Yazar "Guldogan, Emek" seçeneğine göre listele
Listeleniyor 1 - 20 / 21
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe ARM: An Interactive Web Software for Association Rules Mining and an Application in Medicine(Ieee, 2019) Percin, Ibrahim; Yagin, Fatma Hilal; Guldogan, Emek; Yologlu, SaimIn this study, it is aimed to develop a user-friendly, interactive web software for association rules mining. In the developed software, among the association rule methods; Filtered Associatior, Apriori, Frequent Pattern Growth, Predictive Apriori, Generalized Sequential Patterns, HotSpot, Tertius algorithms are used. In addition, association rules algorithms have certain limitation(s) regarding the structure of the data set. Therefore, preprocess menu in the software includes missing value assignment and variable type conversion, methods. In order to evaluate the association rules, support and confidence criteria are present in the software. However, it is not always possible to distinguish interesting and important rules only according to criteria of support and confidence. Therefore, in the proposed software; leverage, lift and conviction criteria are also included. A medical application is performed by using association rules mining, and the experimental results are evaluated based on the outputs of the developed software.Öğe ARTIFICIAL INTELLIGENCE-ASSISTED PREDICTION OF COVID-19 STATUS BASED ON THORAX CT SCANS USING A PROPOSED META-LEARNING STRATEGY(Carbone Editore, 2022) Guldogan, Emek; Yilderim, Ismail Okan; Sevgi, Serkan; Colak, CemilBackground: Radiological techniques integrated with artificial intelligence (AI) are a promising diagnostic tool for the rapidly increasing number of COVID-19 cases today. In this study, we intended to construct an artificial intelligence-assisted prediction of COVID-19 status based on thorax computed tomography (CT) scans using a proposed meta-learning strategy. Methods: A public dataset including 1252 positive and 1230 negative thorax CT scans of SARS-CoV-2 was used in the current study. The CT images for COVID-19 status were analyzed by 26 transfer learning (TL) models. The stacking ensemble learning was used to obtain more consistent and high-performance prediction results by combining the prediction results of 26 TL models with an Results: Mobile had the best prediction with an accuracy of 0.946 (95% CI: 0.93-0.962) among the TL models. The Meta-learning model yielded the best classification accuracy of 0.993 (0.98-1), which outperformed MobileNet, the most successful architecture Conclusions: The proposed meta-model that can distinguish CT images between COVID-19 positive and abnormal/normal conditions due to other etiology of COVID-19 negative may be beneficial in such pandemics. The AI application in this study can be used in mobile, desktop, and web-based platforms to have facilitating and complementary effects on classical reporting and the current workload in radiology departments.Öğe Can melatonin correct the negative effect of experimental diabetes created during the maternal period on fetal rat development and puppies cognitive functions?(2021) Evren, Bahri; Koz, Sema Tulay; Ozkan, Yusuf; Guldogan, EmekAim: Chronic hyperglycemia can cause cognitive impairments such as learning and memory impairment. In our study, we aimed to investigate the levels of glial fibrillary acidic protein (GFAP), neural cell adhesion molecules (NCAM), lipid peroxidation (LPO), and glutathione (GSH) molecules and the protective effect of melatonin in the brain tissue of baby rats with diabetic mothers. Materials and Methods: Wistar-Albino rats used in the experiments were obtained from Firat University Experimental Research Center. Morris Water Maze Test is a learning and memory test commonly used in rats and mice. In the statistical analysis of the data; one-way analysis of variance (One-way ANOVA) was used to evaluate the significance of NCAM, GFAP, LPO, GSH levels between three groups, and repeated measures analysis of variance (Repeated measures one-way ANOVA) was used to evaluate the Morris Water Maze learning test. Results: Learning was worse in rats whose mothers were diabetic compared to diabetes + melatonin and control groups. With the administration of melatonin to diabetic mothers during their pregnancy, an improvement was observed in the learning ability of baby rats. NCAM 180, GFAP, GSH levels were significantly lower (p <0.05, p <0.001, p <0.05), and LPO level was higher (p <0.001) in baby rats with diabetic mothers compared to the control group. NCAM 180 and GFAP levels were significantly higher in the group that was administered melatonin during pregnancy (p <0.05, p <0.01), and LPO levels were lower (p <0.01). With the administration of melatonin during pregnancy, GSH levels were higher than the diabetes group, even though the difference was not statistically significant. Conclusion: Learning and memory functions are impaired in the offspring of diabetic mothers. The decrease in NCAM isoforms can inhibit brain development and the formation of synaptic plasticity. Decreased GFAP density may pose a problem in completing brain maturation in offspring of diabetic mothers. It has been observed that the administration of melatonin to diabetic mothers during their pregnancy is protective against the harmful effects of oxidative stress in their offspring due to its antioxidant effect.