Yazar "Arslan, Ahmet Kadir" seçeneğine göre listele
Listeleniyor 1 - 20 / 65
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A novel software for method comparison: MCS (method comparison software)-assessing agreement between estimated fetal weights calculated by Hadlock I-V formulas and birth weight(Springer Heidelberg, 2024) Yasar, Seyma; Arslan, Ahmet Kadir; Polat, Busra Berfin; Melekoglu, Rauf; Colak, Cemil; Yologlu, SaimIntroductionThe evaluation of the performance of new methods, expected to provide cheaper and faster results than existing (reference) methods in the health field, is based on comparing the results obtained with this new method to those obtained with the existing method. The primary aim of this study is to examine the correlational and absolute agreement between measurement methods in clinical studies using Bland-Altman analysis and methodological (Ordinary Least Squares, Weighted Ordinary Least Squares, Deming, Weighted Deming, Passing-Bablok, Theil-Sen, and Passing-Bablok for Large Data Sets.) methods, and the secondary aim is to compare the accuracy and precision of Hadlock (I-V) formulas used for fetal weight estimation.Materials and methodsThe study was conducted on singleton pregnancies examined in the Prenatal Diagnosis and Treatment Unit of the Department of Obstetrics and Gynecology at Inonu University Faculty of Medicine and who gave birth in the Obstetrics Unit between 01.01.2020 and 01.09.2023, whose gestational ages were confirmed by first-trimester ultrasonography. Estimated fetal weights were calculated using Hadlock (I-V) formulas, and the agreement of these weights with birth weight was evaluated with Bland-Altman method.ResultsThe comparison of estimated fetal weights calculated using Hadlock formulas with birth weight was analyzed using Bland-Altman analysis, ICC, and CCC values along with regression analyses. According to the mean difference values obtained by Bland-Altman analysis, the estimated fetal birth weights obtained by the Hadlock IV formula were most consistent with the actual birth weights.ConclusionsThe estimated fetal weights obtained using the Hadlock IV formula resulted in the closest measurements to the birth weight. This study showcases the efficacy of a new web-based software, Method Comparison Software (MCS), which can be utilized for evaluating the agreement between different methods in clinical measurements.Öğe Application of medical data mining on the prediction of apache II score(Medicine Science | International Medical Journal, 2015) Çolak, Cemil; Aydoğan, Mustafa Said; Arslan, Ahmet Kadir; Yücel, AytaçThe Acute Physiology and Chronic Health Evaluation (APACHE II) is a beneficial tool for the estimation of risk and the comparison of the patients who received care with similar risk properties. Machine learning based systems can assist clinicians in the early diagnosis of diseases. This research aimed at predicting the APACHE II score using Support Vector Machine (SVM) from Medical Data Mining (MDM). The records of 280 patients from intensive care unit included the dataset containing the target variable (the APACHE II score), and 23 demographical/clinical predictor variables. Genetic algorithm based feature selection and 10-fold cross validation method were employed. SVM with radial basis (RBF) was constructed. The performance of the proposed approach was assessed using root mean squared error (RMSE), mean absolute error (MAE), correlation (R) and coefficient of determination (R2). Mean age of the individuals was 51±23 years. 153 (54.6%) were females, and 127 (45.4%) were males. The proposed approach yielded the values of 1.037 for RMSE, 0.727 for MAE, 0.993 for R and 0.986 for R2, respectively. The results demonstrated that the proposed approach had an excellent predictive performance of the APACHE II score. Additionally, ensemble approaches such as bagging, boosting, voting etc. can improve markedly the performance of the prediction and classification tasks.Öğe Application of Medical Data Mining on the Prediction of APACHE II Score(2015) Çolak, Cemil; Aydoğan, Mustafa Said; Arslan, Ahmet Kadir; Yücel, AytaçThe Acute Physiology and Chronic Health Evaluation (APACHE II) is a beneficial tool for the estimation of risk and the comparison of the patients who received care with similar risk properties. Machine learning based systems can assist clinicians in the early diagnosis of diseases. This research aimed at predicting the APACHE II score using Support Vector Machine (SVM) from Medical Data Mining (MDM). The records of 280 patients from intensive care unit included the dataset containing the target variable (the APACHE II score), and 23 demographical/clinical predictor variables. Genetic algorithm based feature selection and 10-fold cross validation method were employed. SVM with radial basis (RBF) was constructed. The performance of the proposed approach was assessed using root mean squared error (RMSE), mean absolute error (MAE), correlation (R) and coefficient of determination (R2). Mean age of the individuals was 51±23 years. 