21 results on '"Arslan, Ahmet Kadir"'
Search Results
2. The effect of different norepinephrine administration methods on hypotension after spinal anesthesia in caesarean sections.
- Author
-
Seyhun, Nursen, Gulhas, Nurcin, Ozkan, Ahmet Selim, Duz, Senem Arda, and Arslan, Ahmet Kadir
- Subjects
SYSTOLIC blood pressure ,BOLUS drug administration ,SPINAL anesthesia ,ANESTHESIA in obstetrics ,SALINE solutions - Abstract
We aimed to evaluate the effect of different routes of norepinephrine (NE) administration on maternal hypotension in pregnant females undergoing spinal anesthesia for caesarean section. 208 pregnant women were divided randomly into 4 groups (n=52). Bolus 4 µg/ml NE was administered intravenous (iv) immediately after spinal anesthesia in Group PB (Prophylactic Bolus). In Group PI (Prophylactic Infusion), 1 ml of saline solution was applied promptly after spinal anesthesia and then the NE infusion was started at 1 ml/min. In Group TB (Treatment Bolus), 1 ml Physiological Saline (PS) was administered after 1 ml/min infusion of PS immediately after spinal anesthesia and then 1 ml/min NE bolus when blood pressure decreased by 20% after the entry. In Group TBI (Treatment Bolus Infusion), 1 ml PS was administered after 1 ml/min infusion of PS immediately after spinal anesthesia, 1 ml NE and then 1 ml/min NE infusion was initiated when blood pressure decreased by 20% after the entry. At the 4th, 6th, and 8th minutes, the PI Group exhibited higher systolic and mean blood pressures than the other groups (p<.001). Additionally, hypotension was statistically lower in the PI Group than in PB, TB, TBI groups (p<.001), and episodes of hypotension, ephedrine required and extra NE boluses given were statistically lower in the PI Group than in the other groups (p<.001). Umbilical vein (UV) pH values were lower in the TBI Group at compared to the other groups (p<.001). It is suggested that a prophylactic infusion of 4 µg/min of NE in the prevention of hypotension following spinal anesthesia for cesarean section will reduce the possibility of maternal hypotension and better maintain fetal well-being than a prophylactic bolus, a treatment bolus or a posttreatment bolus infusion at the same dose. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Combining the Strengths of the Explainable Boosting Machine and Metabolomics Approaches for Biomarker Discovery in Acute Myocardial Infarction.
- Author
-
Arslan, Ahmet Kadir, Yagin, Fatma Hilal, Algarni, Abdulmohsen, AL-Hashem, Fahaid, and Ardigò, Luca Paolo
- Subjects
- *
MYOCARDIAL infarction , *BIOLOGICAL systems , *CORONARY occlusion , *SMALL molecules , *BIOMOLECULES - Abstract
Acute 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. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Incidence of emergency surgery in anterior abdominal wall hernias
- Author
-
Karatas, Turgay, primary, Selcuk, Engin Burak, additional, Karatas, Mehmet, additional, Yildirim, Atilla, additional, Tahtali, Ibrahim Nuvit, additional, and Arslan, Ahmet Kadir, additional
- Published
- 2023
- Full Text
- View/download PDF
5. Comparison of "primary repair" and "placing a drain without repair" methods in duodenum perforations.
- Author
-
Karataş, Turgay, Kanlıöz, Murat, Karataş, Mehmet, Göktürk, Nurcan, Selçuk, Engin Burak, Çevirgen, Furkan, Türköz, Yusuf, Yıldız, Azibe, Arslan, Ahmet Kadir, and Özbağ, Davut
- Subjects
DUODENUM surgery ,C-reactive protein ,ANIMAL experimentation ,IMMUNOHISTOCHEMISTRY ,PLASTIC surgery ,ANTIOXIDANTS ,RATS ,COMPARATIVE studies ,TREATMENT effectiveness ,NEUTROPHILS ,ABDOMINAL surgery ,BLOOD sedimentation ,DESCRIPTIVE statistics ,INTESTINAL perforation ,MEDICAL drainage - Abstract
Copyright of Turkish Journal of Trauma & Emergency Surgery / Ulusal Travma ve Acil Cerrahi Dergisi is the property of KARE Publishing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
6. Assessment of Association Rule Mining Using Interest Measures on the Gene Data
- Author
-
AKBAŞ, Kübra Elif, KIVRAK, Mehmet, ARSLAN, Ahmet Kadir, YAKINBAŞ, Tuğçe, KORKMAZ, Hasan, ÖNALAN, Ebru, and ÇOLAK, Cemil
- Subjects
Data Mining ,Association Rules ,Apriori Algorithm ,Interest Measures ,Gene Expression Data ,Veri madenciliği ,birliktelik kuralları ,apriori algoritması ,ilginçlik ölçütleri ,gen ifadesi verisi ,Medicine ,Tıp - Abstract