Öğe Classification of chronic kidney failure by applying different tree-based methods on a medical data set(2021) Guldogan, Emek; Kucukacali, ZeynepThe purpose of this study is to classify chronic kidney failure (CKF) by applying different tree-based methods on the open-access CKF data set and to compare the performance of the methods used. Classification models will be created using decision trees, J48, Random Forest, and Gradient Boosted Trees from tree-based methods used in the study were applied to an open-access data set named "Chronic Kidney Disease". There are 400 patients in the data set used, 250 (62.5%) of these patients have chronic kidney failure. Different tree-based methods were implemented to classify chronic kidney failure. Among the 4 different tree-based classification models used, the model with the best classification metrics is the Random Forest model, and other models have also yielded successful results. As a result, very successful results were obtained in the study performed with the classification methods used and the chronic renal failure data set. Each model was able to classify the data with high classification performance.Öğe Clinical and radiological outcomes of patients on whom posterior C1-C2 stabilization is applied in C2 odontoid fractures(2021) Pasahan, Ramazan; Guldogan, EmekC2 odontoid fractures constituting 18% of total cervical fractures have a high mortality rate. These fractures may be treated with surgical methods such as external immobilization and odontoid screwing, and anterior or posterior transarticular screwing. Our study presents the clinical and radiological outcomes of patients who received C1-C2 posterior stabilization in C2 odontoid fractures. Twenty patients who underwent posterior C1-2 stabilization at İnönü University neurosurgery clinic between 01.01.2015 and 01.06.2020 were included in this study. These patients were categorized based on their age, sex, fusion ratio, failure to position the fracture line, comorbid diseases, additional trauma, type of accident, duration of hospitalization, the shape of the fracture line, complications and calcification ratios around the dens, and they were followed up for six months. There was a fusion in the fracture line of 19 (95.0%) patients. It is possible to fail to position the fracture in those with irregular fracture lines among patients, and there was a statistically significant difference regarding this issue (p=0.001). There were 3 (15.0%) patients with calcification around the dens. There was a significant relationship between calcification around the dens and age, where the calcification ratio increased as the age increased (p=0.004). The fusion rate is high among patients who receive C1-C2 stabilization. In patients where calcification develops around the dens, the possibility of neck pain to continue despite the stabilization removal should be kept in mind. In the treatment of C2 odontoid fractures,posterior C1-2 stabilization is an effective method.Öğe The comparison of effects of thiopental and ketofol on emergence agitation in patients with nasal surgery: A prospective, single-blind, randomized clinical trial(2020) Guldogan, Emek; Karaaslan, ErolAim: Emergence agitation (EA) is a postanesthetic phenomenon that is common in patients who undergo nasal surgery with general anesthesia, which manifests itself with confusion and violent behaviors and may cause serious problems such as bleeding in the surgical site, unplanned removal of catheter or endotracheal tube. In this study, we aimed to compare the effect of thiopental and ketofol on EA formation after nasal surgery.Material and Methods: This study was performed as a prospective, randomized, single-blind, clinical trial in 80 patients undergoing nasal surgery. The patients were randomly divided into two groups as thiopental (group P:40) and ketofol (group K:40). As the primary outcome; Riker Sedation Agitation Scale (RSAS) was used in order to evaluate EA at the 5th minute after extubation. As the secondary outcome; we aimed to evaluate predisposing factors causing EA.Results: The mean age of the patients was 38.55±13.12 in Group P, while it was 40.68±11.88 in Group K. The incidence of emergence agitation (EA) was significantly higher in Group P than in Group K. There was a statistically significant difference between the two groups (Group P:12 cases (30%), Group K:1 case (2.5%), P:0.001). Residual sedation values in PACU were similar in both groups (P:0.248). The duration of stay in PACU was significantly lower in Group P (P:0.001). Duration of anesthesia, duration of surgery, time to extubation and time to verbal response times were similar in both groups. There was no statistically significant difference between the groups.Conclusion: In patients who underwent nasal surgery under general anesthesia; using ketofol instead of thiopental can significantly reduce EA.