Yazar "Cicek, Ipek Balikci" seçeneğine göre listele
Listeleniyor 1 - 20 / 29
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Comparison of Three Different Surgical Treatments in Late Stage Kienböck's Disease(Thieme Medical Publ Inc, 2026) Ozdemir, Ferdi; Ozdes, Huseyin Utku; Karakaplan, Mustafa; Ergen, Emre; Aslanturk, Okan; Cicek, Ipek Balikci; Ertem, KadirObjective Different treatment options exist for the late-stage Kienb & ouml;ck disease (KD). The functional outcomes of patients undergoing scaphocapitate fusion (SCF), tendon ball arthroplasty (TBA), and radius metaphyseal core decompression in stages 3 to 4 KD were investigated. Materials and Methods This is a retrospective study spanning similar to 11 years, conducted at our clinic, involving the operated patient KD. The study included 51 patients with an average follow-up duration of 68 months (range: 16-130 months). Patients who underwent SCF, TBA, and radius metaphyseal core decompression were divided into three groups based on the surgical approach. The range of motion of the wrist joint and grip strength of the operated wrists were assessed alongside the unaffected wrist during follow-up evaluations. Satisfaction levels among patients were measured by comparing groups internally and based on disease stages. Functional outcomes were evaluated using quick disabilities of the arm, shoulder, and hand (Q-DASH) and Mayo wrist scoring scales. Results Of the patients, 28 were female (54.9%) and 23 were male (45.1%). The mean age was 34 years (range: 19-62 years). There were 12 patients (23.53%) in the radial decompression group, 10 patients (19.61%) in the SCF group, and 29 patients (56.86%) in the TBA group. When the wrist joint Range of motion (ROM)s are analyzed, the losses in both stages 3A and 3B disease are significant compared with the intact wrist in all three surgical methods. When the groups were compared, a higher loss of wrist joint ROM was observed in the TBA group, especially in Kienb & ouml;ck stage 3B patients ( p < 0.001). Furthermore, there were no differences between patient scores in stage 3A when assessments were made using Q-DASH and Mayo scores ( p = 0.156 for Q-DASH and p = 0.060 for Mayo). In stage 3B, Mayo's results were similar, while the radial decompression group was reported to be more favorable in terms of Q-DASH scores ( p = 0.035). Conclusion KD is surgically treated with various operations identified. In terms of functional outcomes, all three surgeries are considered satisfactory. However, in young and active patients, even in advanced stages of the disease, metaphyseal core decompression should be attempted as an initial treatment due to its easier approach and the avoidance of direct manipulation of the carpus.Öğe A Comprehensive CNN Model for Age-Related Macular Degeneration Classification Using OCT: Integrating Inception Modules, SE Blocks, and ConvMixer(Mdpi, 2024) Yusufoglu, Elif; Firat, Huseyin; Uzen, Huseyin; Ozcelik, Salih Taha Alperen; Cicek, Ipek Balikci; Sengur, Abdulkadir; Atila, OrhanBackground/Objectives: Age-related macular degeneration (AMD) is a significant cause of vision loss in older adults, often progressing without early noticeable symptoms. Deep learning (DL) models, particularly convolutional neural networks (CNNs), demonstrate potential in accurately diagnosing and classifying AMD using medical imaging technologies like optical coherence to-mography (OCT) scans. This study introduces a novel CNN-based DL method for AMD diagnosis, aiming to enhance computational efficiency and classification accuracy. Methods: The proposed method (PM) combines modified Inception modules, Depthwise Squeeze-and-Excitation Blocks, and ConvMixer architecture. Its effectiveness was evaluated on two datasets: a private dataset with 2316 images and the public Noor dataset. Key performance metrics, including accuracy, precision, recall, and F1 score, were calculated to assess the method's diagnostic performance. Results: On the private dataset, the PM achieved outstanding performance: 97.98% accuracy, 97.95% precision, 97.77% recall, and 97.86% F1 score. When tested on the public Noor dataset, the method reached 100% across all evaluation metrics, outperforming existing DL approaches. Conclusions: These results highlight the promising role of AI-based systems in AMD diagnosis, of-fering advanced feature extraction capabilities that can potentially enable early detection and in-tervention, ultimately improving patient care and outcomes. While the proposed model demon-strates promising performance on the datasets tested, the study is limited by the size and diversity of the datasets. Future work will focus on external clinical validation to address these limita-tions.