Amaç: Veri madenciliği, önceden büyük ölçekli verilerden ortaya çıkarılmayan faydalı bilgilerin keşfedilme sürecidir. Veri madenciliğinin yaygın olarak kullanıldığı alanlardan biri de sağlıktır. Veri madenciliği ile hastalığın tanı ve tedavisi ile hastalığı etkileyen risk faktörleri hızlı bir şekilde belirlenebilmektedir. Birliktelik kuralları, veri madenciliği tekniklerinden biridir. Bu çalışmanın amacı, birliktelik kuralı algoritmalarından biri olan apriori algoritması ile güçlü birliktelik kuralları elde ederek hasta profillerini belirlemektir.Materyal ve Metot: Çalışmada kullanılan veri seti 205 akut miyokard enfarktüsü (AMI) hastasından oluşmaktadır. Hastalar ayrıca FNDC5 polimorfizmlerinin rs3480, rs726344, rs16835198 genotipini de taşımaktadır. Apriori algoritması ile elde edilen kuralları değerlendirmek için destek ve güven ölçüleri kullanılır. Ancak bu ölçütler ile elde edilen kurallar doğrudur ancak güçlü değildir. Bu nedenle, daha güçlü kurallar elde etmek amacıyla iki temel ölçütün yanı sıra ilginçlik ölçütleri kullanılmaktadır. Bu çalışmada daha güçlü kurallara ulaşmak için ilginçlik ölçütlerinden kaldıraç, kanaat, kesinlik faktörü, cosine, korelasyon katsayısı (phi) ve karşılıklı bilgi ölçütleri uygulanmıştır.Bulgular: Çalışmada 108 kural elde edilmiştir. Bu kurallara ilginçlik ölçütlerinin de uygulanması ile elde edilen kural sayısı 29 olmuştur ve bu kurallar güçlü kural olarak nitelendirilmiştir.Sonuç: Sonuç olarak, klinik karar verme sürecinde ilginçlik ölçütlerinin kullanılmasıyla daha güçlü kurallar elde edilmiştir. Elde edilen güçlü kurallar sayesinde AMİ hastalarının hasta profili belirleme ve klinik karar verme sürecini kolaylaştıracaktır., Aim: 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.
- Published
- 2022
7. Impact of COVID-19 pandemic on pediatric appendicitis hospital admission time and length of hospital stay.
- Author
-
Taşçı, Aytaç, Gürünlüoğlu, Kubilay, Yıldız, Turan, Arslan, Ahmet Kadir, Akpınar, Necmettin, Çin, Ecem Serbest, and Demircan, Mehmet
- Subjects
LENGTH of stay in hospitals ,C-reactive protein ,SCIENTIFIC observation ,APPENDICITIS ,PATIENTS ,RETROSPECTIVE studies ,HOSPITAL admission & discharge ,DESCRIPTIVE statistics ,COVID-19 pandemic ,PARENTS ,EDUCATIONAL attainment - Abstract
Copyright of Turkish Journal of Trauma & Emergency Surgery / Ulusal Travma ve Acil Cerrahi Dergisi is the property of KARE Publishing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2022
- Full Text
- View/download PDF
8. A NOVEL INTERPRETABLE WEB-BASED TOOL ON THE ASSOCIATIVE CLASSIFICATION METHODS: AN APPLICATION ON BREAST CANCER DATASET
- Author
-
ARSLAN, Ahmet Kadir, TUNÇ, Zeynep, BALIKÇI ÇİÇEK, İpek, and ÇOLAK, Cemil
- Subjects
Engineering, Electrical and Electronic ,Artificial intelligence,association rules,associative classification,web-based software,breast cancer ,Mühendislik, Elektrik ve Elektronik - Abstract
Aim: The second-largest cause of cancer mortality for women is breast cancer. The main techniques for diagnosing breast cancer are mammography and tumor biopsy accompanied by histopathological studies. The mammograms are not detective of all subtypes of breast tumors, particularly those which arise and are more aggressive in young women or women with dense breast tissue. Circulating prognostic molecules and liquid biopsy approaches to detect breast cancer and the death risk are desperately essential. The purpose of this study is to develop a web-based tool for the use of the associative classification method that can classify breast cancer using the association rules method.Materials and Methods: In this study, an open-access dataset named “Breast Cancer Wisconsin (Diagnostic) Data Set” was used for the classification. To create this web-based application, the Shiny library is used, which allows the design of interactive web-based applications based on the R programming language. Classification based on association rules (CBAR) and regularized class association rules (RCAR) are utilized to classify breast cancer (malignant/benign) based on the generated rules.Results: Based on the classification results of breast cancer, accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score values obtained from the CBAR model are 0.954, 0.951, 0.939, 0.964, 0.939, 0.964, and 0.939 respectively.Conclusion: In the analysis of the open-access dataset, the proposed model has a distinctive feature in classifying breast cancer based on the performance metrics. The associative classification software developed based on CBAR produces successful predictions in the classification of breast cancer. The hypothesis established within the scope of the purpose of this study has been confirmed as the similar estimates are achieved with the results of other papers in the classification of breast cancer.