Öğe A Computer-Assisted Diagnosis Tool for Classifying COVID-19 based on Chest X-Ray Images(Duzce Univ, Fac Medicine, 2021) Yagin, Fatma Hilal; Guldogan, Emek; Ucuzal, Hasan; Colak, CemilObjective: Since COVID-19 is a worldwide pandemic, COVID-19 detection using a convolutional neural network (CNN) has been an extraordinary research technique. In the reported studies, many models that can predict COVID-19 based on deep learning methods using various medical images have been created; however, clinical decision support systems have been limited. The aim of this study is to develop a successful deep learning model based on X-ray images and a computer-assisted, fast, free and web-based diagnostic tool for accurate detection of COVID-19. Methods: In this study a 15-layer CNN model was used to detect COVID-19 using X-ray images, which outperformed many previously published CNN models in terms of classification. The model performance is evaluated according to Accuracy, Matthews Correlation Coefficient (MCC), F1 Score, Specificity, Sensitivity (Recall), Youden's Index, Precision (Positive Predictive Value: PPV), Negative Predictive Value (NPV), and Confusion Matrix (Classification matrix). In the second phase of the study, the computer-aided diagnostic tool for COVID-19 disease was developed using Python Flask library, JavaScript and Html codes. Results: The model to diagnose COVID-19 has an average accuracy of 98.68 % in the training set and 96.98 % in the testing set. Among the evaluation metrics, the minimum value is 93.4 % for MCC and Youden's index, and the maximum value is 97.8 for sensitivity and NPV. A higher sensitivity value means a lower false negative (FN) value, and a low FN value is an encouraging outcome for COVID-19 cases. This conclusion is crucial because minimizing the overlooked cases of COVID-19 (false negatives) is one of the main goals of this research. Conclusions: In this period when COVID-19 is spreading rapidly around the world, it is thought that the free and web-based COVID-19 X-Ray clinical decision support tool can be a very effective and fast diagnostic tool. The computer-aided system can assist physicians and radiologists in making clinical decisions about the disease, as well as provide support in diagnosis, follow-up, and prognosis. The developed computer-assisted diagnosis tool can be publicly accessed at http://biostatapps.inonu.edu.tr/CSYX/..Öğe Development Of Web-Based Software For Acute Coronary Syndrome And A Medical Data Mining Application(2017) Guldogan, Emek; Yagmur, JulideAim: Medical data mining is based on data mining methods and related intelligent methods (e.g., granular computing, neural networks and soft computing) used in medicine. In this research, it was aimed to develop a web-based software and to implement medical data mining on the records of the patients with acute coronary syndrome. Materials and Methods: The data in this study included retrospective observations recorded in the database from the webbased software developed for Cardiology Department, Turgut Özal Medical Center, Inonu University. PHP (Personal Home Page) programming language and MySQL Database Management System were employed for the development of the web-based software system. Laplace Support Vector Machines (LSVM) was constructed to predict absence or presence of diabetes mellitus in patients with acute coronary syndrome. Results: A web based software performing data entry, query, delete, update, etc. was developed. As a result of medical data mining application, the accuracy and area under ROC curve with 95% CI were obtained as; 0.9804 (0.9716 - 0.987) and 0.9332 (0.9096 - 0.9567), respectively. Conclusion: The developed web-based software created a very important infrastructure for implementing medical data mining applications. It was determined that the LSVM model produced very good predictive results to estimate absence or presence of diabetes mellitus in patients with acute coronary syndrome.