153 (54.6%) were females, and 127 (45.4%) were males. The proposed approach yielded the values of 1.037 for RMSE, 0.727 for MAE, 0.993 for R and 0.986 for R, respectively. The results demonstrated that the proposed approach had an excellent predictive performance of the APACHE II score. Additionally, ensemble approaches such as bagging, boosting, voting etc. can improve markedly the performance of the prediction and classification tasks.Öğe Application of medical data mining on the prediction of apache ıı score(Medicine Science | International Medical Journal, 2015) Çolak, Cemil; Aydogan, Mustafa Said; Arslan, Ahmet Kadir; Yücel, AytaçThe Acute Physiology and Chronic Health Evaluation (APACHE II) is a beneficial tool for the estimation of risk and the comparison of the patients who received care with similar risk properties. Machine learning based systems can assist clinicians in the early diagnosis of diseases. This research aimed at predicting the APACHE II score using Support Vector Machine (SVM) from Medical Data Mining (MDM). The records of 280 patients from intensive care unit included the dataset containing the target variable (the APACHE II score), and 23 demographical/clinical predictor variables. Genetic algorithm based feature selection and 10-fold cross validation method were employed. SVM with radial basis (RBF) was constructed. The performance of the proposed approach was assessed using root mean squared error (RMSE), mean absolute error (MAE), correlation (R) and coefficient of determination (R2 ). Mean age of the individuals was 51±23 years. 153 (54.6%) were females, and 127 (45.4%) were males. The proposed approach yielded the values of 1.037 for RMSE, 0.727 for MAE, 0.993 for R and 0.986 for R2 , respectively. The results demonstrated that the proposed approach had an excellent predictive performance of the APACHE II score. Additionally, ensemble approaches such as bagging, boosting, voting etc. can improve markedly the performance of the prediction and classification tasks.Öğe Assessment of Association Rule Mining Using Interest Measures on the Gene Data(2022) Akbaş, Kübra Elif; Kıvrak, Mehmet; Arslan, Ahmet Kadir; Yakınbas, Tuğçe; Korkmaz, Hasan; Onalan, Ebru; Çolak, CemilAim: Data mining is the discovery process of beneficial information, not revealed from large-scale data beforehand. One of the fields in which data mining is widely used is health. With data mining, the diagnosis and treatment of the disease and the risk factors affecting the disease can be determined quickly. Association rules are one of the data mining techniques. The aim of this study is to determine patient profiles by obtaining strong association rules with the apriori algorithm, which is one of the association rule algorithms. Material and Method: The data set used in the study consists of 205 acute myocardial infarction (AMI) patients. The patients have also carried the genotype of the FNDC5 (rs3480, rs726344, rs16835198) polymorphisms. Support and confidence measures are used to evaluate the rules obtained in the Apriori algorithm. The rules obtained by these measures are correct but not strong. Therefore, interest measures are used, besides two basic measures, with the aim of obtaining stronger rules. In this study For reaching stronger rules, interest measures lift, conviction, certainty factor, cosine, phi and mutual information are applied. Results: In this study, 108 rules were obtained. The proposed interest measures were implemented to reach stronger rules and as a result 29 of the rules were qualified as strong. Conclusion: As a result, stronger rules have been obtained with the use of interest measures in the clinical decision making process. Thanks to the strong rules obtained, it will facilitate the patient profile determination and clinical decision-making process of AMI patients.