Papers by MEHMET ALİ KOBAT
International Journal of Imaging Systems and Technology
An accurate diagnosis of pulmonary hypertension (PH) is crucial to ensure that patients receive t... more An accurate diagnosis of pulmonary hypertension (PH) is crucial to ensure that patients receive timely treatment. One of the used imaging models to detect pulmonary hypertension is the X-ray. Therefore, a new automated PH-type classification model has been presented to depict the separation ability of deep learning for PH types. We retrospectively enrolled 6642 images of patients with PH and the control group. A new X-ray image dataset was collected from a multicentre in this work. A transfer learning-based image classification model has been presented in classifying PH types. Our proposed model was applied to the collected dataset, and this dataset contains six categories (five PH and a non-PH). The presented deep feature engineering (computer vision) model attained 86.14% accuracy on this dataset. According to the extracted ROC curve, the average area under the curve rate has been calculated at 0.945. Therefore, we believe that our proposed model can easily separate PH and non-PH ...
Journal of Craniofacial Surgery
In this study, the authors aim to investigate the effect of dual antiplatelet agents on peri-impl... more In this study, the authors aim to investigate the effect of dual antiplatelet agents on peri-implant–guided bone regeneraation by studying a sample of rats with titanium implants in their tibias. The rats were randomly divided into 5 groups: acetylsalicylic acid (ASA) (n=10), treated with 20 mg/kg of ASA; ASA+CLPD (Clopidogrel): (n=10), treated with 20 mg/kg of ASA and 30 mg/kg of clopidogrel; ASA+PRSG (Prasugrel): (n=10), treated with 20 mg/kg of ASA and 15 mg/kg of prasugrel; ASA+TCGR (Ticagrelor): (n=10), treated with 20 mg/kg of ASA and 300 mg/kg of ticagrelor; and a control group (n=10) received no further treatment after implant surgery. Bone defects created half of the implant length circumferencial after implant insertion and defects filled with bone grafts. After 8 weeks experimental period, the rats sacrified and implants with surrounding bone tissues were collected to histologic analysis; bone filling ratios of defects (%) and blood samples collected to biochemical analys...
International Journal of Machine Learning and Cybernetics
Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning ... more Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning (ML) models have been used for automated MI detection on ECG signals. Deep learning models generally yield high classification performance but are computationally intensive. We have developed a novel multilevel hybrid feature extraction-based classification model with low time complexity for MI classification. The study dataset comprising 12-lead ECGs belonging to one healthy and 10 MI classes were downloaded from a public ECG signal databank. The model architecture comprised multilevel hybrid feature extraction, iterative feature selection, classification, and iterative majority voting (IMV). In the hybrid handcrafted feature (HHF) generation phase, both textural and statistical feature extraction functions were used to extract features from ECG beats but only at a low level. A new pooling-based multilevel decomposition model was presented to enable them to create features at a high level. This model used average and maximum pooling to create decomposed signals. Using these pooling functions, an unbalanced tree was obtained. Therefore, this model was named multilevel unbalanced pooling tree transformation (MUPTT). On the feature extraction side, two extractors (functions) were used to generate both statistical and textural features. To generate statistical features, 20 commonly used moments were used. A new, improved symmetric binary pattern function was proposed to generate textural features. Both feature extractors were applied to the original MI signal and the decomposed signals generated by the MUPTT. The most valuable features from among the extracted feature vectors were selected using iterative neighborhood component analysis (INCA). In the classification phase, a one-dimensional nearest neighbor classifier with tenfold cross-validation was used to obtain lead-wise results. The computed lead-wise results derived from all 12 leads of the same beat were input to the IMV algorithm to generate ten voted results. The most representative was chosen using a greedy technique to calculate the overall classification performance of the model. The HHF-MUPTT-based ECG beat classification model attained excellent performance, with the best lead-wise accuracy of 99.85% observed in Lead III and 99.94% classification accuracy using the IMV algorithm. The results confirmed the high MI classification ability of the presented computationally lightweight HHF-MUPTT-based model.
