Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
1122 results
Search Results
Publication Metadata only Prediction of cyclosporine A blood levels: An application of the adaptive-network-based fuzzy inference system (ANFIS) in assisting drug therapy(2008) Gören, Sezer; Karahoca, Adem; Onat, Filiz Yilmaz; Gören, Mehmet Zafer; Gören, Sezer, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Karahoca, Adem, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Onat, Filiz Yilmaz, Department of Pharmacology and Clinical Pharmacology, Marmara Üniversitesi Tip Fakültesi, Istanbul, Turkey; Gören, Mehmet Zafer, Department of Pharmacology and Clinical Pharmacology, Marmara Üniversitesi Tip Fakültesi, Istanbul, TurkeyObjective: Therapeutic drug monitoring (TDM) is a procedure in which the levels of drugs are assayed in various body fluids with the aim of individualizing the dose of critical drugs, such as cyclosporine A. Cyclosporine A assays are performed in blood. Methods: We proposed the use of the Takagi and Sugeno-type adaptive-network-based fuzzy inference system (ANFIS) to predict the concentration of cyclosporine A in blood samples taken from renal transplantation patients. We implemented the ANFIS model using TDM data collected from 138 patients and 20 input parameters. Input parameters for the model consisted of concurrent use of drugs, blood levels, sampling time, age, gender, and dosing intervals. Results: Fuzzy modeling produced eight rules. The developed ANFIS model exhibited a root mean square error (RMSE) of 0.045 with respect to the training data and an error of 0.057 with respect to the checking data in the MATLAB environment. Conclusion: ANFIS can effectively assist physicians in choosing best therapeutic drug dose in the clinical setting. © 2008 Springer-Verlag. © 2009 Elsevier B.V., All rights reserved., MEDLINE® is the source for the MeSH terms of this document.Publication Metadata only Information system design for a hospital emergency department: A usability analysis of software prototypes(2010) Karahoca, Adem; Bayraktar, Erkan; Tatoglu, Ekrem; Karahoca, Dilek Yiğit; Karahoca, Adem, Faculty of Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Bayraktar, Erkan, Faculty of Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Tatoglu, Ekrem, Faculty of Economics and Administrative Sciences, Bahçeşehir Üniversitesi, Istanbul, Turkey; Karahoca, Dilek Yiğit, Faculty of Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyStudy objective: The purpose of this study is to evaluate the usability of emergency department (ED) software prototypes developed for Tablet personal computers (Tablet PCs) in order to keep electronic health records (EHRs) of patients errorless and accessible through mobile technologies. In order to serve this purpose, two alternative prototypes were developed for Tablet PCs: Mobile Emergency Department Software (MEDS) and Mobile Emergency Department Software Iconic (MEDSI) among which the user might choose the more appropriate one for ED operations based on a usability analysis involving the target users. Methods: The study is based on a case study of 32 potential users of our prototypes at the ED of Kadikoy-AHG in Istanbul, Turkey. We examined usability of the prototypes for medical information systems by means of Nielsen's heuristic evaluation and cognitive walkthrough methods relying on 7-point scales, and scenario completion success rate and average scenario completion time, respectively. Results: The implementation of MEDSI in our case study confirmed the view that the usability evaluation results of iconic GUIs were better than those of non-iconic GUIs in terms of Nielsen's heuristic evaluation, effectiveness and user satisfaction. For the whole sample, paired t-test scores indicated that there was a significant difference (p < 0.01) between mean values of Nielsen's usability scores toward MEDS and MEDSI indicating that MEDSI was evaluated more favorably than MEDS. As for effectiveness of the prototypes, significant differences (p < 0.01) were noted between MEDS and MEDSI in terms of both overall scenario completion success rate and average scenario completion time. Similarly, for the full sample of users independent sample t-test scores indicated that MEDSI was perceived significantly more favorable (p < 0.01) than MEDS in terms of overall user satisfaction. Conclusion: The study provides two important contributions to the extant literature. First, it addresses a topic and methodology that serves potentially interesting to the biomedical informatics community. Drawing on good background information and appropriate context, it involves various aspects of usability testing. Another contribution of the study lies in its examination of two different prototypes during the design phase involving the target users. © 2009 Elsevier Inc. All rights reserved. © 2010 Elsevier B.V., All rights reserved., MEDLINE® is the source for the MeSH terms of this document.Publication Metadata only Classification of the colonic polyps in