Öğe An Explainable Approach to Parkinson's Diagnosis Using the Contrastive Explanation Method-CEM(Mdpi, 2025) Cicek, Ipek Balikci; Kucukakcali, Zeynep; Deniz, Birgul; Algul, Fatma EbruBackground/Objectives: Parkinson's disease (PD) is a progressive neurodegenerative disorder that requires early and accurate diagnosis. This study aimed to classify individuals with and without PD using volumetric brain MRI data and to improve model interpretability using explainable artificial intelligence (XAI) techniques. Methods: This retrospective study included 79 participants (39 PD patients, 40 controls) recruited at Inonu University Turgut Ozal Medical Center between 2013 and 2025. A deep neural network (DNN) was developed using a multilayer perceptron architecture with six hidden layers and ReLU activation functions. Seventeen volumetric brain features were used as the input. To ensure robust evaluation and prevent overfitting, a stratified five-fold cross-validation was applied, maintaining class balance in each fold. Model transparency was explored using two complementary XAI techniques: the Contrastive Explanation Method (CEM) and Local Interpretable Model-Agnostic Explanations (LIME). CEM highlights features that support or could alter the current classification, while LIME provides instance-based feature attributions. Results: The DNN model achieved high diagnostic performance with 94.1% accuracy, 98.3% specificity, 90.2% sensitivity, and an AUC of 0.97. The CEM analysis suggested that reduced hippocampal volume was a key contributor to PD classification (-0.156 PP), whereas higher volumes in the brainstem and hippocampus were associated with the control class (+0.035 and +0.150 PP, respectively). The LIME results aligned with these findings, revealing consistent feature importance (mean = 0.1945) and faithfulness (0.0269). Comparative analyses showed different volumetric patterns between groups and confirmed the DNN's superiority over conventional machine learning models such as SVM, logistic regression, KNN, and AdaBoost. Conclusions: This study demonstrates that a deep learning model, enhanced with CEM and LIME, can provide both high diagnostic accuracy and interpretable insights for PD classification, supporting the integration of explainable AI in clinical neuroimaging.Öğe Assessment of COVID-19-Related Genes Through Associative Classification Techniques(Duzce Univ, Fac Medicine, 2022) Cicek, Ipek Balikci; Kaya, Mehmet Onur; Colak, CemilObjective: This study aims to classify COVID-19 by applying the associative classification method on the gene data set consisting of open access COVID-19 negative and positive patients and revealing the disease relationship with these genes by identifying the genes that cause COVID-19. Methods: In the study, an associative classification model was applied to the gene data set of patients with and without open access COVID-19. In this open-access data set used, 15979 genes are belonging to 234 individuals. Out of 234 people, 141 (60.3%) were COVID-19 negative and 93 (39.7%) were COVID-19 positives. In this study, LASSO, one of the feature selection methods, was performed to choose the relevant predictors. The models' performance was evaluated with accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. Results: According to the study findings, the performance metrics from the associative classification model were accuracy of 92.70%, balanced accuracy of 91.80%, the sensitivity of 87.10%, the specificity of 96.50%, the positive predictive value of 94.20%, the negative predictive value of 91.90%, and F1-score of 90.50%. Conclusions: The proposed associative classification model achieved very high performances in classifying COVID-19. The extracted association rules related to the genes can help diagnose and treat the disease.Öğe Assessment of Patient Safety Attitude Levels Among Healthcare Professionals Working in the Operating Room(Erciyes Univ Sch Medicine, 2023) Tamer, Murat; Akbulut, Sami; Cicek, Ipek Balikci; Saritas, Hasan; Akbulut, Mehmet Serdar; Ozer, Ali; Colak, CemilObjective: This study aims to determine the factors affecting the perception levels of operating room (OR) nurses and nurse anesthetists working in the OR regarding patient safety attitudes. Materials and Methods: This study was conducted using face-to-face interviews with 117 healthcare professionals working as OR nurses (n=60) and nurse anesthetists (n=57). The patient safety attitude questionnaire (SAQ), where the reliability analysis was also performed for the SAQ scale. and sociodemographic characteristics were used for this study. Qualitative variables were given as numbers and percentages (%), and the dataset belonging to quantitative variables that met the normal distribution criteria was given as mean (standard deviation), and data of quantitative variables that did not comply with nor-mality were given as median, IQR, and 95% CI of the median.Results: There were significant differences between OR nurses and nurse anesthetists regarding job satisfaction (p=0.015) and total SAQ score (p=0.040). Significant differences were detected between men and women participants regarding smoking (p=0.020) and stress recognition (p=0.040). The reliability analysis of the scale was as follows: total (alpha: 0.791), job satisfaction (alpha: 0.883), teamwork climate (alpha: 0.856), safety climate (alpha: 0.864), perceptions of management (alpha: 0.881), stress recognition (alpha: 0.791), and working conditions (alpha: 0.530).Conclusion: It was shown that the patient safety attitudes of the healthcare professionals participating in this study are above average, although it is still insufficient, where the stress identification score of the female participant was higher, and it was also found that the nurses' job satisfaction and SAQ score were higher.