- Published
- 2020
9. İşgücüne Katılma Durumunu Etkileyen Faktörlerin Kategorik Regresyon İle Çözümlenmesi
- Author
-
SAKLIYAN, Sarp, KIVRAK, Mehmet, GÜLDOĞAN, Emek, ARSLAN, Ahmet Kadir, and ÇOLAK, Cemil
- Subjects
Social ,Sosyal ,İşgücüne Katılma Durumu,Kategorik Regresyon,Hanehalkı Büyüklüğü,İşsizlik Oranı ve Enflasyon - Abstract
İşgücüne katılma durumunu etkileyen bağımsız değişkenler; göç, cinsiyet, yaş, hanehalkı büyüklüğü, maaş, eğitim, çalışma durumu, çalıştığı sektör, enflasyon ve işgücü endeksleri olarak belirlenmiştir. Belirlenen değişkenlerin optimum ölçeklendirme ile bağımlı değişken üzerindeki beklenen varyansı açıklama oranını görerek, değişkenlerin kısmi katkılarını ve istatistiksel anlamlılıklarını incelemek amaçlanmıştır. Analizler, TUİK (Türkiye İstatistik Kurumu) Hanehalkı İşgücü verilerinin 2016 yılına ait son altı aylık verileri üzerinden 2463 hane verisine kategorik regresyon (CATREG) uygulanmıştır. Çözümleme, IBM SPSS Statistics 20 programında yapılmıştır. Veri yapısına uygun ölçeklendirme ile çözümleme yapıldığında, R^2 değeri model anlamlı çıkmasına rağmen yüksek seviyede çıkmamıştır. Optimum ölçeklendirme ile değişkenler tekrardan belli bir kısıt dahilinde ölçeklendirildiğinde, modelin anlamlı ve R^2 değerinin belirgin şekilde arttığı tespit edilmiştir. Bu kapsamda optimal ölçeklemenin bu konuda kuvvetli olduğunu savunabiliriz. Optimum ölçeklendirme ile bağımsız değişkenlerin bağımlı değişkendeki varyansı açıklama oranındaki değişimler görülmüştür. Elde edilen optimum model sonrası R^2 değerinin düşük seviyede kalması ve anlamlı beklenen değişkenlerin anlamsız çıkması ise analize sokulan verilerin tutarlılığının sağlanamamasından kaynaklanmaktadır.Bu makale için 15-06-2021 tarihinde bir düzeltme yayınlandı. https://dergipark.org.tr/tr/pub/ayd/issue/62792/952715
- Published
- 2020
10. DÜZELTME: İŞGÜCÜNE KATILMA DURUMUNU ETKİLEYEN FAKTÖRLERİN KATEGORİK REGRESYON İLE ÇÖZÜMLENMESİ
- Author
-
SAKLIYAN, Sarp, KIVRAK, Mehmet, GÜLDOĞAN, Emek, ARSLAN, Ahmet Kadir, and ÇOLAK, Cemil
- Subjects
Social ,İşgücüne katılma durumu,Kategorik regresyon,Hanehalkı büyüklüğü,İşsizlik oranı ve enflasyon ,Sosyal - Abstract
İşgücüne katılma durumunu etkileyen bağımsız değişkenler; göç, cinsiyet, yaş, hanehalkı büyüklüğü, maaş, eğitim, çalışma durumu, çalıştığı sektör, enflasyon ve işgücü endeksleri olarak belirlenmiştir. Belirlenen değişkenlerin optimum ölçeklendirme ile bağımlı değişken üzerindeki beklenen varyansı açıklama oranını görerek, değişkenlerin kısmi katkılarını ve istatistiksel anlamlılıklarını incelemek amaçlanmıştır. Analizler, TUİK (Türkiye İstatistik Kurumu) Hanehalkı İşgücü verilerinin 2016 yılına ait son altı aylık verileri üzerinden 2463 hane verisine kategorik regresyon (CATREG) uygulanmıştır. Çözümleme, IBM SPSS Statistics 20 programında yapılmıştır. Veri yapısına uygun ölçeklendirme ile çözümleme yapıldığında, 𝑅 2 değeri model anlamlı çıkmasına rağmen yüksek seviyede çıkmamıştır. Optimum ölçeklendirme ile değişkenler tekrardan belli bir kısıt dahilinde ölçeklendirildiğinde, modelin anlamlı ve 𝑅 2 değerinin belirgin şekilde arttığı tespit edilmiştir. Bu kapsamda optimal ölçeklemenin bu konuda kuvvetli olduğunu savunabiliriz. Optimum ölçeklendirme ile bağımsız değişkenlerin bağımlı değişkendeki varyansı açıklama oranındaki değişimler görülmüştür. Elde edilen optimum model sonrası 𝑅 2 değerinin düşük seviyede kalması ve anlamlı beklenen değişkenlerin anlamsız çıkması ise analize sokulan verilerin tutarlılığının sağlanamamasından kaynaklanmaktadır.Bu makalenin ilk hali 17-09-2020 tarihinde yayınlandı. https://dergipark.org.tr/tr/pub/ayd/issue/56831/703233
- Published
- 2020
11. Optimal Endoscopic Management of Anastomotic Strictures After Double-Biliary Reconstruction in Right Lobe Living-Donor Liver Transplantation.