CT-colonography using region covariance as descriptor features of suspicious regions(2010) Kılıç, Niyazi; Kursun, Olcay; Uçan, Osman Nuri; Kılıç, Niyazi, Department of Electrical and Electronics Engineering, Istanbul Üniversitesi, Istanbul, Turkey; Kursun, Olcay, Department of Electrical and Electronics Engineering, Istanbul Üniversitesi, Istanbul, Turkey; Uçan, Osman Nuri, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyWe present an algorithm to classify polyps in CT colonography images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, they cannot simply be fed to traditional machine learning tools such as support vector machines (SVMs) or artificial neural networks (ANNs). To benefit from the simple yet one of the most powerful nonparametric machine learning approach k-nearest neighbor classifier, it suffices to compute the pairwise distances among the covariance descriptors using a distance metric involving their generalized eigenvalues, which also follows from the Lie group structure of positive definite matrices. This approach is fast and discriminates polyps from non-polyps with high accuracy using only a small size descriptor, which consists of 36 unique features per image region extracted from the suspicious regions that we have obtained by combined cellular neural network (CNN) and template matching detection method. These suspicious regions are, in average, 15 × 17 = 255 pixels in our experiments. © Springer Science + Business Media, LLC 2008. © 2010 Elsevier B.V., All rights reserved., MEDLINE® is the source for the MeSH terms of this document.Publication Metadata only Telediagnosis of parkinson's disease using measurements of dysphonia(2010) Sakar, C. Okan; Kursun, Olcay; Sakar, C. Okan, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kursun, Olcay, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyParkinson's disease (PD) is a neurological illness which impairs motor skills, speech, and other functions such as mood, behavior, thinking, and sensation. It causes vocal impairment for approximately 90% of the patients. As the symptoms of PD occur gradually and mostly targeting the elderly people for whom physical visits to the clinic are inconvenient and costly, telemonitoring of the disease using measurements of dysphonia (vocal features) has a vital role in its early diagnosis. Such dysphonia features extracted from the voice come in variety and most of them are interrelated. The purpose of this study is twofold: (1) to select a minimal subset of features with maximal joint relevance to the PD-score, a binary score indicating whether or not the sample belongs to a person with PD, and (2) to build a predictive model with minimal bias (i.e. to maximize the generalization of the predictions so as to perform well with unseen test examples). For these tasks, we apply the mutual information measure with the permutation test for assessing the relevance and the statistical significance of the relations between the features and the PD-score, rank the features according to the maximum-relevance-minimum-redundancy (mRMR) criterion, use a Support Vector Machine (SVM) for building a classification model and test it with a more suitable cross-validation scheme that we called leave-one-individual-out that fits with the dataset in hand better than the conventional bootstrapping or leave-one-out validation methods. © 2009 Springer Science+Business Media, LLC. © 2010 Elsevier B.V., All rights reserved., MEDLINE® is the source for the MeSH terms of this document.Publication Metadata only Coupled nonparametric shape and moment-based intershape pose priors for multiple basal ganglia structure segmentation(2010) Uzunbaş, Mustafa Gökhan; Soldea, Octavian; Ünay, Devrim; Çetin, Müjdat; Unal, Gozde Bozkurt; Erçil, Aytül; Ekin, Ahmet; Uzunbaş, Mustafa Gökhan, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey, Department of Computer Science, Piscataway, United States; Soldea, Octavian, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Ünay, Devrim, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Çetin, Müjdat, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Unal, Gozde Bozkurt, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Erçil, Aytül, Faculty of Engineering and Natural Sciences, Sabancı Üniversitesi, Tuzla, Turkey; Ekin, Ahmet, Video Processing and Analysis Group, Philips Research, Eindhoven, NetherlandsThis paper presents a new active contour-based, statistical method for simultaneous volumetric segmentation of multiple subcortical structures in the brain. In biological tissues, such as the human brain, neighboring structures exhibit co-dependencies which can aid in segmentation, if properly analyzed and modeled. Motivated by this observation, we formulate the segmentation problem as a maximum a posteriori estimation problem, in which we incorporate statistical prior models on the shapes and intershape (relative) poses of the structures of interest. This provides a principled mechanism to bring high level information about the shapes