Öğe Beyond Black Boxes: Interpretable AI with Explainable Neural Networks (ENNs) for Acute Myocardial Infarction (AMI) Using Common Hematological Parameters(Mdpi, 2025) Kucukakcali, Zeynep; Cicek, Ipek BalikciBackground and Objectives: This study aims to evaluate the diagnostic potential of routinely available hematological parameters for acute myocardial infarction (AMI) by employing an Explainable Neural Network (ENN) model that combines high predictive accuracy with interpretability. Materials and Methods: A publicly available dataset comprising 981 individuals (477 AMI patients and 504 controls) was analyzed. A broad set of hematological features-including white blood cell subtypes, red cell indices, and platelet-based markers-was used to train an ENN model. Bootstrap resampling was applied to enhance model generalizability. The model's performance was assessed using standard classification metrics such as accuracy, sensitivity, specificity, F1-score, and Matthews Correlation Coefficient (MCC). SHapley Additive exPlanations (SHAP) were employed to provide both global and individualized insights into feature contributions. Results: The study analyzed hematological and biochemical parameters of 981 individuals. The explainable neural network (ENN) model demonstrated excellent diagnostic performance, achieving an accuracy of 94.1%, balanced accuracy of 94.2%, F1-score of 93.9%, and MCC of 0.883. The AUC was 0.96, confirming strong discriminative ability. SHAP-based explainability analyses highlighted neutrophils (NEU), white blood cells (WBC), RDW-CV, basophils (BA), and lymphocytes (LY) as the most influential predictors. Individual- and class-level SHAP evaluations revealed that inflammatory and erythrocyte-related parameters played decisive roles in AMI classification, while distributional analyses showed narrower parameter ranges in healthy individuals and greater heterogeneity among patients. Conclusions: The findings suggest that cost-effective, non-invasive blood parameters can be effectively utilized within interpretable AI frameworks to enhance AMI diagnosis. The integration of ENN with SHAP provides a dual benefit of diagnostic power and transparent rationale, facilitating clinician trust and real-world applicability. This scalable, explainable model offers a clinically viable decision-support tool aligned with the principles of precision medicine and ethical AI.Öğe Central serous retinopathy classification with deep learning-based multilevel feature extraction from optical coherence tomography images(Elsevier Sci Ltd, 2025) Uzen, Huseyin; Firat, Huseyin; Ozcelik, Salih Taha Alperen; Yusufoglu, Elif; Cicek, Ipek Balikci; Sengur, AbdulkadirCentral Serous Chorioretinopathy (CSCR) is an ocular disease characterized by fluid accumulation under the retina, which can lead to permanent visual impairment if not diagnosed early. This study presents a deep learning-based Convolutional Neural Network (CNN) model designed to automatically diagnose acute and chronic CSCR from Optical Coherence Tomography (OCT) images through multi-level feature extraction. The proposed CNN architecture consists of consecutive layers like a traditional CNN. However, it also extracts various features by creating feature maps at four different levels (F1, F2, F3, F4) for the final feature map. The model processes information using group-wise convolution and Pointwise Convolution Block (PCB) at each level. In this way, each feature group is further processed to obtain more representative features, enabling more independent learning. After the PCB outputs, the 4 feature maps are vectorized and combined, thus creating the final feature map. Finally, classification prediction scores are obtained by applying a fully connected layer and softmax function to this feature map. The experimental study utilized two datasets obtained from Elazig Ophthalmology Polyclinic. The dataset includes 3860 OCT images from 488 individuals, with images categorized into acute CSCR, chronic CSCR, wet AMD, dry AMD, and healthy controls. Our proposed method achieves an increase in accuracy of 0.77%, attaining 96.40% compared to the highest previous accuracy of 95.73% by ResNet101. Precision is enhanced by 0.95%, reaching 95.16% over ResNet101 ' s 94.21%. The sensitivity (recall) is improved by 0.90%, achieving 95.65% versus ResNet101 ' s 94.75%. Additionally, the F1 score is increased by 0.93%, attaining 95.38% compared to ResNet101 ' s 94.45%. These results illustrate the effectiveness of our method, offering more precise and reliable diagnostic capabilities in OCT image classification. In conclusion, this study demonstrates the potential of artificial intelligence-supported diagnostic tools in the analysis of OCT images and contributes significantly to the development of early diagnosis and treatment strategies.