Background: Screening and accurate diagnosis of chronic thromboembolic pulmonary hypertension(CTE... more Background: Screening and accurate diagnosis of chronic thromboembolic pulmonary hypertension(CTEPH) are critical for managing the progression and preventing associated mortality; however, there are no tools for this purpose. We developed and validated an artificial intelligence (AI) algorithm for predicting CTEPH using electrocardiography (ECG). Methods: ECG signals were obtained from 54 regular and 23 CTEPH patients to test the technique. A dataset was created by converting the ECG results to digital. The 12-channel ECG signal received from 77 individuals is 924x1300 in size. The end-point was the diagnosis of CTEPH. By applying the suggested Nigerian motif pattern method to this data set, we obtained a feature matrix of 924x15010. FSCmRMR algorithm determined the most influential 947 characteristics among 15010 features and obtained a matrix of 924x947. We used a decision tree, SVM(Support Vector Machine), and KNN(K-Nearest Neighbour )algorithms to classify the selected most weig...
Medical Engineering & Physics
Computers in Biology and Medicine
Cardiovascular Therapeutics, 2013
The pathophysiology of cardiac syndrome X (CSX) is still unclear, but most patients with CSX have... more The pathophysiology of cardiac syndrome X (CSX) is still unclear, but most patients with CSX have endothelial dysfunction. It has been shown that adropin uniquely effects the regulation of endothelial function. The purpose of the study was to evaluate the role of adropin in CSX. Eighty-six consecutive cardiac syndrome X-diagnosed patients and 86 age-sex matched healthy subjects were enrolled into the study. Serum adropin levels, nitrite/nitrate levels were measured in each subject. The adropin levels were significantly lower in patients with CSX than healthy subjects (1.7 ± 0.8 ng/mL and 3.4 ± 1.8 ng/mL, respectively; P < 0.001). The BMI values of patients with CSX were significantly higher than control subjects (28.1 ± 2.4 kg/m(2) and 26.0 ± 3.7 kg/m(2) , respectively; P < 0.001). Plasma nitrite/nitrate levels were lower in patients with CSX than control subjects (15.9 ± 1.6 μmol/L vs. 25.4 ± 2.8 μmol/L, respectively; P < 0.001), and they have a significantly positive correlation with plasma adropin levels (r = 0.463, P < 0.001). In the multiple linear regression analysis, nitrite/nitrate levels, BMI, and adropin were found to be independent risk factors for CSX. A ROC curve is used to identify the ability of adropin levels to predict the cardiac syndrome X. The area under the ROC curve was 0.854 for adropin levels (P = 0.0001). The sensitivity and specificity values of adropin levels were 90.7 and 70.9%, respectively (cut-off value 2.73). In conclusion, lower serum adropin levels were associated with CSX. Adropin is an independent risk factor for CSX.
Journal of Health Sciences and Medicine, 2022
Aim: In this study, we aim to investigate the effect of dual anti-platelet agents on osseointegra... more Aim: In this study, we aim to investigate the effect of dual anti-platelet agents on osseointegration by studying a sample of rats with titanium implants in their tibias. Material and Method: The titanium implants were placed surgically to the left tibias of a sample group of 50 rats. After implantation, the rats were randomly divided into five groups: acetylsalicylic acid (ASA) (n =10), treated with 20 mg/kg of ASA; ASA+ clopidogrel (CLPD) (n=10), treated with 20 mg/kg of ASA and 30 mg/kg of CLPD; ASA+ prasugrel (PRSG) (n=10), treated with 20 mg/kg of ASA and 15 mg/kg of PRSG; ASA+ ticagrelor (TCGR) (n=10), treated with 20 mg/kg of ASA and 300 mg/kg of TCGR; and a control group (CNT) (n =10) received no further treatment following implant surgery. The experimental period lasted four weeks, during which all medications were administered with oral gavage. Concluding the experimental period, the animals were euthanized, and researchers collected blood serums and the implants, along wi...