Öğe Effect of the COVID-19 pandemic on patients with presumed diagnosis of acute appendicitis(Baishideng Publishing Group Inc, 2022) Akbulut, Sami; Tuncer, Adem; Ogut, Zeki; Sahin, Tevfik Tolga; Koc, Cemalettin; Guldogan, Emek; Karabulut, ErtugrulBACKGROUNDAcute appendicitis (AAp) is the most frequent cause of acute abdominal pain, and appendectomy is the most frequent emergency procedure that is performed worldwide. The coronavirus disease 2019 (COVID-19) pandemic has caused delays in managing diseases requiring emergency approaches such as AAp and trauma.AIMTo compare the demographic, clinical, and histopathological outcomes of patients with AAp who underwent appendectomy during pre-COVID-19 and COVID-19 periods.METHODSThe demographic, clinical, biochemical, and histopathological parameters were evaluated and compared in patients who underwent appendectomy with the presumed diagnosis of AAp in the pre-COVID-19 (October 2018-March 2020) and COVID-19 (March 2020-July 2021) periods.RESULTSAdmissions to our tertiary care hospital for AAp increased 44.8% in the COVID-19 period. Pre-COVID-19 (n = 154) and COVID-19 (n = 223) periods were compared for various parameters, and we found that there were statistically significant differences in terms of variables such as procedures performed on the weekdays or weekends [odds ratio (OR): 1.76; P = 0.018], presence of AAp findings on ultrasonography (OR: 15.4; P < 0.001), confirmation of AAp in the histopathologic analysis (OR: 2.6; P = 0.003), determination of perforation in the appendectomy specimen (OR: 2.2; P = 0.004), the diameter of the appendix (P < 0.001), and hospital stay (P = 0.003). There was no statistically significant difference in terms of interval between the initiation of symptoms and admission to the hospital between the pre-COVID-19 (median: 24 h; interquartile range: 34) and COVID-19 (median: 36 h; interquartile range: 60) periods (P = 0.348). The interval between the initiation of symptoms until the hospital admission was significantly longer in patients with perforated AAp regardless of the COVID-19 or pre-COVID-19 status (P < 0.001).CONCLUSIONThe present study showed that in the COVID-19 period, the ultrasonographic determination rate of AAp, perforation rate of AAp, and duration of hospital stay increased. On the other hand, negative appendectomy rate decreased. There was no statistically significant delay in hospital admissions that would delay the diagnosis of AAp in the COVID-19 period.Öğe Hybrid Explainable Artificial Intelligence Models for Targeted Metabolomics Analysis of Diabetic Retinopathy(Mdpi, 2024) Yagin, Fatma Hilal; Colak, Cemil; Algarni, Abdulmohsen; Gormez, Yasin; Guldogan, Emek; Ardigo, Luca PaoloBackground: Diabetic retinopathy (DR) is a prevalent microvascular complication of diabetes mellitus, and early detection is crucial for effective management. Metabolomics profiling has emerged as a promising approach for identifying potential biomarkers associated with DR progression. This study aimed to develop a hybrid explainable artificial intelligence (XAI) model for targeted metabolomics analysis of patients with DR, utilizing a focused approach to identify specific metabolites exhibiting varying concentrations among individuals without DR (NDR), those with non-proliferative DR (NPDR), and individuals with proliferative DR (PDR) who have type 2 diabetes mellitus (T2DM). Methods: A total of 317 T2DM patients, including 143 NDR, 123 NPDR, and 51 PDR cases, were included in the study. Serum samples underwent targeted metabolomics analysis using liquid chromatography and mass spectrometry. Several machine learning models, including Support Vector Machines (SVC), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and Multilayer Perceptrons (MLP), were implemented as solo models and in a two-stage ensemble hybrid approach. The models were trained and validated using 10-fold cross-validation. SHapley Additive exPlanations (SHAP) were employed to interpret the contributions of each feature to the model predictions. Statistical analyses were conducted using the Shapiro-Wilk test for normality, the Kruskal-Wallis H test for group differences, and the Mann-Whitney U test with Bonferroni correction for post-hoc comparisons. Results: The hybrid SVC + MLP model achieved the highest performance, with an accuracy of 89.58%, a precision of 87.18%, an F1-score of 88.20%, and an F-beta score of 87.55%. SHAP analysis revealed that glucose, glycine, and age were consistently important features across all DR classes, while creatinine and various phosphatidylcholines exhibited higher importance in the PDR class, suggesting their potential as biomarkers for severe DR. Conclusion: The hybrid XAI models, particularly the SVC + MLP ensemble, demonstrated superior performance in predicting DR progression compared to solo models. The application of SHAP facilitates the interpretation of feature importance, providing valuable insights into the metabolic and physiological markers associated with different stages of DR. These findings highlight the potential of hybrid XAI models combined with explainable techniques for early detection, targeted interventions, and personalized treatment strategies in DR management.