Öğe Çeşitli Çekirdek Fonksiyonları ile Oluşturulan Destek Vektör Makinesi Modellerinin Performanslarının İncelenmesi: Bir Klinik Uygulama(2017) Güldoğan, Emek; Arslan, Ahmet Kadir; Yağmur, JülideAmaç: Bu araştırmanın birincil amacı; çeşitli çekirdek fonksiyonları ile oluşturulan destek vektör makinesi modellerinin, Akut Koroner Sendromlu hastalarda diabetes mellitusu sınıflandırma performanslarının incelenmesi ve karşılaştırılmasıdır. Bu araştırmanın ikincil amacı ise, destek vektör makinesi modeli oluşturulurken kullanılan çeşitli çekirdek fonksiyonlarının parametrelerinin optimize edilerek en iyi sınıflandırma perfo rmansını elde etmeye çalışmaktır. Gereç ve Yöntem: Bu çalışmada incelenen veriler, İnönü Üniversitesi T urgut Özal Tıp Merkezi Kardiyoloji Anabilim Dalı için geliştirilen veritabanından geriye yönelik (retrospektif) olarak seçilmiştir. Çalışmadaki söz konusu veriler Akut Koroner Sendromlu hastalarda tip 2 diabetes mellitus ile değişik demografik ve klinik değişkenleri içermektedir. Akut Koroner Sendromlu hastalarda tip 2 diabetes mellitus'un sınıflandırılması için Destek Vektör Makinesi modelleri kullanılmıştır. İlgili modeller, ANOVA radyal tabanlı fonksiyon, bessel, doğrusal, Gaussian radyal tabanlı fonksiyon, laplace, polinomiyal ve sigmoid çekirdekleri ile oluşturulmuştur. Bulgular: Laplace çekirdek fonksiyonu ile oluşturulan en iyi sınıflama performansına sahip destek vektör makinesi modeline ilişkin doğr uluk, ROC eğrisi altında kalan alan, duyarlılık ve özgüllük [seçicilik] ölçütleri ile % 95 güven aralığı değerleri sırasıyla; 0.9804 (0.9716 - 0.987), 0.9332 (0.9096 - 0.9567), 0.9999 (0.9791 - 1.000) ve 0.9776 (0.9675 - 0.9852) olarak elde edilmiştir. Sonuç: İncelenen değişik çekirdek fonksiyonları ile oluşturulan modeller arasında söz konusu performans ölçütleri dikkate alındığında, en iyi sınıflama performansı laplace Destek Vektör Makinesi modelinden elde edilmiştir. İlerleyen çalışmalarda, farklı klinik verilerde değişik çekirdek fonksiyonlu Destek Vektör Makinesi modelleri ile diğer makine öğrenmesi ya da veri madenciliği algoritmalarının kullanılması hastalıkların sınıflandırma başarısını artırabilecektir.Öğe Combining the Strengths of the Explainable Boosting Machine and Metabolomics Approaches for Biomarker Discovery in Acute Myocardial Infarction(Mdpi, 2024) Arslan, Ahmet Kadir; Yagin, Fatma Hilal; Algarni, Abdulmohsen; AL-Hashem, Fahaid; Ardigo, Luca PaoloAcute Myocardial Infarction (AMI), a common disease that can have serious consequences, occurs when myocardial blood flow stops due to occlusion of the coronary artery. Early and accurate prediction of AMI is critical for rapid prognosis and improved patient outcomes. Metabolomics, the study of small molecules within biological systems, is an effective tool used to discover biomarkers associated with many diseases. This study intended to construct a predictive model for AMI utilizing metabolomics data and an explainable machine learning approach called Explainable Boosting Machines (EBM). The EBM model was trained on a dataset of 102 prognostic metabolites gathered from 99 individuals, including 34 healthy controls and 65 AMI patients. After a comprehensive data preprocessing, 21 metabolites were determined as the candidate predictors to predict AMI. The EBM model displayed satisfactory performance in predicting AMI, with various classification performance metrics. The model's predictions were based on the combined effects of individual metabolites and their interactions. In this context, the results obtained in two different EBM modeling, including both only individual metabolite features and their interaction effects, were discussed. The most important predictors included creatinine, nicotinamide, and isocitrate. These metabolites are involved in different biological activities, such as energy metabolism, DNA repair, and cellular signaling. The results demonstrate the potential of the combination of metabolomics and the EBM model in constructing reliable and interpretable prediction outputs for AMI. The discussed metabolite biomarkers may assist in early diagnosis, risk assessment, and personalized treatment methods for AMI patients. This study successfully developed a pipeline incorporating extensive data preprocessing and the EBM model to identify potential metabolite biomarkers for predicting AMI. The EBM model, with its ability to incorporate interaction terms, demonstrated satisfactory classification performance and revealed significant metabolite interactions that could be valuable in assessing AMI risk. However, the results obtained from this study should be validated with studies to be carried out in larger and well-defined samples.