and the relationships of anatomical structures into the segmentation problem. For learning the prior densities we use a nonparametric multivariate kernel density estimation framework. We combine these priors with data in a variational framework and develop an active contour-based iterative segmentation algorithm. We test our method on the problem of volumetric segmentation of basal ganglia structures in magnetic resonance images. We present a set of 2-D and 3-D experiments as well as a quantitative performance analysis. In addition, we perform a comparison to several existent segmentation methods and demonstrate the improvements provided by our approach in terms of segmentation accuracy. © 2010 IEEE. © 2010 Elsevier B.V., All rights reserved.Publication Metadata only Denoising embolic Doppler ultrasound signals using Dual Tree Complex Discrete Wavelet Transform(2010) Serbes, Görkem; Aydın, Nizamettin; Serbes, Görkem, Department of Electrical Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Aydın, Nizamettin, Department of Computer Engineering, Yıldız Teknik Üniversitesi, Istanbul, TurkeyEarly and accurate detection of asymptomatic emboli is important for monitoring of preventive therapy in stroke-prone patients. One of the problems in detection of emboli is the identification of an embolic signal caused by very small emboli. The amplitude of the embolic signal may be so small that advanced processing methods are required to distinguish these signals from Doppler signals arising from red blood cells. In this study instead of conventional discrete wavelet transform, the Dual Tree Complex Discrete Wavelet Transform was used for denoising embolic signals. Performances of both approaches were compared. Unlike the conventional discrete wavelet transform discrete complex wavelet transform is a shift invariant transform with limited redundancy. Results demonstrate that the Dual Tree Complex Discrete Wavelet Transform based denoising outperforms conventional discrete wavelet denoising. Approximately 8 dB improvement is obtained by using the Dual Tree Complex Discrete Wavelet Transform compared to the improvement provided by the conventional Discrete Wavelet Transform (less than 5 dB). © 2010 IEEE. © 2011 Elsevier B.V., All rights reserved.Publication Metadata only The 2010 Eurobarometer on the life sciences(2011) Gaskell, George D.; Allansdottir, Agnes; Allum, Nick; Castro, Paula; Esmer, Yilmaz; Fischler, Claude; Jackson, Jonathan; Kronberger, Nicole; Hampel, Jürgen; Mejlgaard, Niels; Gaskell, George D., London School of Economics and Political Science, London, United Kingdom; Allansdottir, Agnes, Università degli Studi di Siena, Siena, Italy; Allum, Nick, University of Essex, Colchester, United Kingdom; Castro, Paula, Iscte – Instituto Universitário de Lisboa, Lisbon, Portugal; Esmer, Yilmaz, Bahçeşehir Üniversitesi, Istanbul, Turkey; Fischler, Claude, École des Hautes Études en Sciences Sociales, Paris, France; Jackson, Jonathan, London School of Economics and Political Science, London, United Kingdom; Kronberger, Nicole, Johannes Kepler University Linz, Linz, Austria; Hampel, Jürgen, Universität Stuttgart, Stuttgart, Germany; Mejlgaard, Niels, Aarhus Universitet, Aarhus, Denmark[No abstract available]Publication Metadata only The impact of conservative discourses in family policies, population politics, and gender rights in Poland and Turkey(2011) Korkut, Umut; Eslen-Ziya, Hande; Korkut, Umut, Glasgow Business School, Glasgow Caledonian University, Glasgow, United Kingdom; Eslen-Ziya, Hande, Bahçeşehir Üniversitesi, Istanbul, TurkeyThis article uses childcare as a case study to test the impact of ideas that embody a traditional understanding of gender relations in relation to childcare. Conservative ideas regard increasing female labor market participation as a cause of decreasing fertility on the functioning of a set of general policies to increase fertility rates. It looks into the Polish and Turkish contexts for empirical evidence. The Polish context shows a highly institutionalized system of family policies in contrast to almost unessential institutions in Turkey. Formally, the labor market participation of women is much lower in Turkey than in Poland. Yet, given the size of the informal market in Turkey, womens labor participation is obviously higher than what appears in the statistics. Bearing in mind this divergence, the article suggests Poland and Turkey as two typologies for studying population politics in contexts where socially conservative ideas regarding gender remain paramount. We qualify ideas as conservative if they enforce a traditional understanding of gender relations in care-giving and underline womens role in the labor market as an element of declining fertility. In order to delineate ideational impact, this article looks into how ideas (a) supplant and (b) substitute formal institutions. Therefore, we argue that there are two mechanisms pertaining to the dominance of conservative conventions: conservative ideas may either supplant the