Öğe Classification of Breast Cancer on the Strength of Potential Risk Factors with Boosting Models: A Public Health Informatics Application(Galenos Publ House, 2022) Akbulut, Sami; Cicek, Ipek Balikci; Colak, CemilAim: The diagnosis of breast cancer can be accomplished using an algorithm or an early detection model of breast cancer risk via determining factors. In the present study, gradient boosting machines (GBM), extreme gradient boosting (XGBoost) and light gradient boosting (LightGBM) models were applied and their performances were compared. Methods: The open-access Breast Cancer Wisconsin Dataset, which includes 10 features of breast tumors and results from 569 patients, was used for this study. The GBM, XGBoost, and LightGBM models for classifying breast cancer were established by a repeated stratified K-fold cross validation method. The performance of the model was evaluated with accuracy, recall, precision, and area under the curve (AUC). Results: Accuracy, recall, AUC, and precision values obtained from the GBM, XGBoost, and LightGBM models were as follows: (93.9%, 93.5%, 0.984, 93.8%), (94.6%, 94%, 0.985, 94.6%), and (95.3%, 94.8%, 0.987, 95.5%), respectively. According to these results, the best performance metrics were obtained from the LightGBM model. When the effects of the variables in the dataset on breast cancer were assessed in this study, the five most significant factors for the LightGBM model were the mean of concave points, texture mean, concavity mean, radius mean, and perimeter mean, respectively. Conclusion: According to the findings obtained from the study, the LightGBM model gave more successful predictions for breast cancer classification compared with other models. Unlike similar studies examining the same dataset, this study presented variable significance for breast cancer-related variables. Applying the LightGBM approach in the medical field can help doctors make a quick and precise diagnosis.Öğe Classification of stroke with gradient boosting tree using smote-based oversampling method(2021) Yağın, Fatma Hilal; Cicek, Ipek Balikci; Tunç, ZeynepThe aim of this study is to classify the disease with the gradient increasing tree classification method in an open access dataset containing data from patients with and without stroke disease. In addition, it is aimed to compare the results by balancing the data with the oversampling method Synthetic Minority Over-sampling Technique (SMOTE) which is one of the data balancing methods in the study. In this study, a dataset containing information about patients with and without stroke disease obtained from the address "https://www.kaggle.com/asaumya/healthcare-problem-prediction-stroke-patients" was used. In the study, SMOTE was used as the data balancing method, and the gradient boosting tree method was used in the modeling. The performance of the model was evaluated by Specificity, sensitivity, accuracy, positive predictive value and negative predictive values. Specificity, sensitivity, accuracy, positive predictive value and negative predictive values were obtained as 0.0887, 0.9772, 0.9339, 0.9544 and 0.1679, respectively, according to the modeling result using the gardient boosting tree method using the original version of the dataset. Specificity, sensitivity, accuracy, positive predictive value and negative predictive values were obtained as 0.0887, 0.9772, 0.9339, 0.9544 and 0.1679, respectively, according to the modeling result using the gardient boosting tree method using the SMOTE applied version of the dataset. When the results obtained from the study were examined, the modeling results made with the SMOTE applied dataset were obtained more consistently and realistically. As a result, it is suggested that researchers use dataset balancing methods to acquire more accurate results whenever they come across an unbalanced dataset problem.Öğe Comparison of the efficacy of extracorporeal shock wave therapy and trigger point dry needling in the treatment of Calcaneal Epin- A randomized trial(Sage Publications Inc, 2025) Arpaci, Muhammed Furkan; Dogru, Feyzi; Deniz, Mine Argali; Cicek, Ipek Balikci; Baykara, Rabia Aydogan; Erdem, Cumali; Tas, FerhatBackground: Dry needling (DN) and Extracorporeal shock wave therapy (ESWT) are common in calcaneal epin treatment. Objective The aim of the study was to compare the effects of both treatments on proprioception, balance, pain, and functional status. Methods: 90 patients which consist of 45 patients as DN + self stretching and 45 patients as ESWT + self stretching. Patients in each group were treated 1 session per week for 4 weeks. Assessments of 15 degrees ankle dorsiflexion and plantar flexion proprioception, one leg standing test (OLST), foot function index (FFI), visual analog scale (VAS) (first step, resting, activity), quality of life scale (SF-36) were performed. The outcomes were recorded at pre-treatment, post-treatment, and 4 weeks after the post-treatment. Results: Statistically significant differences were determined in VAS (resting, first step, activity) and FFI values in both treatment methods (p < 0.05). In OLST, SF-36, and FFI evaluations, DN was statistically more effective than the ESWT method (p < 0.001). In the 15 degrees proprioception evaluations, a significant difference was observed in the patient's ankle in both methods, while the DN method is more effective in the indicated stages of evaluation. Conclusions: Both methods applied to epin calcanei patients were effective, but the DN method is a more effective treatment method than the ESWT method in terms of balance, proprioception, foot function, and quality of life.