Öğe Comparison of Performances of Associative ClassificationMethods for Cervical Cancer Prediction: Observational Study(2021) Yağın, Fatma Hilal; Yağın, Burak; Arslan, Ahmet Kadir; Çolak, CemilObjective: Associative classification is a method thatgenerates a rule-based classifier in a categorical data set. The mainpurpose of the associative classification is to create classificationmodels with high performance and, in addition, to improve inter pretability thanks to the rules it creates. In this study, it is aimed toclassify, predict cervical cancer with the methods of relational clas sification and to determine the most important parameters and rela tional rules associated with the disease. Material and Methods: Inthe study, regular class association rules (RCAR) and classificationbased on associations (CBA) methods were applied to the openaccess data set named “Cervical Cancer Behavioral Risk Data Set”and the results were compared. In order to separate the numericalvariables in the data set, Boruta feature selection method was ap plied to determine the most important features about Ameva andcervical cancer. The performances of the created relational classifi cation models were evaluated with accuracy, balanced accuracy,sensitivity, specificity, Matthews correlation coefficient (MCC), G mean, diagnostic accuracy, Youden’s index, positive predictivevalue, negative predictive value and F1-score criteria. Results: Ac cording to CBA model results, sensitivity is 100%, specificity 98%,accuracy 98.6%, balanced accuracy 99%, Youden's index 98%,MCC 96.7%, diagnostic accuracy 98.6%, G-mean 97.7%, negativepredictive value 1%, positive predictive value 95.5%, and F1 score97.7%. According to RCAR model results, sensitivity is 90.5%,specificity 98%, accuracy 95.8%, balanced accuracy 94.3%,Youden's index 88.5%, MCC 89.8%, diagnostic accuracy 95.8%,G-mean 95.6%, negative predictive value 96.2%, positive predic tive value 95%, and F1 score 92.7%. Conclusion: When the resultsare examined, it can be said that the CBA model is more successfulin classifying cervical cancer compared to the RCAR model. Inaddition, the relational classification models created in this studyand the rules obtained regarding the disease are promising in termsof their use in early diagnosis and preventive medicine practices forcervical cancer.Öğe Contribution of aspiration to the diagnosis of lung cancer in endobronchial ultrasound-guided fine-needle biopsy(Assoc Medica Brasileira, 2021) Guven, Arzu Nakis; Yalcinsoy, Murat; Akatli, Ayse Nur; Arslan, Ahmet KadirOBJECTIVE: Endobronchial ultrasound-guided transbronchial needle aspiration has been successfully applied in both diagnosis and staging of mediastinal and hilar lymphadenopathies and masses, especially in malignant cases. However, the optimal procedure of Endobronchial ultrasound-guided transbronchial needle aspiration to further increase diagnostic yield and minimize processing complexity remains controversial. This study aims to compare aspiration biopsy (Endobronchial ultrasound-guided transbronchial needle aspiration) and non-aspiration biopsy (Endobronchial ultrasound-guided transbronchial needle capillary sampling) in terms of sample adequacy, diagnosis, and quality in malignant cases. METHODS: Between March 2018 and June 2020, Endobronchial ultrasound- guided was performed sequentially on patients with mediastinal and/or hilar lymph nodes that were considered malignant. Each lymphadenopathy was sampled with and without aspiration. A single-blinded pathologist evaluated the samples. RESULTS: A total of 84 lymph nodes evaluations of 51 patients were included. Most samples were taken from the right lower paratracheal lymph nodes ( n=27, 32.2%) and subcarinal LN (n=21, 25%). The mean size of the lymph nodes was 21.21 +/- 8.257 (8-40) mm. The agreement between the two procedures in terms of sample adequacy and diagnostic yield was 69.1% (95%CI 58-78.7, p=0.076). In addition, according to the goodness-of-fit statistics, the kappa values were 0.255 (p=0.015) and 0.302 (p=0.004) for sample adequacy and diagnostic yield, respectively. There was no difference between the two procedures in relation to complications. CONCLUSION: Although the agreement between the two procedures is weak, Endobronchial ultrasound-guided transbronchial needle capillary sampling can be performed with less personnel, without reducing diagnostic yield and tissue adequacy. These findings can assist clinicians in determining the optimal procedure for Endobronchial ultrasound-guided.Öğe Derin öğrenme ve topluluk öğrenme yöntemlerine dayalı bilgisayar destekli tanı sisteminin geliştirilmesi: Omik teknolojileri üzerine uygulaması(İnönü Üniversitesi, 2021) Arslan, Ahmet KadirAmaç: Bu tez çalışmasında, kolorektal kanser hastalığına ilişkin açık erişimli deneysel metabolomik veri seti kullanılarak, çeşitli topluluk öğrenme ve derin öğrenme modelleri ile ilgili hastalığın sınıflandırılmasını sağlayabilecek bir ardışık kod sisteminin (pipeline) tasarlanması ve bu kapsamda yüksek çıktılı bir karar destek sisteminin geliştirilmesi amaçlanmıştır. Materyal ve Metot: Bu tez çalışmasında, Washington Üniversitesi, Anesteziyoloji ve Algoloji Bölümü, Northwest Metabolomik Araştırma Merkezi'nde yürütülen PR000226 numaralı proje kapsamında üretilen veri seti kullanılmıştır. İlgili veri seti, iki denek grubu, 66 KRK hastası ve 92 sağlıklı kontrol olmak üzere toplam 158 örnekten oluşmaktadır. Değişken