Copyright © 2012 Mehmet Balin et al. This is an open access article distributed under the Creativ... more Copyright © 2012 Mehmet Balin et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Background/Objective. It is known that menopause or lack of endogenous estrogen is a risk factor for endothelial dysfunction and CAD. Lectin-like oxidized low-density lipoprotein receptor-1 (LOX-1) is involved inmultiple phases of vascular dysfunction.The purpose of the current study was to determine the association between soluble LOX-1 (sLOX-1) and pregnancy followed by delivery in women of reproductive age. Materials/Methods. Sixty-eight subjects with pregnancy followed by delivery (group 1) and 57 subjects with nongravidity (group 2) were included in this study. Levels of sLOX-1 were measured in serum by EL SA. Results. Plasma levels of sLOX-1 were significantly lower in Group 1 than Group 2 in women of reproductive age (0.52 ± 0.1...
Pulmonary hypertension may be related to many pathologic conditions. Therefore, a multidisciplina... more Pulmonary hypertension may be related to many pathologic conditions. Therefore, a multidisciplinary approach is required to perform the correct diagnosis, with particular reliance on imaging techniques. Echocardiography is the most commonly used and cheapest imaging technique in patients with pulmonary hypertension. A basic echocardiographic approach is essential for screening of the patients with suspected pulmonary hypertension. Right heart assessment should not be done with one parameter. Its screening should examine the right heart using multiple acoustic windows, and there port should perform an assessment based on parameters. The parameters to be represented and stated should contain a evaluate of right ventricular (RV), right atrial (RA), RV systolic function (at least one of the following: fractional area change (FAC), tricuspid annular plane systolic excursion (TAPSE), S’, and myocardial performance (IMP), and pulmonary artery (PA) pressure (sPAP) with guess of RA pressure ...
Journal of contemporary medicine, 2014
In patient with recurrent ischemic cerebrovascular events, left atrial thrombus have showed by tr... more In patient with recurrent ischemic cerebrovascular events, left atrial thrombus have showed by transthoracic echocardiography and then we have planned by transesophageal echocardiography (TEE). In TEE, thrombus. demonstrated as 30x31mm in size, heterogeneous. The patient was worsened during the evaluation and we diagnosed cerebrovascular event. This experience made that during TEE retching and vagal maneuvers may cause stroke.
Pericardial effusion is common disease and difficult to diagnose. Tuberculosis accounts for up to... more Pericardial effusion is common disease and difficult to diagnose. Tuberculosis accounts for up to 4% of acute pericarditis and 7% of cardiac tamponade cases. Quick treatment can be lifesaving but requires accurate diagnosis. We report a case of a 65-year-old man who presented with a 3-week history of fever with chills, non-productive cough and dyspnea. The case was diagnosed by positivity of acid-fast staining, culture and polymerase chain reaction (PCR) of the aspirated pericardial fluid and treated promptly with antituberculosis drugs. The patient showed complete recovery.
Cardiology and Cardiovascular Medicine
Introduction: heart failure with reduced ejection fraction (HFrEF) is a chronic disease defined a... more Introduction: heart failure with reduced ejection fraction (HFrEF) is a chronic disease defined as ejection fraction (EF)<40 together with heart failure symptoms, which is progressive and has a high risk of mortality. Fibromyalgia (FM) is defined as chronic pain syndrome, characterized by widespread musculoskeletal system pain, anxiety, orthostatic hypotension, and sleep disorders, with unknown etiology. This study aimed to determine the relationship between FM with heart failure. Material and Method: The study included 131 patients with HFrEF who described widespread body pain who presented at the Cardiology Polyclinic between January 2019 and December 2019 and 91 patients with widespread body pain and not with heart failure. All the patients were evaluated in respect of FM using the 2016 diagnostic criteria. Results: The HFrEF group comprised 65 (49.61%) males and 66 (50.39%) females with a mean age of 67.68 ± 11.41 years and the control group comprised 43 (47.25%) males and 48 (52.75%) females with a mean age of 64.65 ± 12.62 years. The mean EF was 29.22 ± 4.04% in the HFrEF group and 60.10 ± 3.79% in the group control. A diagnosis of FM was made in 27 (20.61%) of the 131 patients with HFrEF and in 5 (5.49%) of the 91 patients control (p<0.05). When a comparison was made of patients with FM using Nonsteroid anti-inflammatory drugs (NSAIDs) (6/27, 22.22%) and patients without FM using NSAIDs (8/181, 6.10%), it was determined that patients with FM used NSAIDs at a statistically significantly higher rate (p<0.05). A significant correlation was determined between FM and the severity of depression (p<0.05) and the depression score (p<0.05).