Öğe Evaluation of Post-traumatic Stress, Depression, and Anxiety Levels in Survivors of the 2023 Kahramanmaraş Türkiye Earthquakes at the 12th Month After the Event(Cambridge Univ Press, 2025) Cansel, Neslihan; Sandikli, Hatice; Melez, Sahide Nur Ipek; Sandikli, Mustafa; Cicek, Ipek Balikci; Kayhan Tetik, BurcuObjectives On February 6, 2023, 7.7 and 7.6 magnitude earthquakes struck southeastern T & uuml;rkiye, affecting 11 provinces and causing significant losses. This study aims to assess the mental health status of survivors in the twelfth month after the earthquake.Methods A cross-sectional study was conducted using an online survey with the virtual snowball sampling method. The survey included sociodemographic data, previous traumas, earthquake-related experiences, and the Post-Earthquake Trauma Level Determining Scale (PETLDS) and Hospital Anxiety and Depression Scale.Results The study included 2544 participants. The mean PETLDS score was 58.14 +/- 18.18, indicating that the participants were highly traumatized. Among them, 59.5% had high levels of post-traumatic symptoms, 44.2% had high anxiety, and 61% had high depression symptoms. 35.77% of participants displayed a co-occurrence of post-traumatic stress along with anxiety and depression. Female gender was the strongest predictor of high-level trauma and anxiety, while a history of psychiatric disorder was the strongest predictor of depression. Multiple logistic regression analysis indicated that symptoms were predicted by low income, low education level, smoking, comorbid chronic diseases, past traumatic experiences, the loss or injury of a loved one due to the earthquake, personal injury, temporary displacement, and damage to homes and workplaces.Conclusions The findings suggest that one year after the earthquake, mental health problems are prevalent among survivors, highlighting the need for urgent psychiatric interventions.Öğe Evaluation of the relationship between nasal septal deviation and development of facial asymmetry with anthropometric measurements depending on age(Elsevier Ireland Ltd, 2022) Arpaci, Muhammed Furkan; Ozbag, Davut; Aydin, Sukru; Senol, Deniz; Baykara, Rabia Aydogan; Cicek, Ipek BalikciAim: It was aimed to determine the change of facial asymmetry resulting from nasal septal deviation (SD) depending on age, gender, degree of deviation and the affected area besides the effect of SD on somatotype and craniofacial morphology. Materials and methods: 171 volunteers (90 males, 81 females), 27 individuals aged 9-13, 44 individuals aged 14-18, 44 individuals aged 19-23 and 56 individuals in control group participated in the study conducted in otorhinolaryngology polyclinic.11 photometric, 16 anthropometric measurements were taken from the participants. Results: SD affects facial asymmetry formation, although not statistically significant compared to healthy individuals asymmetry rates (p>0.05). It was determined that the degree of SD affected asymmetry only between the ages of 14-18 (in adolescence) and the development of asymmetry in all SD patients was not statistically dependent on age and gender (p>0.05). Photometric measurements demonstrated asymmetries in horizontally-extending parameters of 1/3 middle part of face. There was no statistically significant difference in the cranial anthropometric measurements of the upper and lower 1/3 of the face compared to the control group (p>0.05). The order of the most asymmetrical parameters is Alare-Zygion, Alare-Subnasale, Cheilion-Gonion, Exocanthion-Cheilion, Midsagittal plane-Zygion, Zygion-Cheilion, Zygion-Gonion, Subalare-Cheilion, Glabella-Exocanthion. In all participants were determined that endomorph somatotype was dominant in female and mesomorph somatotype was dominant in male besides SD did not affect somatotype and somatotype did not alter with age. Conclusion: The development of facial asymmetry due to SD is not affected by age and gender furthermore SD does not affect craniofacial asymmetry and somatotype.Öğe Explainable artificial intelligence model for identifying COVID-19 gene biomarkers(Pergamon-Elsevier Science Ltd, 2023) Yagin, Fatma Hilal; Cicek, Ipek Balikci; Alkhateeb, Abedalrhman; Yagin, Burak; Colak, Cemil; Azzeh, Mohammad; Akbulut, SamiAim: COVID-19 has revealed the need for fast and reliable methods to assist clinicians in diagnosing the disease. This article presents a model that applies explainable artificial intelligence (XAI) methods based on machine learning techniques on COVID-19 metagenomic next-generation sequencing (mNGS) samples.Methods: In the data set used in the study, there are 15,979 gene expressions of 234 patients with COVID-19 negative 141 (60.3%) and COVID-19 positive 93 (39.7%). The least absolute shrinkage and selection operator (LASSO) method was applied to select genes associated with COVID-19. Support Vector Machine -Synthetic Minority Oversampling Technique (SVM-SMOTE) method was used to handle the class imbalance problem. Logistics regression (LR), SVM, random forest (RF), and extreme gradient boosting (XGBoost) methods were constructed to predict COVID-19. An explainable approach based on local