seçim yöntemleri olarak LASSO, Elastic-Net, Boruta ve BorutaShap yöntemleri kullanılmıştır. Sınıflandırma görevinde ise XGBoost, LightGBM, derin sinir ağları ve yığın otokodlayıcı modelleri kullanılmıştır. Bulgular: Bulgular incelendiğinde, en zayıf sınıflandırma performansı gösteren modelin yığın otokodlayıcı olduğu görülmektedir. Modelin hiçbir değişken seçimi senaryosunda istenilen sınıflandırma performansını başarısını gösteremediği görülmektedir. LightGBM modeli hem eğitim hem de test veri setlerinin sınıflandırmasında, tüm performans ölçütleri açısından, en iyi sonuçları vermiştir. Ayrıca LightGBM modeli bu sınıflandırma başarımını tüm değişken seçim yöntemleri bazında elde etmiştir. Sonuç: Bu tez çalışmasında, topluluk öğrenme yöntemlerinin, tüm değişken seçim senaryolarında, derin öğrenme yöntemlerine kıyasla çok daha iyi sınıflandırma sonuçları verdiği görülmüştür. Söz konusu topluluk öğrenme yöntemlerinin, büyük veri setlerinde daha hızlı sonuç verebilmeleri için grafik işlem birimi (GPU) destekli sürümlerinin kullanılmasının işlem ve zaman maliyetleri açısından daha verimli olacağı önerilebilir.Öğe Development of Artificial Intelligence Based Clinical Decision Support System on Medical Images for the Classification of COVID-19(2023) Çolak, Cemil; Arslan, Ahmet Kadir; Ucuzal, Hasan; Köse, Adem; Yıldırım, İsmail Okan; Güldoğan, Emek; Çolak, M. CengizAim: The first imaging method to play an vital role in the diagnosis of COVID-19 illness is the chest X-ray. Because of the abundance of large-scale annotated picture datasets, convolutional neural networks (CNNs) have shown considerable performance in image recognition/classification. The current study aims to construct a successful deep learning model that can distinguish COVID-19 from healthy controls using chest X-ray images.Material and Methods: The dataset in the study consists of subjects with 912 negative and 912 positive PCR results. A prediction model was built using VGG-16 with transfer learning for classifying COVID-19 chest X-ray images. The data set was split at random into 80% training and 20% testing groups.Results: The accuracy, F1 score, sensitivity, specificity, positive and negative values from the model that can successfully distinguish COVID-19 from healthy controls are 97.3%, 97.3%, 97.8%, 96.7%, 96.7%, and 97.8% regarding the testing dataset, respectively.Conclusion: The suggested technique might greatly improve on current radiology-based methodologies and serve as a beneficial tool for clinicians/radiologists in diagnosing and following up on COVID-19 patients.Öğe Different medical data mining approaches based prediction of ischemic stroke(Computer Methods and Programs in Biomedicine, 2016) Arslan, Ahmet Kadir; Çolak, Cemil; Sarıhan, Mehmet EdizAim: Medical data mining (also called knowledge discovery process in medicine) processes for extracting patterns from large datasets. In the current study, we intend to assess different medical data mining approaches to predict ischemic stroke. Materials and methods: The collected dataset from Turgut Ozal Medical Centre, Inonu University, Malatya, Turkey, comprised the medical records of 80 patients and 112 healthy individuals with 17 predictors and a target variable. As data mining approaches, support vector machine (SVM), stochastic gradient boosting (SGB) and penalized logistic regression (PLR) were employed. 10-fold cross validation resampling method was utilized, and model performance evaluation metrics were accuracy, area under ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The grid search method was used for optimizing tuning parameters of the models. Results: The accuracy values with 95% CI were 0.9789 (0.9470–0.9942) for SVM, 0.9737 (0.9397–0.9914) for SGB and 0.8947 (0.8421–0.9345) for PLR. The AUC values with 95% CI were 0.9783 (0.9569–0.9997) for SVM, 0.9757 (0.9543–0.9970) for SGB and 0.8953 (0.8510–0.9396) for PLR. Conclusions: The results of the current study demonstrated that the SVM produced the best predictive performance compared to the other models according to the majority of evaluation metrics. SVM and SGB models explained in the current study could yield remarkable predictive performance in the classification of ischemic stroke.Öğe Different medical data mining approaches based prediction of ischemic stroke(Computer Methods and Programs in Biomedicine, 2016) Arslan, Ahmet Kadir; Çolak, Cemil; Sarıhan, Mehmet EdizMedical data mining (also called knowledge discovery process in medicine) processes for extracting patterns from large datasets. In the current study, we intend to assess different medical data mining approaches to predict ischemic stroke. The collected dataset from Turgut Ozal Medical Centre, Inonu University, Malatya, Turkey, comprised the medical records of 80 patients and 112 healthy individuals with 17 predictors and a target variable. As data mining approaches, support vector machine (SVM), stochastic gradient boosting (SGB) and penalized logistic regression (PLR) were employed. 