DSpace Arşivi :: by Yazar "Kucukakcali, Zeynep" değerine göre listeleniyor

Yazar "Kucukakcali, Zeynep" seçeneğine göre listele

Listeleniyor 1 - 20 / 40

A Nationwide Assessment of Turkish Society's Knowledge and Attitudes Toward Xenotransplantation
(Wiley, 2025) Akbulut, Sami; Kucukakcali, Zeynep; Ozer, Ali; Colak, Cemil
Background: This study aimed to assess public perceptions, awareness, and attitudes toward xenotransplantation (XTx) and organ donation in Turkey by examining the influence of demographic, socioeconomic, and religious factors to identify barriers and facilitators to organ donation and XTx acceptance Methods: This cross-sectional survey was conducted with 10 650 participants, selected through stratified sampling to ensure national representation. Data collection was performed via Computer-Assisted Personal Interviewing (CAPI), with structured questionnaires designed to evaluate participants' perspectives on organ donation, XTx, and religious influences, and comparisons were made based on age groups, geographical region, sectarian affiliation, education level, belief categories, and economic status. ResultsOrgan donation rates were low across all demographic groups, with notable differences by geographical region, education level, income, age, and religious beliefs. The highest organ donation rate was in Central Anatolia (0.9%), while Southeastern Anatolia had the lowest (0.0%) (p = 0.014). Higher education (p = 0.001) and income levels (p = 0.01) correlated with greater organ donation support. Younger individuals (18-24 years) were less religiously observant, while older participants (65+) displayed the highest religious adherence (p = 0.022). Acceptance of XTx from halal animals was highest in the Aegean region (43.0%) (p = 0.001) and among participants with lower religious adherence (27.4%) (p = 0.004). Approval for XTx from non-halal animals was significantly lower, particularly among highly religious individuals (23.9%). Awareness of XTx-related studies was lowest among participants aged 65+ (9.4%) (p < 0.001) and highest among Maliki participants (27.3%). Conclusion: This study highlights the influence of demographic, socioeconomic, and religious factors on public attitudes toward organ donation and XTx in Turkey. These findings offer critical insights for policymakers and healthcare professionals to design culturally adaptive strategies that improve organ donation rates and foster XTx acceptance.
An Explainable Approach to Parkinson's Diagnosis Using the Contrastive Explanation Method-CEM
(Mdpi, 2025) Cicek, Ipek Balikci; Kucukakcali, Zeynep; Deniz, Birgul; Algul, Fatma Ebru
Background/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.
Are Ki-67 and Procalcitonin Expression Levels Useful in Predicting the Biological Behavior of Hepatocellular Carcinoma After Liver Transplantation?
(Mdpi, 2025) Karabulut, Ertugrul; Akbulut, Sami; Samdanci, Emine Turkmen; Akatli, Ayse Nur; Elsarawy, Ahmed; Kucukakcali, Zeynep; Ogut, Zeki
Background: Examinations of procalcitonin (PCT) and Ki-67 expression levels in hepatocellular carcinoma (HCC) patients who have undergone liver transplantation (LT) through immunohistochemical analyses of tumor tissue may reveal the biological characteristics of the tumor, thus informing the selection of HCC patients for LT. Methods: Hepatectomy specimens from 86 HCC patients who underwent LT were obtained and analyzed immunohistochemically for the expression of PCT and Ki-67. The percentage and intensity of PCT staining, as well as the percentage of Ki-67 expression, were assessed for each patient. The impacts of PCT and Ki-67 expression on disease-free survival, overall survival, and the recurrence rate were studied, as well as their correlations with other clinicopathological features. Results: The recurrent HCC group showed a higher Ki-67 level (p < 0.001), larger maximum dominant tumor diameter (p < 0.001), and higher rate of vascular invasion (p = 0.001). The pre-transplant AFP (p = 0.001), maximum dominant tumor diameter (p < 0.001), number of