interpretable model-agnostic expla-nations (LIME) and SHAPley Additive exPlanations (SHAP) methods was applied to determine COVID-19-associated biomarker candidate genes and improve the final model's interpretability.Results: For the diagnosis of COVID-19, the XGBoost (accuracy: 0.930) model outperformed the RF (accuracy: 0.912), SVM (accuracy: 0.877), and LR (accuracy: 0.912) models. As a result of the SHAP, the three most important genes associated with COVID-19 were IFI27, LGR6, and FAM83A. The results of LIME showed that especially the high level of IFI27 gene expression contributed to increasing the probability of positive class.Conclusions: The proposed model (XGBoost) was able to predict COVID-19 successfully. The results show that machine learning combined with LIME and SHAP can explain the biomarker prediction for COVID-19 and provide clinicians with an intuitive understanding and interpretability of the impact of risk factors in the model.Öğe Explainable Machine Learning for the Early Clinical Detection of Ovarian Cancer Using Contrastive Explanations(Mdpi, 2025) Kucukakcali, Zeynep; Cicek, Ipek Balikci; Akbulut, SamiBackground: Ovarian cancer is often diagnosed at advanced stages due to the absence of specific early symptoms, resulting in high mortality rates. This study aims to develop a robust and interpretable machine learning (ML) model for the early detection of ovarian cancer, enhancing its transparency through the use of the Contrastive Explanation Method (CEM), an advanced technique within the field of explainable artificial intelligence (XAI). Methods: An open-access dataset of 349 patients with ovarian cancer or benign ovarian tumors was used. To improve reliability, the dataset was augmented via bootstrap resampling. A three-layer deep neural network was trained on normalized demographic, biochemical, and tumor marker features. Model performance was measured using accuracy, sensitivity, specificity, F1-score, and the Matthews correlation coefficient. CEM was used to explain the model's classification results, showing which factors push the model toward Cancer or No Cancer decisions. Results: The model achieved high diagnostic performance, with an accuracy of 95%, sensitivity of 96.2%, and specificity of 93.5%. CEM analysis identified lymphocyte count (CEM value: 1.36), red blood cell count (1.18), plateletcrit (0.036), and platelet count (0.384) as the strongest positive contributors to the Cancer classification, with lymphocyte count demonstrating the highest positive relevance, underscoring its critical role in cancer detection. In contrast, age (change from -0.13 to +0.23) and HE4 (change from -0.43 to -0.05) emerged as key factors in reversing classifications, requiring substantial hypothetical increases to shift classification toward the No Cancer class. Among benign cases, a significant reduction in RBC count emerged as the strongest determinant driving a shift in classification. Overall, CEM effectively explained both the primary features influencing the model's classification results and the magnitude of changes necessary to alter its outputs. Conclusions: Using CEM with ML allowed clear and trustworthy detection of early ovarian cancer. This combined approach shows the promise of XAI in assisting clinicians in making decisions in gynecologic oncology.Öğe Grad-CAM Enhanced Explainable Deep Learning for Multi-Class Lung Cancer Classification Using DE-SAMNet Model(Mdpi, 2026) Kilic, Murat; Biyikli, Merve; Yelman, Abdulkadir; Firat, Huseyin; Uzen, Huseyin; Cicek, Ipek Balikci; Sengur, AbdulkadirBackground/Objectives: Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, making early and accurate diagnosis crucial for improving patient outcomes. Although chest computed tomography (CT) enables detailed assessment of lung abnormalities, manual interpretation is time-consuming, requires expert expertise, and is prone to diagnostic variability. To address these challenges, this study proposes DE-SAMNet, a hybrid deep learning framework for automated multi-class LC classification from CT scans. Methods: The model integrates two pre-trained convolutional neural networks-DenseNet121 and EfficientNetB0-operating in parallel to extract complementary multi-scale features. A Spatial Attention Module (SAM) is applied to each feature stream to emphasize clinically important regions. Final classification is performed through a compact fusion mechanism involving global average pooling, batch normalization, and a fully connected layer. DE-SAMNet was evaluated on two datasets: a public dataset (IQ-OTH/NCCD) with benign, malignant, and normal cases, and a private clinical dataset including benign, malignant, cystic, and healthy cases. Results: On the public dataset, the model achieved a 99.00% F1-score, 98.41% recall, 99.64% precision, and 99.54% accuracy. On the private dataset, it obtained 95.96% accuracy, 95.99% precision, 96.04% F1-score, and 96.21% recall, outperforming existing approaches. To enhance reliability, explainable AI (XAI) techniques such as Grad-CAM were used to visualize the model's decision rationale. The resulting heatmaps effectively highlight lesion-specific regions, offering transparency and supporting clinical interpretability. Conclusions: This explainability strengthens trust in automated predictions and demonstrates the clinical potential of the proposed system. Overall, DE-SAMNet delivers a highly accurate and interpretable solution for early LC detection.