Öğe An intelligent system for the classification of postoperative pleural effusion between 4 and 30 days using medical knowledge discovery.(Allied Acad, 2017) Guldogan, Emek; Arslan, Ahmet Kadir; Colak, M. Cengiz; Colak, Cemil; Erdil, NevzatObjective: Pleural Effusion (PE) is a considerable and a common health problem. The classification of this condition is of great importance in terms of clinical decision making. The purpose of the study is to design an intelligent system for the classification of postoperative pleural effusion between 4 and 30 days after surgery by medical knowledge discovery (MKD) methods. Materials and methods: This study included 2309 individuals diagnosed with coronary artery disease for elective coronary artery bypass grafting (CABG) operation. The results of chest x-ray were used to diagnose PE. The subjects were allocated to two groups: PE group (n=81) and non-PE group (n=2228), consecutively. In the preprocessing step, outlier analysis, data transformation and feature selection processes were performed. In the data mining step, Naive Bayes, Bayesian network and Random Forest algorithms were utilized. Accuracy and area under receiver operating characteristics (ROC) curve (AUC) were calculated as evaluation metrics. Results: In the preprocessing step, 85 outlier observations were removed from the study. The rest of the data consisted of 2224 subjects: 2149 of these individuals were in non-PE group, and the 75 were in PE group. Random Forest yielded the best classification performance with 97.45% of accuracy and 0.990 of AUC for 0.7 of the optimal split ratio by Grid search algorithm. Conclusion: The achieved results pointed out that the best classification performance was obtained from the RF ensemble model. Therefore, the suggested intelligent system can be used as a clinical decision making tool.Öğe An intelligent system for the classification of postoperative pleural effusion between 4 and 30 daysusing medical knowledge discovery.(Scıentıfıc publıshers ındıa, 87-greater azad enclave, p o quarsı, alıgarh, 00000, ındıa, 2017) Guldogan, Emek; Arslan, Ahmet Kadir; Colak, M. Cengiz; Colak, Cemil; Erdil, NevzatObjective: Pleural Effusion (PE) is a considerable and a common health problem. The classification of this condition is of great importance in terms of clinical decision making. The purpose of the study is to design an intelligent system for the classification of postoperative pleural effusion between 4 and 30 days after surgery by medical knowledge discovery (MKD) methods. Materials and methods: This study included 2309 individuals diagnosed with coronary artery disease for elective coronary artery bypass grafting (CABG) operation. The results of chest x-ray were used to diagnose PE. The subjects were allocated to two groups: PE group (n=81) and non-PE group (n=2228), consecutively. In the preprocessing step, outlier analysis, data transformation and feature selection processes were performed. In the data mining step, Naive Bayes, Bayesian network and Random Forest algorithms were utilized. Accuracy and area under receiver operating characteristics (ROC) curve (AUC) were calculated as evaluation metrics. Results: In the preprocessing step, 85 outlier observations were removed from the study. The rest of the data consisted of 2224 subjects: 2149 of these individuals were in non-PE group, and the 75 were in PE group. Random Forest yielded the best classification performance with 97.45% of accuracy and 0.990 of AUC for 0.7 of the optimal split ratio by Grid search algorithm. Conclusion: The achieved results pointed out that the best classification performance was obtained from the RF ensemble model. Therefore, the suggested intelligent system can be used as a clinical decision making tool.Öğe Multi-parameter-based radiological diagnosis of Chiari Malformation using Machine Learning Technology(Wiley-Hindawi, 2021) Tetik, Bora; Dogan, Gulec Mert; Pasahan, Ramazan; Durak, Mehmet Akif; Guldogan, Emek; Sarac, Kaya; Onal, CagatayBackground The known primary radiological diagnosis of Chiari Malformation-I (CM-I) is based on the degree of tonsillar herniation (TH) below the Foramen Magnum (FM). However, recent data also shows the association of such malformation with smaller posterior cranial fossa (PCF) volume and the anatomical issues regarding the Odontoid. This study presents the achieved result regarding some detected potential radiological findings that may aid CM-I diagnosis using several machine learning (ML) algorithms. Materials and Methods Midsagittal T1-weighted MR images were collected in 241 adult patients diagnosed with CM, eleven morphometric measures of the posterior cerebral fossa were performed. Patients whose imaging was performed in the same centre and on the same device were included in the study. By matching age and gender, radiological exams of 100 clinically/radiologically proven symptomatic CM-I cases