tumor nodules (p < 0.001), rate of vascular invasion (p = 0.001), and Ki-67 level (p = 0.044) were higher in patients beyond the Milan criteria. Similarly, the pre-transplant AFP (p < 0.001); maximum dominant tumor diameter (p < 0.001); number of tumor nodules (p < 0.001); rates of portal vein tumor thrombus (p = 0.002), poor differentiation (p = 0.021), and vascular invasion (p < 0.001); and Ki-67 level (p = 0.010) were higher in patients beyond the expanded Malatya criteria. The maximum dominant tumor diameter (p = 0.006); Ki-67 level (p = 0.003); rates of vascular invasion (p < 0.001), cases beyond the Milan criteria (p = 0.042) and the expanded Malatya criteria (p = 0.027), and portal vein tumor thrombus (p = 0.020); and presence of recurrence (p < 0.001) were higher in HCC patients with mortality. The Kaplan-Meier estimates indicated that Ki-67 levels exceeding 5% significantly affected DFS and OS. Although the Kaplan-Meier estimates indicated that a PCT staining percentage of >= 25% did not have a statistically significant effect on DFS or OS, the outcomes may be considered clinically significant. Conclusions: This study demonstrated that the Ki-67 proliferation index can be used as a predictive biomarker of the biological behavior of HCC. Furthermore, we claim that PCT expression over a particular threshold might impact recurrence and survival, and we believe that further multicenter prospective studies focused on standardized PCT antibody staining are crucial in order to determine its potential as a biomarker for HCC.
Artificial intelligence in acute appendicitis: A comprehensive review of machine learning and deep learning applications
(Baishideng Publishing Group Inc, 2025) Akbulut, Sami; Kucukakcali, Zeynep; Colak, Cemil
Acute appendicitis (AAp) remains one of the most common abdominal emergencies, requiring rapid and accurate diagnosis to prevent complications and unnecessary surgeries. Conventional diagnostic methods, including medical history, clinical assessment, biochemical markers, and imaging techniques, often present limitations in sensitivity and specificity, especially in atypical cases. In recent years, artificial intelligence (AI) has demonstrated remarkable potential in enhancing diagnostic accuracy through machine learning (ML) and deep learning (DL) models. This review evaluates the current applications of AI in both adult and pediatric AAp, focusing on clinical data-based models, radiological imaging analysis, and AI-assisted clinical decision support systems. ML models such as random forest, support vector machines, logistic regression, and extreme gradient boosting have exhibited superior diagnostic performance compared to traditional scoring systems, achieving sensitivity and specificity rates exceeding 90% in multiple studies. Additionally, DL techniques, particularly convolutional neural networks, have been shown to outperform radiologists in interpreting ultrasound and computed tomography images, enhancing diagnostic confidence. This review synthesized findings from 65 studies, demonstrating that AI models integrating multimodal data including clinical, laboratory, and imaging parameters further improved diagnostic precision. Moreover, explainable AI approaches, such as SHapley Additive exPlanations and local interpretable model-agnostic explanations, have facilitated model transparency, fostering clinician trust in AI-driven decision-making. This review highlights the advancements in AI for AAp diagnosis, emphasizing that AI is used not only to establish the diagnosis of AAp but also to differentiate complicated from uncomplicated cases. While preliminary results are promising, further prospective, multicenter studies are required for large-scale clinical implementation, given that a great proportion of current evidence derives from retrospective designs, and existing prospective cohorts exhibit limited sample sizes or protocol variability. Future research should also focus on integrating AI-driven decision support tools into routine emergency care workflows.