10-fold cross validation resampling method was utilized, and model performance evaluation metrics were accuracy, area under ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The grid search method was used for optimizing tuning parameters of the models. The accuracy values with 95% CI were 0.9789 (0.9470–0.9942) for SVM, 0.9737 (0.9397–0.9914) for SGB and 0.8947 (0.8421–0.9345) for PLR. The AUC values with 95% CI were 0.9783 (0.9569–0.9997) for SVM, 0.9757 (0.9543–0.9970) for SGB and 0.8953 (0.8510–0.9396) for PLR. The results of the current study demonstrated that the SVM produced the best predictive performance compared to the other models according to the majority of evaluation metrics. SVM and SGB models explained in the current study could yield remarkable predictive performance in the classification of ischemic stroke.Öğe Different medical data mining approaches based prediction of ischemic stroke(Computer Methods and Programs in Biomedicine, 2016) Arslan, Ahmet Kadir; Çolak, Cemil; Sarıhan, Mehmet EdizAim: Medical data mining (also called knowledge discovery process in medicine) processes for extracting patterns from large datasets. In the current study, we intend to assess different medical data mining approaches to predict ischemic stroke. Materials and methods: The collected dataset from Turgut Ozal Medical Centre, Inonu University, Malatya, Turkey, comprised the medical records of 80 patients and 112 healthy individuals with 17 predictors and a target variable. As data mining approaches, support vector machine (SVM), stochastic gradient boosting (SGB) and penalized logistic regression (PLR) were employed. 10-fold cross validation resampling method was utilized, and model performance evaluation metrics were accuracy, area under ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The grid search method was used for optimizing tuning parameters of the models. Results: The accuracy values with 95% CI were 0.9789 (0.9470–0.9942) for SVM, 0.9737 (0.9397–0.9914) for SGB and 0.8947 (0.8421–0.9345) for PLR. The AUC values with 95% CI were 0.9783 (0.9569–0.9997) for SVM, 0.9757 (0.9543–0.9970) for SGB and 0.8953 (0.8510–0.9396) for PLR. Conclusions: The results of the current study demonstrated that the SVM produced the best predictive performance compared to the other models according to the majority of evaluation metrics. SVM and SGB models explained in the current study could yield remarkable predictive performance in the classification of ischemic stroke.Öğe Different medical data mining approaches based prediction of ischemic stroke(Elsevier Ireland Ltd, 2016) Arslan, Ahmet Kadir; Colak, Cemil; Sarihan, Mehmet EdizAim: Medical data mining (also called knowledge discovery process in medicine) processes for extracting patterns from large datasets. In the current study, we intend to assess different medical data mining approaches to predict ischemic stroke. Materials and methods: The collected dataset from Turgut Ozal Medical Centre, Inonu University, Malatya, Turkey, comprised the medical records of 80 patients and 112 healthy individuals with 17 predictors and a target variable. As data mining approaches, support vector machine (SVM), stochastic gradient boosting (SGB) and penalized logistic regression (PLR) were employed. 10-fold cross validation resampling method was utilized, and model performance evaluation metrics were accuracy, area under ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The grid search method was used for optimizing tuning parameters of the models. Results: The accuracy values with 95% CI were 0.9789 (0.9470-0.9942) for SVM, 0.9737 (0.9397-0.9914) for SGB and 0.8947 (0.8421-0.9345) for PLR. The AUC values with 95% CI were 0.9783 (0.9569-0.9997) for SVM, 0.9757 (0.9543-0.9970) for SGB and 0.8953 (0.8510-0.9396) for PLR. Conclusions: The results of the current study demonstrated that the SVM produced the best predictive performance compared to the other models according to the majority of evaluation metrics. SVM and SGB models explained in the current study could yield remarkable predictive performance in the classification of ischemic stroke. (C) 2016 Elsevier Ireland Ltd. All rights reserved.