and 100 healthy controls were assessed. Eleven morphometric measures of the posterior cerebral fossa were examined using 5 designed ML algorithms. Results The mean age of patients was 29.92 +/- 15.03 years. The primary presenting symptoms were headaches (62%). Syringomyelia and retrocurved-odontoid were detected in 34% and 8% of patients, respectively. All of the morphometric measures were significantly different between the groups, except for the distance from the dens axis to the posterior margin of FM. The Radom Forest model is found to have the best 1.0 (14 of 14) ratio of accuracy in regard to 14 different combinations of morphometric features. Conclusion Our study indicates the potential usefulness of ML-guided PCF measurements, other than TH, that may be used to predict and diagnose CM-I accurately. Combining two or three preferable osseous structure-based measurements may increase the accuracy of radiological diagnosis of CM-I.Öğe Non-traumatic non-aneurysmal subarachnoid haemorrhage: Single institutional experience(202) Pasahan, Ramazan; Tetik, Bora; Guldogan, Emek; Durak, M. Akif; Yildirim, İsmail OkanAim: Despite the advanced diagnostic methods we use today, the rate of negative digital subtraction angiography (DSA) is 15% in patients diagnosed with subarachnoidal hemorrhage (SAH), and these types of hemorrhages are named as non-aneurysmal (NASAH). Various factors such as inadequate interpretation of the beginning angiography, vasospasm, thrombosis, intra-cerebral hematoma pressure may cause DSA to be negative. This study aims to determine the causes of bleeding in patients who were suffered from NASAH. Materials and Methods: The study evaluated 664 patients with SAH from 2010 to 2016. DSA was performed on these patients within the first 3 or 6 hours. Sixty-seven patients with DSA negative were included in the study group. The patients were divided into three groups as perimesencephalic subarachnoidal hemorrhage (PMSAH), non-perimesencephalic subarachnoidal hemorrhage (nPMSAH), CT negative subarachnoidal hemorrhage (CT negative SAH). These three groups were evaluated based on age, gender, Glascow coma scale (GCS), World Federation of Neurosurgical Societies (WFNS) grade, Hunt and Hess Classification and Fisher’s scale, hospitalization time duration, complications and computerized tomography (CT), and cervical and cranial MRI was performed on patients without correlation between DSA results if needed. Results: Of the 664 patients diagnosed with SAH, 67 (10.09%) had NASAH. Statistically significant differences were found between CT Negative SAH and PMSAH and CT Negative SAH and nPMSAH in terms of the variables of GCS during hospital admission and total duration of hospitalization. Statistically significant differences were found between CT Negative SAH and PMSAH and nPMSAH in terms of the variables of GCS during hospital discharge. There were statistically significant differences between the types in terms of WFNS Classification, Hunt and Hess Classification and Fisher’s Scala. Conclusion: We believe that this study will contribute to the literature about the necessity of performing additional radiologic imaging during clinical follow-up since belated diagnosis in patients with NASAH may increase mortality.Öğe PREDICTION OF COVID-19 SEVERITY IN SARS-COV-2 RNA-POSITIVE PATIENTS BY DIFFERENT ENSEMBLE LEARNING STRATEGIES(Carbone Editore, 2022) Bag, Harika Gozde Gozukara; Kivrak, Mehmet; Guldogan, Emek; Colak, CemilIntroduction: While the coronavirus only persists marginally for 95% of the infected cases, the remaining 5% are in critical or life-threatening conditions. This study aimed to design an intelligent model that predicts the severity level of the disease by modeling the relationships between the COVID-19 infection severity and the various demographic/clinical features of individuals. Materials and methods: A public dataset of a cross-sectional study including the demographic and symptomatological characteristics of 223 COVID-19 patients was used and randomly partitioned into training (75%) and testing (25%) datasets. During training, the class imbalance problem was solved, and the related factors with the COVID-19 severity were selected using the evolutionary method supported by a genetic algorithm. Neural Network (NN), Support Vector Machine (SVM), QUEST algorithms together with confidence weighted voting, voting, and highest confidence wins strategies (HCWS) were constructed, and the predictive power of models was determined by performance metrics. Results: Based on the performance indicators, among the individual models, the NN model outperformed SVM and QUEST algorithms in the training and testing datasets. However, ensemble approaches gave better predictions as compared to individual models according to all the evaluation metrics. Conclusion: The proposed voting ensemble model outperforms other ensemble and individual machine learning approaches for the severity prediction of COVID-19 disease. The proposed ensemble learning model can be integrated into web or mobile applications to classify the severity of COVID-19 for clinical decision support.