Öğe HBsAg relapse after living donor liver transplantation in hepatocelluler carcinoma patients with hepatitis D virus infection may result in hepatocellular carcinoma relapse(Elsevier, 2020) Baskiran, Adil; Sahin, Tevfik Tolga; Ince, Volkan; Karakas, Serdar; Ozdemir, Fatih; Cicek, Ipek Balikci; Yalcin, Kendal[Abstract Not Available]Öğe Interpretable Prediction of Myocardial Infarction Using Explainable Boosting Machines: A Biomarker-Based Machine Learning Approach(Mdpi, 2025) Kucukakcali, Zeynep; Cicek, Ipek Balikci; Akbulut, SamiBackground/Objectives: This study aims to build an interpretable and accurate predictive model for myocardial infarction (MI) using Explainable Boosting Machines (EBM), a state-of-the-art Explainable Artificial Intelligence (XAI) technique. The objective is to identify and rank clinically relevant biomarkers that contribute to MI diagnosis while maintaining transparency to support clinical decision making. Methods: The dataset comprises 1319 patient records collected in 2018 from a cardiology center in the Erbil region of Iraq. Each record includes eight routinely measured clinical and biochemical features, such as troponin, CK-MB, and glucose levels, and a binary outcome variable indicating the presence or absence of MI. After preprocessing (e.g., one-hot encoding, normalization), the EBM model was trained using 80% of the data and tested on the remaining 20%. Model performance was evaluated using standard metrics including AUC, accuracy, sensitivity, specificity, F1 score, and Matthews correlation coefficient. Feature importance was assessed to identify key predictors. Partial dependence analyses provided insights into how each variable affected model predictions. Results: The EBM model demonstrated excellent diagnostic performance, achieving an AUC of 0.980, an accuracy of 96.6%, sensitivity of 96.8%, and specificity of 96.2%. Troponin and CK-MB were identified as the top predictors, confirming their established clinical relevance in MI diagnosis. In contrast, demographic and hemodynamic variables such as age and blood pressure contributed minimally. Partial dependence plots revealed non-linear effects of key biomarkers. Local explanation plots demonstrated the model's ability to make confident, interpretable predictions for both positive and negative cases. Conclusions: The findings highlight the potential of EBM as a clinically useful and ethical AI approach for MI diagnosis. By combining high predictive accuracy with transparency, EBM supports biomarker prioritization and clinical risk stratification, thus aligning with precision medicine and responsible AI principles. Future research should validate the model on multi-center datasets and explore additional features for broader clinical use.Öğe Investigating the Impact of Body Composition Analysis on Quality of Life and Anxiety-Depression in Adult Males with Chronic Obstructive Pulmonary Disease(Mdpi, 2025) Kurtoglu, Ahmet; Eken, Ozgur; Ciftci, Rukiye; Cicek, Ipek Balikci; Durmaz, Dilber; Deniz, Mine Argali; Aldhahi, Monira I.Background/Objectives: Chronic obstructive pulmonary disease (COPD) is a progressive respiratory disorder characterized by systemic manifestations, including altered body composition, reduced quality of life, and psychological distress. Despite its significance, the relationship between body composition parameters and symptoms of fatigue, anxiety, and depression in patients with COPD remains underexplored. This study aimed to examine the association between detailed body composition metrics and quality of life, fatigue, and anxiety and depression symptoms in male patients with COPD compared to healthy controls. Methods: This cross-sectional study included 49 men with COPD and 51 age-matched healthy controls aged 50-80 years. Body composition was assessed using bioelectrical impedance analysis (BIA). Pulmonary function, dyspnea, activities of daily living, and psychological status were evaluated using spirometry, the Medical Research Council Dyspnea Scale, the London Chest Activity of Daily Living Scale (LCADL), and the Hospital Anxiety and Depression Scale (HADS), respectively. Results: Compared to the controls, patients with COPD exhibited significantly lower forced expiratory volume in one second (FEV1: 1.1 vs. 2.16 L; p < 0.001), lower fat mass (15.0 vs. 24.3 kg; p < 0.001), and higher muscle mass (53.8 vs. 42.0 kg; p < 0.001). They also reported significantly greater fatigue (Borg scale: 4 vs. 0; p < 0.001), higher anxiety (8 vs. 5; p = 0.006), and depression scores (11 vs. 5; p < 0.001), along with more pronounced limitations in their daily activities. Conclusions: COPD is associated with profound impairments in body composition, physical function, and mental health. Detailed body composition analysis using BIA provides valuable clinical insights and may aid in tailoring individualized interventions to improve quality of life and psychological outcomes in COPD management.