- Author
-
Çağın, Yasir Furkan, Erdoğan, Mehmet Ali, Sağlam, Osman, Yıldırım, Oğuzhan, Bilgiç, Yılmaz, Arslan, Ahmet Kadir, Sarıcı, Kemal Barış, and Yılmaz, Sezai
- Subjects
LENGTH of stay in hospitals ,SURGICAL anastomosis ,CHOLESTASIS ,ENDOSCOPIC retrograde cholangiopancreatography ,OPERATIVE surgery ,TIME ,PLASTIC surgery ,SURGICAL complications ,SURGERY ,PATIENTS ,RETROSPECTIVE studies ,SURGICAL stents ,TREATMENT effectiveness ,COMPARATIVE studies ,TREATMENT failure ,HOSPITAL mortality ,DESCRIPTIVE statistics ,LIVER transplantation ,MEDICAL drainage ,CATHETERIZATION ,BILIARY tract surgery ,ORGAN donors ,LONGITUDINAL method ,TRANSPLANTATION of organs, tissues, etc. ,EVALUATION - Abstract
Background: There is no consensus on the optimal drainage technique in the management of biliary anastomotic strictures occurring after right-lobe living-donor liver transplantation (RL LDLT). Aims: To investigate whether there is a superiority between unilateral and bilateral drainage groups in terms of efficacy and safety of biliary drainage in RL LDLT patients undergoing double-biliary reconstruction. Study Design: Retrospective Cohort Methods: Between January 2009 and August 2019, 1693 patients underwent RL LDLT. Of these, 182 patients who developed biliary anastomotic strictures out of the 306 patients who had double-biliary reconstruction, were included in the study. One hundred fifty-five patients with technical success were divided into 2 groups as unilateral (n=116) and bilateral (n=39) drainage groups. The groups were compared in terms of variable parameters such as clinical success, additional procedure, post-ERCP complication, procedures after clinical failure, hospital stay, mortality, and survival. Results: The clinical success was higher in the bilateral group (70% vs. 82%, P = .201). In the initial and the follow-up periods, a total of 44 (38%) patients in the unilateral group were switched to the bilateral drainage group due to the increased need for stenting. The placement of a stent successfully solved the problem only in 28% (32/117) of the patients in the unilateral group, while this rate was 44% (17/39) in the bilateral group. The median follow-up time of both groups was 42 months, and was equal. The number of stent-free follow-up patients in the unilateral drainage group was less than that in the bilateral drainage group (4 and 7, respectively). Conclusion: An active attempt should be made for bilateral drainage in patients with biliary anastomotic stricture following RL LDLT. However, for patients in whom bilateral drainage is not possible, unilateral drainage may be recommended, with the placement of a maximum number of stents following primary biliary balloon dilatation, depending on the degree of stricture. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
12. Excess Deaths in Malatya in the COVID-19 Pandemic.
- Author
-
Aytemur, Zeynep Ayfer, Yalçınsoy, Murat, Arslan, Ahmet Kadir, and Hacıevliyagil, Süleyman Savaş
- Subjects
MATHEMATICS ,DESCRIPTIVE statistics ,DEATH ,POLYMERASE chain reaction ,COVID-19 pandemic - Abstract
OBJECTIVE: In our study, the effects of the COVID-19 pandemic in Malatya province, other than confirmed case deaths, were investigated. MATERIAL AND METHODS: The records of those who died between 2016 and 2020 were reviewed on the official website of the Malatya Metropolitan Municipality, and the numbers of deaths in those 5 years were recorded on a weekly basis. The arithmetic mean of the deaths between 2016 and 2019 was calculated, and it was investigated whether the number of deaths in 2020 was more than expected. RESULTS: In 2020, 1743 (61%) excess deaths were detected. While the mean number of deaths reported 4 years before 2020 was 2860, it was determined that the number of deaths in 2020 was 4603, and there were 1743 (61%) excess deaths. CONCLUSION: The deaths occurred in Malatya during the COVID-19 pandemic were more than expected. It has been supposed that some deaths were of polymerase chain reaction negative and hence unrecorded COVID-19 patients' deaths, and some deaths were caused by other indirect effects of the pandemic. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
13. Koroner arter hastalarında hipertansiyonun sınıflandırılması için dengesiz sınıf probleminin tıbbi bilgi keşfi süreci ile giderilmesi
- Author
-
