by using cheaper materials. To prove albumin immobilization and the bilirubin-albumin interaction atomic force microscopy (AFM) was used, and a good correlation was achieved from AFM images. In conclusion, considering the cost-effectiveness side of the proposed method, a low cost and more sensitive bilirubin measurement device which is effective and reusable was developed instead of the current commercial products. (C) 2017 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.
Data Integration for Gene Expression Prediction
(2018) Bayrak, Tuncay; Ogul, Hasan; 0000-0001-6826-4350; U-4603-2019
In computational system biology, one challenging topic is predicting the exact value of gene expression for further meta-analysis. For this, a data integration approach and regression based task are proposed. To improve prediction performance, gene expression data consisted of continuous value is integrated with binary data from miRNA-mRNA regulation pairs by a simple approach. For regression task, a recently introduced method, Relevance Vector Machine (RVM) and linear regression are used. For evaluation, Spearman and Pearson Correlation Coefficients, and Root Mean Squared Error are used. The results we obtain show that the proposed approach can significantly improve the prediction performance. Data integration approach and RVM are promising in many machine learning problems.
Eliminating Rib Shadows in Chest Radiographic Images Providing Diagnostic Assistance
(2016) Ogul, Hasan; Ogul, B. Buket; Agildere, A. Muhtesem; Bayrak, Tuncay; Sumer, Emre; https://orcid.org/0000-0003-4223-7017; https://orcid.org/0000-0001-6826-4350; 26775736; AAB-5802-2020; U-4603-2019
A major difficulty with chest radiographic analysis is the invisibility of abnormalities caused by the superimposition of normal anatomical structures, such as ribs, over the main tissue to be examined. Suppressing the ribs with no information loss about the original tissue would therefore be helpful during manual identification or computer-aided detection of nodules on a chest radiographic image. In this study, we introduce a two-step algorithm for eliminating rib shadows in chest radiographic images. The algorithm first delineates the ribs using a novel hybrid self-template approach and then suppresses these delineated ribs using an unsupervised regression model that takes into account the change in proximal thickness (depth) of bone in the vertical axis. The performance of the system is evaluated using a benchmark set of real chest radiographic images. The experimental results determine that proposed method for rib delineation can provide higher accuracy than existing methods. The knowledge of rib delineation can remarkably improve the nodule detection performance of a current computer-aided diagnosis (CAD) system. It is also shown that the rib suppression algorithm can increase the nodule visibility by eliminating rib shadows while mostly preserving the nodule intensity. (C) 2015 Elsevier Ireland Ltd. All rights reserved.
Evaluation of The Unique Device Identification System and an Approach for Medical Device Tracking
(2017) Bayrak, Tuncay; Copur, Funda Ozdiler
Background: Most countries have different registration and tracking system, but unique device identification based approach was recently introduced in the USA. In 2013, FDA and EU released regulations about unique device identification system. In literature, there is not any study that compares the UDI legislations on the basis of the requirements. In addition to the legal requirements, establishing a UDI system in digital environment is very challenging. Methods: This is a theory based study that includes information from healthcare industries and key points from UDI related legislations which are discussed. To visualize the design of the proposed system, the Dia program that contains the Unified Modeling Language (UML) components was used. Results: Implementation of the UDI based tracking system is very difficult due to two reasons. First, the relevant legislations do not give detailed information on how UDI system will be implemented. Second, each type of medical device has difficulties due to UDI labeling. We have observed that the stakeholders in the medical devices sector in Turkey, especially the manufacturers, are not yet ready for UDI-based tracking. The current registry system is not effective to track medical devices and share data. Conclusions: To overcome compliance problems, UDI requirements should be perfectly determined and subsequently related legislation should be established. Regarding these requirements, every country should introduce an action plan and include all sector stakeholders in that action plan. We suggest a model for medical. device tracking to be able to use instead of the current registry system in Turkey. (C) 2017 Fellowship of Postgraduate Medicine. Published by Elsevier Ltd. All rights reserved.