Öğe Prediction of death status on the course of treatment in SARS-COV-2 patients with deep learning and machine learning methods(Elsevier Ireland Ltd, 2021) Kivrak, Mehmet; Guldogan, Emek; Colak, CemilBackground and Objective: The new type of Coronavirus (2019-nCov) epidemic spread rapidly, causing more than 250 thousand deaths worldwide. The virus, which first appeared as a sign of pneumonia, was later called the SARS-COV-2 with Severe Acute Respiratory Syndrome by the World Health Organization. The SARS-COV-2 virus is triggered by binding to the Angiotensin-Converting Enzyme 2 (ACE 2) inhibitor, which is vital in cardiovascular diseases and the immune system, especially in conditions such as cerebrovascular, hypertension, and diabetes. This study aims to evaluate the prediction performance of death status based on the demographic/clinical factors (including COVID-19 severity) by data mining methods. Methods: The dataset consists of 1603 SARS-COV-2 patients and 13 variables obtained from an open source web address. The current dataset contains age, gender, chronic disease (hypertension, diabetes, renal, cardiovascular, etc.), some enzymes (ACE, angiotensin II receptor blockers), and COVID-19 severity, which are used to predict death status using deep learning and machine learning approaches (random forest, k-nearest neighbor, extreme gradient boosting [XGBoost]). A grid search algorithm tunes hyperparameters of the models, and predictions are assessed through performance metrics. Steps of knowledge discovery in databases are applied to obtain the relevant information. Results: The accuracy rate of deep learning (97.15%) was more successful than the accuracy rate based on classical machine learning (92.15% for RF and 93.4% for k-NN), but the ensemble classifier XGBoost method gave the highest accuracy (99.7%). While COVID-19 severity and age calculated from XGBoost were the two most important factors associated with death status, the most determining variables for death status estimated from deep learning were COVID-19 severity and hypertension. Conclusions: The proposed model (XGBoost) achieved the best prediction of death status based on the factors as compared to the other algorithms. The results of this study can guide patients with certain variables to take early measures and access preventive health care services before they become infected with the virus. (c) 2021 Elsevier B.V. All rights reserved.Öğe Prediction of Melanoma from Dermoscopic Images Using Deep Learning-Based Artificial Intelligence Techniques(Ieee, 2019) Kaplan, Ali; Guldogan, Emek; Colak, Cemil; Arslan, Ahmet K.Recently, hospitals and health care institutions have increasingly been addressing clinical decision support systems (CDSS), which can offer specific patient assessments or recommendations to physicians and health care professionals. It is very useful to develop CDSS which can help physicians to make meaningful and correct decisions by using existing data or image sets. Also, CDSS increases the diagnostic accuracy of diseases, provides significant facilities in precision medicine applications, increases operating efficiency of hospitals and reduces costs. In this context, the proposed project intends to create a model usingpre-trained networks (i.e. VGG-16,) based on deep learning (DL) that can successfully predict the melanoma using dermoscopic images. The current study provides clinical support to physicians in the medical decision-making process for the diagnosis of melanoma.Öğe Prediction of Postcoronary Artery Bypass Grafting Atrial Fibrillation: POAFRiskScore Tool(Georg Thieme Verlag Kg, 2023) Arslan, Ahmet Kadir; Erdil, Nevzat; Guldogan, Emek; Colak, Cemil; Akca, Baris; Colak, M. CengizBackground Atrial fibrillation (AF), a condition that might occur after a heart bypass procedure, has caused differing estimates of its occurrence and risk. The current study analyses the possible risk factors of post-coronary artery bypass grafting (post-CABG) AF (postoperative AF [POAF]) and presents a software for preoperative POAF risk prediction. Methods This retrospective research was performed on 1,667 patients who underwent CABG surgery using the hospital database. The associations between the variables of the patients and AF risk factors after CABG were examined using multivariable logistic regression (LR) after preprocessing the relevant data. The tool was designed to predict POAF risk using Shiny, an R package, to develop a web-based software. Results The overall proportion of post-CABG AF was 12.2%. According to the results of univariate tests, in terms of age ( p < 0.001), blood