Arslan, Ahmet Kadir, Çolak, Cemil, and Biyoistatistik ve Tıbbı Bilişim Anabilim Dalı
- Subjects
Bioistatistics ,Medical informatics ,Sampling methods ,Biyoistatistik ,Hypertension ,Statistics ,Biostatistics ,Statistical techniques ,Morbidity ,Coronary artery disease - Abstract
Amaç: Bu çalışmanın birinci temel amacı, Koroner arter hastalarında mortalite ve morbiditenin artma nedenlerinden biri olan hipertansiyonun, çeşitli risk faktörleri yardımıyla Tıbbi Bilgi Keşfi Süreci uygulanması suretiyle tahmin edilmesi (sınıflandırılması) dir. Çalışmada kullanılan veri setinin bağımlı değişkeni olan hipertansiyonun sınıf dengesizliği probleminin olması nedeniyle, sınıflandırma işlemi yapılmadan önce bu probleminin giderilmesi için çeşitli yaklaşımları kullanan ve ara yüzü Türkçe olan bir web-tabanlı yazılımın geliştirilmesi bu çalışmanın ikinci temel amacıdır.Materyal ve Metot: Çalışmada kullanılan veri seti, 149'u (%16) hipertansiyonu bulunan, 780'i (%84) hipertansiyonu bulunmayan toplam 929 koroner arter hastası kayıtlarından oluşmaktadır. Koroner arter hastalarında hipertansiyonun sınıflandırılması 8 adet bağımsız değişkene dayalı olarak yapılmıştır. Dengesiz sınıf problemini gidermek için çeşitli alt örnekleme, üst örnekleme ve hem alt hem de üst örnekleme yöntemleri kullanılmıştır. Sınıflandırma yöntemleri olarak Çok Katmanlı Algılayıcı, Aşırı Öğrenme Makinesi ve Destek Vektör Makineleri modelleri uygulanmıştır.Bulgular: En iyi sınıflandırma performansının, DBSMOTE sınıf dengeleme yöntemi uygulandıktan sonra Destek Vektör Makinesi modeli ile elde edildiği görülmüştür. İlgili modelin, doğruluk, duyarlılık, seçicilik, kesinlik, f-ölçümü ve g-ortalama değerleri sırasıyla, 0.99, 0.99, 0.99, 0.95, 0.97 ve 0.97 olarak hesaplanmıştır.Sonuç: Çalışmada uygulanan üst örnekleme yöntemlerinin, alt örnekleme yöntemlerine göre modellerin sınıflandırma performanslarına belirgin bir şekilde olumlu katkı yaptığı görülmüştür. Bu çalışma kapsamında yer almayan ancak ilerleyen çalışmalarda ele alınacak olan; hibrit yöntemleri, Maliyet-Duyarlı Öğrenme Tabanlı Yöntemler, Topluluk Öğrenme Tabanlı Yöntemler, Öznitelik Seçimi Tabanlı Yöntemler, daha sağlam ve tutarlı sonuçlar elde edilmesi açısından okuyuculara önerilebilir.Anahtar Kelimeler: Dengesiz sınıf problemi, alt-üst örnekleme yöntemleri, hipertansiyon, tıbbi bilgi keşfi süreci, koroner arter hastalığı. Aim: The primary aim of this study is to estimate (classify) hypertension, one of the causes of mortality and morbidity increase in coronary artery disease patients, by applying Medical Knowledge Discovery Process with various risk factors. Because of the class imbalance problem of hypertension, which is dependent variable of the dataset used in the study, the development of a web-based software which uses various approaches to resolve this problem before the classification process and whose interface is Turkish is the second main aim of this study.Material and Method: The dataset used in the study consisted of records of 929 coronary artery patients with 149 (16%) hypertension and 780 (84%) non-hypertension. Classification of hypertension in coronary artery patients was done based on 8 independent variables. Various over-under sampling and both over and under sampling methods was used to handle the imbalanced class problem. As the classification methods, Multilayer Perceptron, Extreme Learning Machine and Support Vector Machine models were performed.Results: The best classification performance was obtained by the Support Vector Machine model after applying the DBSMOTE class balancing method. The accuracy, sensitivity, specificity, precision, f-measure and g-mean metrics of the relevant model were calculated as 0.99, 0.99, 0.99, 0.95, 0.97 and 0.97, respectively.Conclusion: Compared to the undersampling methods, the oversampling methods used in the study showed a positive contribution to the classification performance of the models. Hybrid Methods, Cost-Sensitive Learning Based Methods, Ensemble Learning Based Methods, Feature Selection Based Methods, which aren't included in the scope of this study but will be discussed in further studies, can be suggested to readers for more robust and consistent results.Key Words: Imbalanced class problem, over and under sampling methods, hypertension, medical knowledge discovery process, coronary artery disease. 72