Öğe Digital screen exposure and sleep disorders in children with epilepsy: The impact of sociodemographic, clinical, and individual factors(Academic Press Inc Elsevier Science, 2026) Yucel, Gul; Arslan, Ahmet Kadir; Bicakcioglu, Isinsu; Ekici, Nur Yucel; Ozgor, BilgeObjective: The aim of this study is to determine the relationship between daily digital screen exposure and sleep disorders in children with epilepsy (CWE), focusing on different sleep subdomains. In addition, the possible regulatory role of socio-demographic factors and individual chronotype characteristics affecting digital screen exposure was also evaluated. Methods: This cross-sectional analytical study included 132 CWE and their mothers. Data were collected using sociodemographic/clinical forms, the Sleep Disturbances Scale for Children (SDSC), the Pittsburgh Sleep Quality Index (PSQI), and the Children's Chronotype Questionnaire (CCQ). Digital screen exposure was assessed using a parent-reported form; daily exposure was calculated by taking the weighted average of weekday and weekend usage times. Results: The study found a significant, positive correlation between average digital screen exposure time and total SDSC score (rho = 0.23; p = 0.008). This association was particularly evident in the subdomains of disorders of initiating and maintaining sleep (DIMS), disorders of excessive somnolence (DOES), and sleep--related breathing disorders (SDB). Socio-demographically, maternal education level significantly affected digital screen exposure; children of mothers with a university degree had statistically lower digital screen exposure (p = 0.001). While total digital screen exposure did not differ by chronotype, a stronger positive correlation between digital screen exposure and the SDB subdomain was observed in children with an evening chronotype (rho = 0.363; p = 0.045). Conclusion: These findings indicate that increased digital screen exposure significantly, but only weakly/ moderately, associated with increased the severity of sleep disorders in CWE. Maternal education level and individual chronotype differences play a critical role in managing this negative relationship and identifying at-risk groups. Clinicians should develop personalized intervention programs regarding digital screen exposure, particularly for families with children who have low educational levels and are biologically at risk (evening chronotype).Öğe DO disease stages affect oxidative stress in stable COPD?(Cell Press, 2024) Yalcinsoy, Murat; Beykumul, Aysegul; Gulbas, Gazi; Arslan, Ahmet Kadir; Neselioglu, SalimBackground: Detection of oxidative stress level may lead us to understand the pathogenesis of COPD better and to search for new treatments. Oxidative stress levels have also been shown to be elevated in stable COPD patients. We aimed to investigate whether the stage of COPD affects the severity of inflammation-induced oxidative stress in patients with stable COPD. Methods: Between June 2019 and March 2020, all consecutive patients admitted to COPD-specific outpatient clinics were included. Patients were classified A, B, and E according to the GOLD guideline. Results: The median age of 98 patients (Male: 92 (93.9 %)) was 65 (min-max: 49-86). A statistically significant difference was found between the groups in FEV1, FVC, and FEV1/FVC (p < 0.001). age, and thiols (r = -0.168, p = 0.049; r = -0.184, p = 0.035) and DS (r = -0.209, p = 0.019) were found to be negatively correlated at a low level. When adjusted for age, oxidative stress parameters were similar between stages. Conclusion: No difference between stages and oxidative stress parameters according to GOLD classification in stable COPD patients. Our results may be a guide for not using anti-inflammatory therapy except for attacks.Öğe Effect of oxygen administration with double nasal cannula on respiratory complications in gastrointestinal endoscopy(2025) Demiroz, Duygu; Sanli, Mukadder; Gülhas, Nurçın; Arslan, Ahmet Kadir; Atayan, Yahya; Toplu, Hacı OsmanIn the present study, the purpose was to investigate the effect of oxygen therapy applied with a double nasal cannula on desaturation and respiratory complications in cases planned for gastrointestinal endoscopy. A total of 300 patients with ASA I-II, between the ages of 18-65, who were scheduled to undergo gastrointestinal endoscopy, were included in the study. Following routine monitoring, the patients were randomized into 3 groups using the envelope method. Group TK5 (n=100) was administered 5 liters/minute (L/min) preoxygenation with a nasal oxygen cannula for 5 minutes during the procedure and afterwards, 5 L/min oxygen in the same manner. Group TK15 (n=100) was administered 15 L/min preoxygenation with a nasal oxygen cannula for 5 minutes during the procedure and afterwards, 15 L/min oxygen in the same manner. Group CK30 (n=100): 30 L/min preoxygenation with a double nasal oxygen cannula for 5 minutes, and 30 L/min oxygen in the same manner during and after the procedure. The incidence of desaturation was found to be significantly lower in GTK15 (7%) and