Öğe Modeling Based on Ensemble Learning Methods for Detection of Diagnostic Biomarkers from LncRNA Data in Rats Treated with Cis-Platinum-Induced Hepatotoxicity(Mdpi, 2023) Kucukakcali, Zeynep; Colak, Cemil; Bag, Harika Gozde Gozukara; Cicek, Ipek Balikci; Ozhan, Onural; Yildiz, Azibe; Danis, NefsunBackground: The first aim of this study is to perform bioinformatic analysis of lncRNAs obtained from liver tissue samples from rats treated with cisplatin hepatotoxicity and without pathology. Another aim is to identify possible biomarkers for the diagnosis/early diagnosis of hepatotoxicity by modeling the data obtained from bioinformatics analysis with ensemble learning methods. Methods: In the study, 20 female Sprague-Dawley rats were divided into a control group and a hepatotoxicity group. Liver samples were taken from rats, and transcriptomic and histopathological analyses were performed. The dataset achieved from the transcriptomic analysis was modeled with ensemble learning methods (stacking, bagging, and boosting). Modeling results were evaluated with accuracy (Acc), balanced accuracy (B-Acc), sensitivity (Se), specificity (Sp), positive predictive value (Ppv), negative predictive value (Npv), and F1 score performance metrics. As a result of the modeling, lncRNAs that could be biomarkers were evaluated with variable importance values. Results: According to histopathological and immunohistochemical analyses, a significant increase was observed in the sinusoidal dilatation and Hsp60 immunoreactivity values in the hepatotoxicity group compared to the control group (p < 0.0001). According to the results of the bioinformatics analysis, 589 lncRNAs showed different expressions in the groups. The stacking model had the best classification performance among the applied ensemble learning models. The Acc, B-Acc, Se, Sp, Ppv, Npv, and F1-score values obtained from this model were 90%, 90%, 80%, 100%, 100%, 83.3%, and 88.9%, respectively. lncRNAs with id rna-XR_005492522.1, rna-XR_005492536.1, and rna-XR_005505831.1 with the highest three values according to the variable importance obtained as a result of stacking modeling can be used as predictive biomarker candidates for hepatotoxicity. Conclusions: Among the ensemble algorithms, the stacking technique yielded higher performance results as compared to the bagging and boosting methods on the transcriptomic data. More comprehensive studies can support the possible biomarkers determined due to the research and the decisive results for the diagnosis of drug-induced hepatotoxicity.Öğe Mortality predictors in earthquake victims admitted to intensive care unit in Kahramanmaras, earthquakes(Elsevier Sci Ltd, 2024) Bicakcioglu, Murat; Gok, Abdullah; Cicek, Ipek Balikci; Dogan, Zafer; Ozer, Ayse B.Background: The purpose of this study is to report the data for patients followed-up in our intensive care unit due to the 6th February 2023, earthquake in Kahramanmaras,, T & uuml;rkiye, and to investigate parameters affecting mortality. Methods: The demographic characteristics of patients followed-up in intensive care due to trauma following the earthquake, the treatments administered, developing complications, lengths of stay in the hospital and intensive care, and laboratory data were scanned retrospectively and recorded. These data were then compared between the surviving and non-surviving patients. Results: Twenty-six patients, 13 (50 %) male, were followed-up in our intensive care, 24 (92 %) due to being buried under earthquake debris, and 2 (8 %) due to falling from heights. Increased Sequential Organ Failure Assessment (SOFA) (p = 0.027), higher initial serum potassium (p = 0.043), higher initial serum phosphorus (p = 0.035), higher initial and peak serum magnesium (p = 0.004 and p = 0.001), lower initial and peak bicarbonate (p = 0.021 and p = 0.012) and higher initial and peak serum base deficit values (p = 0.012 and p = 0.009) were associated with mortality. In the subgroup with crush injuries, higher initial and peak serum potassium (p = 0.001 and p = 0.025), higher initial and peak serum magnesium (p = 0.005 and p = 0.004), lower initial and peak bicarbonate (p = 0.019 and p = 0.021) and higher initial and peak serum base deficit values (p = 0.017 and p = 0.025) were associated with mortality. Multiorgan dysfunction failure developed in nine patients, sepsis in seven, dissemine intravascular coagulation in four, and acute respiratory distress syndrome in two. Fasciotomy was performed on 2 (8 %) patients and amputation on 8 (31 %). Extremity injuries were most frequently observed. 10 (38.5 %) of the 12 (46 %) patients developing acute kidney injury required renal replacement therapy. 7 (27 %) patients died during follow-up. In logistic regression analysis, higher SOFA scores, lower initial bicarbonate and BE levels, higher serum initial potassium and magnesium levels were a risk factor for mortality. Higher SOFA scores, lower initial bicarbonate and base deficit and higher initial phosphorus values affected mortality in patients with crush syndrome. Conclusion: Not only increased SOFA, serum potassium, serum phosphorus, and serum magnesium, but also decreased bicarbonate, and base deficit were associated with mortality in earthquake victims with crush syndrome in ICU.