- Published
- 2018
14. Normal Dağılıma Uygunluğu Değerlendirmek için Açık Kaynak Web Tabanlı Yazılım: Normal Dağılımı İnceleme Yazılımı.
- Author
-
ARSLAN, Ahmet Kadir, TUNÇ, Zeynep, and ÇOLAK, Cemil
- Subjects
- *
FALSE positive error , *GAUSSIAN distribution , *MULTIVARIATE analysis , *CONFORMITY , *TEST interpretation - Abstract
Objective: In this study, it was aimed to develop a new user-friendly web-based software that would easily test single-variable univariate and multivariate normal distribution suitability and enable users to get more accurate results in their studies. Material and Method: Shiny, an open source R package, was used to develop the proposed web software. In the developed software, Shapiro-Wilk and Anderson-Darling tests were used for the uniformity of univariate distribution, and Mardia's skewness-kurtosis, Henze-Zircon and Doornik- Hansen tests were used for multivariate normal distribution. Outputs for conformity to normal distribution were supported by using graphical methods. In practice, for the data set where each variable consisting of two variables derived by simulation has a standard normal distribution and the variables contain 1000 observations, the normal distribution conformity analysis has been performed. Results: In the derived data set, each variable is normally distributed according to the Anderson-Darling and Shapiro-Wilk tests. (for x1 and x2 variables, respectively p =0.91 and p =0.707; p =0.756 and p =0.573). In addition, the derived data set showed two-variable normal distribution according to Mardia's skewness-kurtosis, Henze-Zircon and Doornik-Hansen tests. Conclusion: The developed software is a new user-friendly web-based software that can easily perform univariate and multivariate normal distribution conformity analysis and enable users to get more accurate results in their work. In further studies, Type I and Type II error types are planned to be included in the software in order to determine the best method. [ABSTRACT FROM AUTHOR]
- Published
- 2020
15. Application of Medical Data Mining on the Prediction of APACHE II Score
- Author
-
COLAK, Cemil, AYDOGAN, Mustafa Said, ARSLAN, Ahmet Kadir, and YUCEL, Aytac
- Subjects
APACHE II,Medical Data Mining,Support Vector Machines (SVM) - Abstract
The 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. Keywords: APACHE II, Medical Data Mining, Support Vector Machines (SVM)
- Published
- 2016
16. The risk factors of portal vein thrombosis in patients with liver cirrhosis.
- Author
-
Cagin, Yasir Furkan, Bilgic, Yilmaz, Berber, İlhami, Yildirim, Oguzhan, Erdogan, Mehmet Ali, Firat, Feyza, Arslan, Ahmet Kadir, Colak, Cemil, Seckin, Yuksel, and Harputluoglu, Murat
- Subjects
CIRRHOSIS of the liver ,DISEASE risk factors ,ACTIVATED protein C resistance ,METHYLENETETRAHYDROFOLATE reductase ,INTERNATIONAL normalized ratio - Abstract
This study was designed to identify and assess risk factors for portal vein thrombosis (PVT) in patients with cirrhosis. A total of 98 cirrhosis patients with PVT were identified and 101 cirrhosis patients without PVT were chosen as the control group in this retrospective study. Several variables were measured and the two groups PVT and non-PVT were compared statistically. PVT was identified in 98 patients (10%). Significant differences in hematocrit, international normalized ratio, albumin, bilirubin and glucose were determined between the groups (P<0.05). Out of the thrombophilic risk factors in the patients with PVT factor V Leiden was identified in 8.8%, prothrombin gene 6.6% and methylenetetrahydrofolate reductase 2.2%. There was no difference in survival time between groups (P>0.05). [ABSTRACT FROM AUTHOR]
- Published
- 2019
17. Çeşitli Çekirdek Fonksiyonları ile Oluşturulan Destek Vektör Makinesi Modellerinin Performanslarının İncelenmesi: Bir Klinik Uygulama.