GCK30 (2%) compared to GTK5 (31%) (p<0.05). Advanced desaturation was not detected in any patient in GTK15 and GTK30, while it was detected in 18% of the GTK5 group (p<0.05). Severe desaturation was detected in 11% of the GTK5 group, while there was no severe desaturation in the other groups (p<0.05). The duration of desaturation was longer in GTK5 than in the other groups. The time to reach 99% oxygen saturation was significantly shorter in the G15 and G30 groups compared to the G5 group (p < 0.05). This time was significantly shorter in GCK30 than in GTK15 (p<0.05). However, there was a burning sensation in the nose in 30% of the patients in double nasal cannula oxygen applications (p<0.05). It was found that oxygen administration with a double nasal cannula had similar effectiveness to single nasal cannula 15 L/min flows in preventing respiratory complications in sedation applications performed for gastrointestinal system endoscopies, and that respiratory complications were significantly reduced at both flow rates compared to 5 L flow rates. It was also found that a single cannula 15 L/min application was better in terms of patient comfort.Öğe The effects of total parenteral nutrition on telomerase expression in rabbit(2018) Gürünlüoğlu, Kubilay; Bayrakci, Ercan; Kocabıyık, Alper; Gökçe, Hasan; Taşkapan, Mehmet Çağatay; Taşcı, Aytaç; Aksungur, Zeynep; Arslan, Ahmet Kadir; Demircan, MehmetAbstract: Aim: Total parenteral nutrition (TPN) is a technique which is use to give vitally mandatory substances in to the venous compartments whenever the gastrointestinal system cannot be used by the patients. Telomerase catalyzes DNA synthesis, which is necessary to maintain telomere length and stabilize the genome to allow continued cell proliferation. In this study, we explored the effects of TPN administration on telomerase reverse transcriptase (TERT) expression in various tissue and serum telomerase level. Material and Methods: In this study a number of 42 same-aged albino, equal number of male and female, new zealand rabbits were use, divided in to three groups. Group 1 rabbits received TPN for 10 days via a central venous catheter. Group 2 received 50 mL/ kg/day physiological saline via a central venous catheter. Group 3 served as the control group. The rabbits were sacrificed after 10 days, and serum telomerase levels were measured by enzyme-linked immunosorbent assay. TERT expression in gonadal, liver, jejunum, and skin tissues were determined immunohistochemically. Blood samples were obtained before and after TPN and saline administration in the TPN and serum saline groups, respectively, and at the end of the experiment in the control group. Results: Telomerase expression in liver, gonads and serum level of TPN group was significantly higher than control and serum saline groups. Conclusion: TPN may be a positive effect in liver and gonadal telomer kinetic. However, we think that TPN increases DNA damage throughout the body.Öğe The effects of total parenteral nutrition on telomerase expression in rabbit(2018) Gurunluoglu, Kubilay; Bayrakci, Ercan; Gokce, Hasan; Kocbiyik, Alper; Taskapan, Cagatay; Tasci, Aytac; Aksungur, Zeynep; Arslan, Ahmet Kadir; Demircan, MehmetAbstract Aim: Total parenteral nutrition (TPN) is a technique which is use to give vitally mandatory substances in to the venous compartments whenever the gastrointestinal system cannot be used by the patients. Telomerase catalyzes DNA synthesis, which is necessary to maintain telomere length and stabilize the genome to allow continued cell proliferation. In this study, we explored the effects of TPN administration on telomerase reverse transcriptase (TERT) expression in various tissue and serum telomerase level. Material and Methods: In this study a number of 42 same-aged albino, equal number of male and female, new zealand rabbits were use, divided in to three groups. Group 1 rabbits received TPN for 10 days via a central venous catheter. Group 2 received 50 mL/ kg/day physiological saline via a central venous catheter. Group 3 served as the control group. The rabbits were sacrificed after 10 days, and serum telomerase levels were measured by enzyme-linked immunosorbent assay. TERT expression in gonadal, liver, jejunum, and skin tissues were determined immunohistochemically. Blood samples were obtained before and after TPN and saline administration in the TPN and serum saline groups, respectively, and at the end of the experiment in the control group. Results: Telomerase expression in liver, gonads and serum level of TPN group was significantly higher than control and serum saline groups. Conclusion: TPN may be a positive effect in liver and gonadal telomer kinetic. However, we think that TPN increases DNA damage throughout the body.