Gen ifade tahmini için veri bütünleştirme
(Başkent Üniversitesi Fen Bilimleri Enstitüsü, 2019) Bayrak, Tuncay; Oğul, Hasan
Canlı formunun sürdürülebilirliğinin temelinde protein sentezi yer almaktadır. Protein sentezinde, insan genomundaki kodlayıcı genleri düzenleyen küçük nükleotid dizilerinin (mikro RNA) ve diğer yönetici genlerin (Transkripsiyon Faktör, TF) önemli görevleri vardır. Bu çalışmanın amacı, mikro RNA ve TF’lerin düzenleme bilgisinin protein kodlayıcı genlerin ifade tam değerlerinin kestirim performansına etkisini araştırmaktır. Gen ifade tam değerini tahmin etmek için regresyon tabanlı modelleri içeren sistematik yaklaşımlar ortaya konulmuştur. Öncelikle, gen ifade ölçümlerinde yaygın olarak karşılaşılan kayıp veri (missing data) problemini çözmek için doğrusal, k-NN ve İlişkisel Vektör Makinesi (RVM) regresyon modelleri uygulanmıştır. Regresyon modelinin eğitiminde genellikle aynı genin farklı deneylere ait ifade değerlerinden oluşan vektörler kullanılmaktadır. Daha sonra, bu ifade vektörlerine aynı deneye ait farklı gen ifade değerlerinin dâhil edilmesinin gen ifade tahminine etkisi araştırılmıştır. Bunun için İki Yönlü İşbirlikçi Filtreleme (Two-way collaborative filtering) yöntemi kullanılarak gen ifade değerlerinden oluşan tek yönlü veri matrisi iki yönlü veri matrisine dönüştürülmüş ve regresyon modeli bu yeni veri matrisi ile oluşturulmuştur. Gen ifade tahmini için ilk defa kullanılan bu yeni öznitelik sunum tekniği ile kestirim performansının artırıldığı görülmüştür. Ayrıca farklı kanser türlerine ait gen ifade verilerinin bütünleştirilmesinin gen ifade tahminine etkisi de araştırılmıştır. Burada, prostat kanserine ait gen ifade değerlerinin tahmin edilmesinde kolon kanseri verisinin model öğrenmede kullanılmasının kestirim performansını artırdığı görülmüştür. Literatürde gen ifade değerleri kullanılarak gen düzenleyici moleküller ile genler arasındaki ilişkinin tespit edilmesine yönelik çok sayıda çalışma bulunmaktadır. Ancak hücrede meydana gelen bu etkileşimler kullanılarak gen ifade tam değerinin tespitine yönelik çalışmalar oldukça kısıtlıdır. Son olarak, farklı veri yapısındaki miRNA-gen ve TF-gen regülasyon bilgileri ile gen ifade değerleri bütünleştirilmiş olup doğrusal ve RVM regresyon modelleri kullanılarak kestirim performansına etkisi araştırılmıştır. Veri bütünleştirme yaklaşımlarında Öklid, Affine Dönüşüm ve Bhattacharya uzaklık ölçütleri kullanılmıştır. Gen ifade matrisleri; Gene Expression Omnibus veritabanından, TF-gen regülasyon bilgisi TRANSFAC veritabanından ve miRNA-gen regülasyon bilgisi ise mirDB, mirTarbase ve mirConnX veri tabanlarından alınmıştır. Kestirim performansının değerlendirilmesinde Spearman benzerlik katsayısı, Pearson benzerlik katsayısı ve Hata Kareleri Ortalamasının Karekökü (RMSE) ölçütleri kullanılmıştır. miRNA-gen regülasyon bilgisinin bütünleştirilmesi ile gen ifade tahmini performansının artırıldığı görülmüştür. Protein synthesis is the basis of the sustainability of the living form. Small nucleotide sequences (micro-RNA) and other executive genes (Transcription Factor, TF) that regulate coding genes play an important role in the protein synthesis. The aim of this study was to investigate the effect of regulation information of micro-RNA and TFs on the performance of predicting the exact value of expressions of protein coding genes. In order to predict the exact value of gene expression, systematic approaches that includes regression-based models are introduced. First, linear, k-NN and Relational Vector Machine (RVM) regression models were applied to solve the common problem of missing data in gene expression measurements. The expression vectors used in the training phase of the regression model are generally composed of the expression values of the same gene that belongs to different experiments. After that, the effect of the inclusion of different gene expression values of the same experiment on these expression vectors was investigated. For this, the one-way data matrix, consisting of gene expression values, was transformed into a two-way data matrix using Two-way Collaborative Filtering method and the regression model was built with this new data matrix. It is observed that this new feature representation technique that is first used in this study for gene expression predicting increases the performance of predicting. In addition, the effect of integrating gene expression values of different cancer types on gene expression predicting is also investigated. Here, it is observed that the use of colon cancer data in model learning to predict the gene expression of prostate cancer increases prediction performance. There are many studies in the literature to determine the relationship between regulating molecules and genes using gene expression values. However, there are very limited studies based on predicting the exact value of gene expression by using these relations in the cell. Finally, miRNA-gene and TF-gene interaction information and gene expression values were integrated and the prediction performance outcomes obtained by using linear and RVM regression models were discussed. Euclidean, Affine Transformation and Bhattacharya distance measures were used in data integration approaches. Gene expression matrices from Gene Expression Omnibus; TF-gene regulation information from TRANSFAC; miRNA-gene regulation information from mirDB, mirTarbase and mirConnX were used. Spearman similarity coefficient, Pearson similarity coefficient and Root Mean Squared Error (RMSE) were used to evaluate the performance of predicting. It is observed that the performance of predicting gene expression is increased by integrating of miRNA-gene regulation information.