- Author
-
GÜLDOĞAN, Emek, ARSLAN, Ahmet Kadir, and YAĞMUR, Jülide
- Abstract
Objective: The primary aim of this study is to examine and compare the classification performance of support vector machine mo dels generated by various core functions used to classify diabetes mellitus in acute coronary syndrome patients. The secondary aim is to optimize the parameters of the various kernel functions which are used for constructing the support vector machine mo del and to achieve the best classificat ion performance. Material and Method: The data examined in this study were selected retrospectively from the database developed for Inonu University Turgut Ozal Medical Center Cardiology Department. The study included type 2 diabetes mellitus and various demographic and clinical variables in acute coronary syndrome patients. The Support Vector Machine model was used to classify type 2 diabetes mellitus in acute coronary syndrome pat ients. The related models are constructed by ANOVA radial basis funct ion, bessel, linear, Gaussian radial basis funct ion, laplace, polynomial and sigmoid kernel funct ions. Results: The best classification performance was obtained by Support Vector Machine model const ructed by laplace kernel funct ion based on the results of performance metrics. The accuracy, area under ROC curve, sensit ivity and specificity met rics with 95% CI were calc ulated as; 0.9804 (0.9716 - 0.987), 0.9332 (0.9096 - 0.9567), 0.9999 (0.9791 - 1.000) and 0.9776 (0.9675 - 0.9852), respect ively. Conclusion: When the performance metrics were taken into account, the best classification per formance was achieved from the Laplace Support Vector Machine model. In subsequent studies, the use of Support Vector Machine models with different kernel functions and other machine learning or data mining algorithms in different clinical trials may improve the classification success of the diseases. [ABSTRACT FROM AUTHOR]
- Published
- 2017
18. An Interactive Web Application for Kruskal Wallis H Test with R Shiny
- Author
-
ARSLAN, Ahmet Kadir, YAŞAR, Şeyma, ÇOLAK, Cemil, and YOLOĞLU, Saim
- Subjects
Kruskal Wallis H Test,Multiple Comparison Methods,Correction Methods,Web-Based Software ,Kruskal Wallis H Testi,Çoklu Karşılaştırma Yöntemleri,Düzeltme Yöntemleri,Web-Tabanlı Yazılım - Abstract
Kruskal Wallis-H analysis of variance is a nonparametric method used to test the significance of the difference between three or more groups of medians in groups with no normal distribution. Kruskal Wallis H variance analysis, which is a nonparametric counterpart of the one-way analysis of variance, can be used in studies with at least 3 groups of ordinal data. The Kruskal Wallis H test is an extended form of the Mann-Whitney U method from two nonparametric group hypothesis tests. When the difference between the groups is determined after the Kruskal Wallis H variance analysis test, it is necessary to determine where this difference originates. It is very important to decide which of the multiple comparison methods and correction methods used to determine the difference. The purpose of this work is to develop a web-based application that uses the Kruskal Wallis H variance analysis test, which is used in the statistical analysis of studies consisting of three or more groups with nonparametric distribution, using the Shinny package in R software and shows an application of this software on simulation-derived data. The developed interactive web application can be accessed freely at http://biostatapps.inonu.edu.tr/kruskalwallis, Kruskal Wallis-H varyans analizi, normal dağılım göstermeyen gruplarda üç veya daha fazla sayıda grubun ortancaları arasındaki farklılığın anlamlılığını test amacıyla kullanılan parametrik olmayan bir yöntemdir. Sıralı ordinal veriler ile yapılan en az 3 grubun bulunduğu çalışmalarda da tek yönlü varyans analizinin parametrik olmayan karşılığı olan Kruskal Wallis H varyans analizi kullanılabilir. Kruskal Wallis H testi, parametrik olmayan iki grup hipotez testlerinden MannWhitney U yönteminin genişletilmiş biçimidir. Kruskal Wallis H varyans analizi testi sonrası gruplar arası farklılık tespit edildiğinde, bu farklılığın nereden kaynaklandığını belirlenmesi gerekir. Farkı belirlemek için kullanılan çoklu karşılaştırma yöntemleri ve düzeltme yöntemlerinden hangisinin/hangilerinin kullanılacağına karar vermek oldukça önemlidir. Bu çalışmanın amacı, parametrik olmayan dağılıma sahip üç veya daha fazla gruptan oluşan çalışmaların istatistiksel analizlerinde kullanılan Kruskal Wallis H varyans analizi testini, R yazılımındaki Shinny paketini kullanarak gerçekleştiren web-tabanlı bir uygulama geliştirmek ve benzetim simülasyon ile türetilen veriler üzerinde bu yazılımın bir uygulamasını göstermektir. Geliştirilen interaktif web uygulamasına http://biostatapps.inonu.edu.tr/kruskalwallis/ adresinden ücretsiz olarak erişilebilir
19. Comparison of 'primary repair' and 'placing a drain without repair' methods in duodenum perforations.
- Author
-
Karataş T, Kanlioz M, Göktürk N, Çevirgen F, Turkoz Y, Yıldız A, Arslan AK, Selçuk EB, Karataş M, and Özbağ D
- Subjects
- Rats, Animals, Transforming Growth Factor beta1, Duodenum surgery, Drainage, Duodenal Ulcer surgery, Peptic Ulcer Perforation surgery
- Abstract
Background: Duodenal ulcer perforation is a serious condition. A number of methods have been defined and used in surgical treatment. In this study, it was aimed to compare the effectiveness of 'primary repair' and 'drain placement without repair' methods in duodenal perforations using an animal model., Methods: Three equivalent groups of ten rats each were formed. Perforation was created in the duodenum in the first (primary repair/sutured group) and the second group (drain placement without repair/sutureless drainage group). In the first group, the per-foration was repaired with sutures. In the second group, only a drain was placed in the abdomen without sutures. In the third group (control group), only laparotomy was performed. Neutrophil count, sedimentation, serum C-reactive protein (CRP), serum total an-tioxidant capacity (TAC), serum total thiol, serum native thiol, and serum myeloperoxidase (MPO) analyses were performed on animal subjects in the pre-operative period and on the post-operative 1st and 7th days. Histological and immunohistochemical (transforming growth factor-beta 1 [TGF-β1]) analyzes were performed. Blood analysis, histological, and immunohistochemical findings obtained from the groups were compared statistically., Results: There was no significant difference between the first and second groups, except for the TAC on the post-operative 7th day and MPO values on the post-operative 1st day (P>0.05). Although tissue healing was more pronounced in the second group than in the first group, there was no significant difference between the groups (P>0.05). TGF-β1 immunoreactivity observed in the second group was found to be significantly higher than in the first group (P<0.05)., Conclusion: We think that the sutureless drainage method is as effective as the primary repair method in the treatment of duo-denal ulcer perforation and can be safely applied as an alternative to the primary repair method. However, further studies are needed to fully determine the efficacy of the sutureless drainage method.