institutional impact on family policies, or substitute them thanks to a superior reasoning which societies assign to them. Furthermore, conservative conventions prevail alongside womens customary unpaid work as care-givers regardless of the level of their formal workforce participation. We propose as our major findings for the literature of population politics that ideas, as ubiquitous belief systems, are more powerful than institutions since they provide what is perceived as legitimate, acceptable, and good for the societies under study. In the end, irrespective of the presence of institutions, socially conservative ideas prevail. © The Author 2011. Published by Oxford University Press. All rights reserved. © 2012 Elsevier B.V., All rights reserved., MEDLINE® is the source for the MeSH terms of this document.Publication Metadata only A new methodology to associate snps with human diseases according to their pathway related context(2011) Bakir-Güngör, Burcu; Sezerman, Osman Uğur; Bakir-Güngör, Burcu, Biological Sciences and Bioengineering Program, Sabancı Üniversitesi, Tuzla, Turkey, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Sezerman, Osman Uğur, Biological Sciences and Bioengineering Program, Sabancı Üniversitesi, Tuzla, TurkeyGenome-wide association studies (GWAS) with hundreds of żthousands of single nucleotide polymorphisms (SNPs) are popular strategies to reveal the genetic basis of human complex diseases. Despite many successes of GWAS, it is well recognized that new analytical approaches have to be integrated to achieve their full potential. Starting with a list of SNPs, found to be associated with disease in GWAS, here we propose a novel methodology to devise functionally important KEGG pathways through the identification of genes within these pathways, where these genes are obtained from SNP analysis. Our methodology is based on functionalization of important SNPs to identify effected genes and disease related pathways. We have tested our methodology on WTCCC Rheumatoid Arthritis (RA) dataset and identified: i) previously known RA related KEGG pathways (e.g., Toll-like receptor signaling, Jak-STAT signaling, Antigen processing, Leukocyte transendothelial migration and MAPK signaling pathways), ii) additional KEGG pathways (e.g., Pathways in cancer, Neurotrophin signaling, Chemokine signaling pathways) as associated with RA. Furthermore, these newly found pathways included genes which are targets of RA-specific drugs. Even though GWAS analysis identifies 14 out of 83 of those drug target genes, newly found functionally important KEGG pathways led to the discovery of 25 out of 83 genes, known to be used as drug targets for the treatment of RA. Among the previously known pathways, we identified additional genes associated with RA (e.g. Antigen processing and presentation, Tight junction). Importantly, within these pathways, the associations between some of these additionally found genes, such as HLA-C, HLA-G, PRKCQ, PRKCZ, TAP1, TAP2 and RA were verified by either OMIM database or by literature retrieved from the NCBI PubMed module. With the whole-genome sequencing on the horizon, we show that the full potential of GWAS can be achieved by integrating pathway and network-oriented analysis and prior knowledge from functional properties of a SNP. © 2011 Bakir-Gungor, Sezerman. © 2012 Elsevier B.V., All rights reserved.Publication Metadata only Feature extraction using time-frequency/scale analysis and ensemble of feature sets for crackle detection(2011) Serbes, Görkem; Sakar, C. Okan; Kahya, Yasemin Palanduz; Aydın, Nizamettin; Serbes, Görkem, Department of Mechanical Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Sakar, C. Okan, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kahya, Yasemin Palanduz, Department of Electrical Engineering, Boğaziçi Üniversitesi, Bebek, Turkey; Aydın, Nizamettin, Department of Computer Engineering, Yıldız Teknik Üniversitesi, Istanbul, TurkeyPulmonary crackles are used as indicators for the diagnosis of different pulmonary disorders. Crackles are very common adventitious sounds which have transient characteristic. From the characteristics of crackles such as timing and number of occurrences, the type and the severity of the pulmonary diseases can be obtained. In this study, a novel method is proposed for crackle detection. In this method, various feature sets are extracted using time-frequency and time-scale analysis. The extracted feature sets are fed into support vector machines both individually and as an ensemble of networks. Besides, as a preprocessing stage in order to improve the success of the model, frequency bands containing no-information are removed using dual tree complex wavelet transform, which is a shift invariant transform with limited redundancy and an improved version of discrete wavelet transform. The comparative results of individual feature sets and ensemble of sets with pre-processed and non pre-processed data are proposed. © 2011 IEEE. © 2012 Elsevier B.V., All rights reserved.