Microarray Missing Data Imputation Using Regression
(2017) Bayrak, Tuncay; Ogul, Hasan; 0000-0001-6826-4350; U-4603-2019
Having missing values due to several experimental conditions is a common problem in analyzing the results of microarray experiments. Although many imputation methods exist, comparative studies based on regression based models are very limited. Particularly, Relevance Vector Machine (RVM), a recent regression method shown to be effective in various domains, has not been considered so far for missing value imputation in microarray data. In this study, we present a comparative study between regression based models, including linear regression, k-nearest neighbor regression and RVM that uses data obtained from breast, colon and prostate cancer tissues through the microarray technology. The leave-one-out (or Jackknife) procedure is applied for the validation. To measure the performance of the model we used Spearman correlation coefficient (CC). The results reveal that RVM with a Gaussian kernel outperforms other regression models in some cases.
A New Approach for Predicting the Value of Gene Expression: Two-way Collaborative Filtering
(2019) Bayrak, Tuncay; Ogul, Hasan; 0000-0001-6826-4350; AAE-3731-2020; AAE-3731-2020
Background: Predicting the value of gene expression in a given condition is a challenging topic in computational systems biology. Only a limited number of studies in this area have provided solutions to predict the expression in a particular pattern, whether or not it can be done effectively. However, the value of expression for the measurement is usually needed for further meta-data analysis. Methods: Because the problem is considered as a regression task where a feature representation of the gene under consideration is fed into a trained model to predict a continuous variable that refers to its exact expression level, we introduced a novel feature representation scheme to support work on such a task based on two-way collaborative filtering. At this point, our main argument is that the expressions of other genes in the current condition are as important as the expression of the current gene in other conditions. For regression analysis, linear regression and a recently popularized method, called Relevance Vector Machine (RVM), are used. Pearson and Spearman correlation coefficients and Root Mean Squared Error are used for evaluation. The effects of regression model type, RVM kernel functions, and parameters have been analysed in our study in a gene expression profiling data comprising a set of prostate cancer samples. Results: According to the findings of this study, in addition to promising results from the experimental studies, integrating data from another disease type, such as colon cancer in our case, can significantly improve the prediction performance of the regression model. Conclusion: The results also showed that the performed new feature representation approach and RVM regression model are promising for many machine learning problems in microarray and high throughput sequencing analysis.
The Quantitative Analysis of Uvulopalatal Flap Surgery
(2017) Erdamar, Aykut; Bayrak, Tuncay; Firat, Hikmet; Mutlu, Murad; Ardic, Sadik; Eroglu, Osman; 0000-0001-8588-480X; AAA-6844-2019
Objective: In this work, a new methodology based on signal processing techniques for the quantitative analysis of uvulopalatal flap surgery is proposed. Clinical assessment studies of uvulopalatal flap surgery are based on not only the physician's examination, but also the patient's subjective feedback. Quantitative and objective evaluation studies are still lacking in the literature. Materials and Methods: Full night sleep records were analyzed for 21 patients before and after the surgery. The proposed algorithm consists of two independent parts. In the first part, the heart rate variability and complexity of the electrocardiogram were calculated. The second part includes calculating the electroencephalogram sub-band energy. Afterwards, the statistical methods were applied in order to determine the correlation of clinical and experimental parameters. Results: The low frequency/high frequency ratio and the sub-band energy of beta wave were significant for the patients having low postoperative delta sleep duration. Moreover, the sub-band energies of both alpha and beta waves, and theta wave were significant for the patients who had high post-operative delta sleep duration and blood oxygen saturation (SaO(2))-parameter. Complexity was significant for the patients with low postoperative respiratory disturbance index and SaO(2) parameter, and respiratory disturbance is correlated with snoring index. Conclusion: Respiratory disturbance index, which is not significant according to the pre- and post-operative clinical findings, was found to be directly related to the complexity feature. The most important result of this work is that the pre-operative complexity feature is correlated with respiratory disturbance and snoring index. This means that complexity feature can be a predictor prior to surgery.