- Published
- 2023
- Full Text
- View/download PDF
20. Evaluation of risk factors for necrotic tissue resections in elderly patients with groin hernia.
- Author
-
Karatas T, Selcuk EB, Karatas M, Tahtali IN, Yildirim A, and Arslan AK
- Subjects
- Humans, Male, Female, Aged, Middle Aged, Retrospective Studies, Groin surgery, Risk Factors, Necrosis, Hernia, Inguinal surgery, Hernia, Inguinal diagnosis
- Abstract
Aim: To reveal the relationships between patient findings and tissue resection in elderly patients., Materials and Methods: Between September 2020 and September 2022 three hundred eighty four patients over the age of 60 who were operated with the diagnosis of groin hernia were retrospectively analyzed. Gender, age, height, weight and body mass index value, groin and inguinal hernia types, hernia sides, primary or recurrent cases, hernia sac content, incarceration, tissue necrosis and resection presence, and accompanying pathologies were recorded. These findings were compared and evaluated in order to determine the relationships between patient findings and tissue resection, and the findings at risk for tissue resection., Results: Of the patients in the study, 352 (91.7%) were male and 32 (8.3%) were female. The mean age, height, weight and BMI were 67.48±5.893 years, 169.27±6.113 cm, 73.28±7.878 kg and 25,566±2.3518 kg/m2, respectively. There were 369 inguinal, 15 femoral, 285 indirect, 84 direct, 312 primary, and 72 recurrent hernias. Incarceration was present in 65 (16.9%) patients, 19 (4.9%) of these patients underwent resection due to tissue necrosis (twelve omentum and seven small intestine). Tissue resection was 3.1% in male, 25% in female, 4.3% in inguinal, 20% in femoral, 5.6% in indirect, 0% in direct, 3.5% in primary and 11.1% in recurrent hernias. Tissue resections were significantly higher in females, femoral hernias, indirect inguinal hernias and recurrent cases (p<0.05)., Conclusions: We can say that female gender, femoral, indirect and recurrent hernias are important risk factors for tissue resection in elderly patients., Key Words: Elderly Patients, Emergency Surgery, Groin Hernia, Incarceration, Tissue Resection.
- Published
- 2023
21. Impact of COVID-19 pandemic on pediatric appendicitis hospital admission time and length of hospital stay.
- Author
-
Taşçı A, Gürünlüoğlu K, Yıldız T, Arslan AK, Akpınar N, Serbest Çin E, and Demircan M
- Subjects
- Appendectomy adverse effects, Child, Hospitals, Humans, Length of Stay, Pandemics, Retrospective Studies, Appendicitis diagnosis, Appendicitis epidemiology, Appendicitis surgery, COVID-19 epidemiology
- Abstract
Background: Appendicitis is one of the most common surgical emergencies among children. In this retrospective clinical study, we attempted to determine the effects of the COVID-19 pandemic period on hospital admission time and length of hospital stay (LOS) in pediatric appendicitis cases., Methods: We retrospectively compared pediatric appendectomies from the date of the first reported COVID-19 case to June 1, 2020, which is considered as the start of the normalization process, with pre-pandemic pediatric appendectomies of the same number of days in terms of age, gender, hospital admission time, LOS, parental educational level, laboratory values, and histopathological findings., Results: There was an average increase of 2 days in the time from the onset of symptoms to hospital admission in pediatric appen-dicitis patients in the COVID-19 period (p=0.001). Furthermore, C-reactive protein value was statistically significantly higher in the COVID-19 period (p=0.018). Given the LOS, it was calculated as an average of 5 days in the pre-pandemic period and 4 days in the COVID-19 period, and this difference was statistically insignificant (p=0.273). There was no significant difference between the groups in terms of histopathological findings (p=0.176). The parental educational level had no effect on the admission time., Conclusion: The hospital admission time of pediatric appendicitis patients is significantly prolonged in the COVID-19 pandemic, but this prolongation had no histopathological effect. During the pandemic, the recovery of patients who required urgent treatment during the 'stay-at-home' period was also negatively affected. Notwithstanding, we are of the opinion that the absence of an increase in the LOS may be due to the willingness of both families and physicians to keep the LOS as short as possible. Despite the increase in hospital admission time in pediatric appendicitis during the Covid 19 pandemic process, the lack of increase in the rate of complicated appendicitis may be an indicator of the importance of other factors in the development of complicated appendicitis.
- Published
- 2022
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.