Applied Acoustics
Abstract Background Heart valve diseases are commonly seen ailments, and many people suffer from ... more Abstract Background Heart valve diseases are commonly seen ailments, and many people suffer from these diseases. Therefore, early diagnosis and accurate treatment are crucial for these disorders. This research aims to diagnose heart valve diseases automatically by employing a new stable feature generation method. Materials and method This research presents a stable feature generator-based automated heart diseases diagnosis model. This model uses three primary sections. They are stable feature generation using the improved one-dimensional binary pattern (IBP), selecting the most discriminative feature with neighborhood component analysis (NCA), and classification employing the conventional classifiers. IBP uses three kernels, and they are named signum, left signed, and right signed kernels. By applying these kernels, 768 features are generated. NCA aims to choose the most discriminative ones, and 64 features are chosen to employ NCA. The k nearest neighbor (kNN) and support vector machine (SVM) classifier are employed in the classification phase. Open access (public published) Phonocardiogram signal (PCG) sound dataset is used to calculate this model's measurements. This dataset contains 1000 PCGs with five categories. Results The presented IBP and NCA-based heart valve disorders classification model tested using kNN and SVM classifier and attained 99.5% and 98.30% accuracies, respectively. Conclusions Per the results, the presented IBP and NCA-based PCG sound classification is a successful method. Moreover, this model is basic and high accurate. Therefore, it is ready for the development of real-time implementations.
Diagnostics
COVID-19 and heart failure (HF) are common disorders and although they share some similar symptom... more COVID-19 and heart failure (HF) are common disorders and although they share some similar symptoms, they require different treatments. Accurate diagnosis of these disorders is crucial for disease management, including patient isolation to curb infection spread of COVID-19. In this work, we aim to develop a computer-aided diagnostic system that can accurately differentiate these three classes (normal, COVID-19 and HF) using cough sounds. A novel handcrafted model was used to classify COVID-19 vs. healthy (Case 1), HF vs. healthy (Case 2) and COVID-19 vs. HF vs. healthy (Case 3) automatically using deoxyribonucleic acid (DNA) patterns. The model was developed using the cough sounds collected from 241 COVID-19 patients, 244 HF patients, and 247 healthy subjects using a hand phone. To the best our knowledge, this is the first work to automatically classify healthy subjects, HF and COVID-19 patients using cough sounds signals. Our proposed model comprises a graph-based local feature gene...
Soft Computing
Electrocardiogram (ECG) signals have been widely used for disease diagnosis. Besides, the ECG sig... more Electrocardiogram (ECG) signals have been widely used for disease diagnosis. Besides, the ECG signals can be used for human identification. In this work, a Tietze pattern and neighborhood component analysis (NCA)-based human identification method is proposed. Our model uses two feature generation methods to extract both statistical and textural features. The Tietze graph is considered to create a pattern of the presented local graph structure (LGS). Both statistical and textural feature generations are not enough to present a high-accurate model. Therefore, a multileveled structure must be created. Tunable Q-factor wavelet transform (TQWT) is employed as a decomposer. The generated/extracted features in each level are merged, and the merged features are selected using NCA. The k-nearest neighbors (kNN) classifier is deployed on the chosen features in the classification phase to obtain predicted values. The recommended method was tested on two ECG signal corpora called ECGID and MIT-BIH. The model achieved 99.12% and 99.94% accuracies on the used ECGID and MIT-BIH datasets, respectively.
Background: It was investigated whether Galectin-3 is one of the contributing factors to slow cor... more Background: It was investigated whether Galectin-3 is one of the contributing factors to slow coronary flow (SCF). In the cases with SCF angiography shows lagged opacification of epicardial coronary arteries. Research has reported that several determinants of SCF are inflammation and endothelial dysfunction. It is a new finding that Galactin-3 also causes intravascular inflammation followed by lipid endocytosis, macrophage activation, cellular proliferation, monocyte chemotaxis, and cell adhesion, successively. Thus, the cases enrolled in this study were selected based on their angiographical negative results with obstructive coronary artery disease. Method: The study group consists of 94 patients with SCF, and the control group of 92 with normal coronary flow (NCF). The total (n=186) were the cases who were examined for diagnosis of coronary artery disease based on coronary angiography records and atherosclerotic lesion was not detected. SCF rates were identified using TIMI frame c...