urea nitrogen ( p = 0.005), platelet ( p < 0.001), triglyceride ( p = 0.0026), presence of chronic obstructive pulmonary disease (COPD; p = 0.01), and presence of preoperative carotid artery stenosis (PCAS; p < 0.001), there were statistically significant differences between the POAF and non-POAF groups. Multivariable LR analysis disclosed the independent risk factors associated with POAF: PCAS (odds ratio [OR] = 2.360; p = 0.028), COPD (OR = 2.243; p = 0.015), body mass index (OR = 1.090; p = 0.006), age (OR = 1.054, p < 0.001), and platelet (OR = 0.994, p < 0.001). Conclusion The experimental findings from the current research demonstrate that the suggested tool ( POAFRiskScore v.1.0 ) can help clinicians predict POAF risk development in the preoperative period after validated on large sample(s) that can represent the related population(s). Simultaneously, since the updated versions of the proposed tool will be released periodically based on the increases in data dimensions with continuously added new samples and related factors, more robust predictions may be obtained in the subsequent stages of the current study in statistical and clinical terms.Öğe A Proposed Ensemble Model for The Prediction of Coronavirus Anxiety Scale of Migrant Workers(2021) Guldogan, EmekThis study aimed to evaluate the potential negative effects of the scattered migrant worker population on the anxiety level by estimating the coronavirus anxiety scale (CAS) of the COVID-19 anxiety scale with Gradient Boosting Tree (GBT). In this study, a public data set achieved from a questionnaire [developed using the Coronavirus Anxiety Scale (CAS)] was used to conduct on 1350 people over phone calls. GBT model was constructed for predicting the CAS score of migrant workers based on input variables including demographical data. Hyperparameters of the GBT model were tuned using Optimize Parameters (Evolutionary) operator, which seeks the optimum values of the selected parameters by an evolutionary computation approach. Hyperparameters of the GBT model were 50 for the number of trees, 5 for minimal depth, 0.044 for learning rate, and 1.0E-5 for minimum split improvement. A total of 1500 people, 758 (56.1%) male, and 592 (43.9%) female, participated in this study. The experimental findings demonstrated that the GBT yielded a root mean square error of 3.547±0.235, the absolute error of 2.943±0.154, relative error lenient of 31.54%±0.82%, squared error of 12.623±1.691 and correlation of 0.577±0.130. Variable importance values for each input were calculated from the model-based results of the GBT model. The largest importance was achieved for income and the lowest was estimated for Covid-19 Infection. The calculated importances can be evaluated the potential impacts on the CAS score. In future works, different algorithms can be built for detailed predictions about COVID-19-related anxiety levelsÖğe A proposed tree-based explainable artificial intelligence approach for the prediction of angina pectoris(Nature Portfolio, 2023) Guldogan, Emek; Yagin, Fatma Hilal; Pinar, Abdulvahap; Colak, Cemil; Kadry, Seifedine; Kim, JungeunCardiovascular diseases (CVDs) are a serious public health issue that affects and is responsible for numerous fatalities and impairments. Ischemic heart disease (IHD) is one of the most prevalent and deadliest types of CVDs and is responsible for 45% of all CVD-related fatalities. IHD occurs when the blood supply to the heart is reduced due to narrowed or blocked arteries, which causes angina pectoris (AP) chest pain. AP is a common symptom of IHD and can indicate a higher risk of heart attack or sudden cardiac death. Therefore, it is important to diagnose and treat AP promptly and effectively. To forecast AP in women, we constructed a novel artificial intelligence (AI) method employing the tree-based algorithm known as an Explainable Boosting Machine (EBM). EBM is a machine learning (ML) technique that combines the interpretability of linear models with the flexibility and accuracy of gradient boosting. We applied EBM to a dataset of 200 female patients, 100 with AP and 100 without AP, and extracted the most relevant features for AP prediction. We then evaluated the performance of EBM against other AI methods, such as Logistic Regression (LR), Categorical Boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM). We found that EBM was the most accurate and well-balanced technique for forecasting AP, with accuracy (0.925) and Youden's index (0.960). We also looked at the global and local explanations provided by EBM to better understand how each feature affected the prediction and how each patient was classified. Our research showed that EBM is a useful AI method for predicting AP in women and identifying the risk factors related to it. This can help clinicians to provide personalized and evidence-based care for female patients with AP.