Eurasian Journal of Medical Investigation
A trial fibrillation (AF) is the most common heart rhythm disorder, affecting 3-6 million in the ... more A trial fibrillation (AF) is the most common heart rhythm disorder, affecting 3-6 million in the US, including 5% people over age 60. [1, 2] Thereby the aging of the US population, the number of people diagnosed with AF is anticipated to more than double by the year 2050. [1, 3] AF is related to a higher risk of all-cause mortality, stroke, cardiovascular mortality, cardiac events, and heart failure. [4] The enhanced prevalence of AF has significant personal, clinical, and socioeconomic implications, in part because patients with AF often also have impaired cognitive function. [4, 5] Furthermore, the depressive mood has been shown to be more common among patients with AF and Psychological distress is often present among patients diagnosed with AF. [6, 7] Our study is investigated to the association between AF and depression in the outpatients. Methods This study was performed using personal information of the patient at Fırat University. Beck's depression scale assessed the degree of depression of the people who came to cardiology policlinic in two groups.The groups were separated as with AF or not. 54 patients with atrial fibrillation (AF) and 52 patients without AF enrolled in our study.The people who are taking any antidepressant before excluded for increasing the specificity and sensitivity of our research.Relevant cardiac medications, echocardiography and electrocardiographic properties of the patients recorded in our trial. Depression was classified as minimal depression (0-9 point),mild depression (10-16 point), moderate depression (17-29 point) and severe depression (30-63 point). Statistical analyses were Objectives: Depression is related to poor clinical outcomes in patients with cardiovascular diseases like heart failure. However, we have no data demonstrating the association between depression and atrial fibrillation (AF). Methods: A total of 54 patients with AF and 52 patients without AF were enrolled in our study. Depression scores were assessed in 2 groups. Demographic and clinical information were recorded. Results: The mean age of the 2 groups was 61.94±9.49 years and 60.29±8.25 years, and 28% and 27% were female in the respective groups. In patients with AF, the depression score was higher than in the other group (19.7±1 vs. 10.1±2.3; p<0.001). The depression score was univariate and multiple linear regression analysis showed predictors for atrial fibrillation (0.999 [0.998-1.000]; p=0.002; 0.999 [0.998-1.000] p=0.007). The depression scale for predicting AF was determined to be 16.48, with 73% sensitivity and 61% specificity (area under the curve: 0.701; 95% confidence interval: 0.582-0.819). Conclusion: The depression score was higher in patients with AF, and it appears that there is an association between depression and AF. Depression may be a risk factor for AF.
International Journal of the Cardiovascular Academy
Objective: Specific biomarkers are essential in the diagnosis of heart failure. Our trial aim is ... more Objective: Specific biomarkers are essential in the diagnosis of heart failure. Our trial aim is determined that relationship between toll-like receptor-5 (TLR-5) and N-terminal pro-B-type natriuretic peptide (NT-ProBNP) in patients with reduced ejection fraction. Methods: Two groups were formed in our study (normal and patient group). Among the two groups were investigated that relationship between TLR-5 and NT-ProBNP. Results: The plasma levels of both NT-ProBNP and TLR-5 are significantly higher in patients with congestive heart failure than healthy individuals. However, there is no definite correlation between plasma levels of NT-ProBNP and TLR-5 in patients with congestive heart failure. The high-level plasma TLR-5 is of prognostic value independent from the plasma NT-ProBNP levels, in these patients. Conclusion: As a conclusion, according to recent studies, the high plasma levels of NT-ProBNP and TLR-5 are mainly associated with high mortality and longer hospitalization rate in individuals with heart failure. Therefore, the higher is plasma levels of markers such as TLR-5 and NT-ProBNP, the worse is the overall prognosis in these patients. NT- ProBNP and TLR-5 are thought to be the cheapest and the most appropriate marker to be determined.
Uploads
Papers by MEHMET ALİ KOBAT