Artificial intelligence-based prediction of molecular and genetic markers for hepatitis C-related hepatocellular carcinoma
(Lippincott Williams & Wilkins, 2023) Colak, Cemil; Kucukakcali, Zeynep; Akbulut, Sami
Background:Hepatocellular carcinoma (HCC) is the main cause of mortality from cancer globally. This paper intends to classify public gene expression data of patients with Hepatitis C virus-related HCC (HCV+HCC) and chronic HCV without HCC (HCV alone) through the XGboost approach and to identify key genes that may be responsible for HCC.Methods:The current research is a retrospective case-control study. Public data from 17 patients with HCV+HCC and 35 patients with HCV-alone samples were used in this study. An XGboost model was established for the classification by 10-fold cross-validation. Accuracy (AC), balanced accuracy (BAC), sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were utilized for performance assessment.Results:AC, BAC, sensitivity, specificity, positive predictive value, negative predictive value, and F1 scores from the XGboost model were 98.1, 97.1, 100, 94.1, 97.2, 100, and 98.6%, respectively. According to the variable importance values from the XGboost, the HAO2, TOMM20, GPC3, and PSMB4 genes can be considered potential biomarkers for HCV-related HCC.Conclusion:A machine learning-based prediction method discovered genes that potentially serve as biomarkers for HCV-related HCC. After clinical confirmation of the acquired genes in the following medical study, their therapeutic use can be established. Additionally, more detailed clinical works are needed to substantiate the significant conclusions in the current study.
Assessment of Liver Regeneration in Patients Who Have Undergone Living Donor Hepatectomy for Living Donor Liver Transplantation
(Mdpi, 2023) Satilmis, Basri; Akbulut, Sami; Sahin, Tevfik Tolga; Dalda, Yasin; Tuncer, Adem; Kucukakcali, Zeynep; Ogut, Zeki
Background: Inflammation and the associated immune pathways are among the most important factors in liver regeneration after living donor hepatectomy. Various biomarkers, especially liver function tests, are used to show liver regeneration. The aim of this study was to evaluate the course of liver regeneration following donor hepatectomy (LDH) by routine and regeneration-related biomarkers. Method: Data from 63 living liver donors (LLDs) who underwent LDH in Inonu University Liver Transplant Institute were prospectively analyzed. Serum samples were obtained on the preoperative day and postoperative days (POD) 1, 3, 5, 10, and 21. Regenerative markers including alfa-fetoprotein (AFP), des carboxy prothrombin (DCP), ornithine decarboxylase (ODC), retinol-binding protein 4 (RBP4), and angiotensin-converting enzyme isotype II (ACEII) and liver function tests including alanine aminotransferase (ALT), aspartate aminotransferase (AST), gamma-glutamyl transferase (GGT), alkaline phosphatase (ALP) and total bilirubin levels were all analyzed. Results: The median age of the LLDs was 29.7 years and 28 LLDs were female. Eight LLDs developed postoperative complications requiring relaparotomy. The routine laboratory parameters including AST (<0.001), ALT (<0.001), ALP (<0.001), and total bilirubin (<0.001) showed a significant increase over time until postoperative day (POD) 3. For the regeneration-related parameters, except for the RBP4, all parameters including ACEII (p = 0.006), AFP (p = 0.002), DCP (p = 0.007), and ODC (p = 0.002) showed a significant increase in POD3. The regeneration parameters showed a different pattern of change. In right-lobe liver grafts, ACEII (p = 0.002), AFP (p = 0.035), and ODC (p = 0.001) showed a significant increase over time. DCP (p = 0.129) and RBP4 (p = 0.335) showed no significant changes in right-lobe liver grafts. Conclusions: Regenerative markers are increased in a sustained fashion following LDH. This is more prominent following right-lobe grafts which are indicative of progenitor-associated liver regeneration.
Assessment of the relationship between organ donation attitudes and religious beliefs among postgraduate students
(Frontiers Media Sa, 2025) Apak, Umit; Akbulut, Sami; Kucukakcali, Zeynep; Saritas, Hasan
Background: Organ donation is a critical public health issue, and understanding the factors influencing individuals' knowledge, attitudes, and awareness is essential. To address this, we conducted a descriptive and analytical study among postgraduate students, aiming to evaluate the relationship between their knowledge, attitudes, and awareness of organ donation and their religious beliefs. Methods: A survey-based cross-sectional study was conducted among about 500 postgraduate students at Inonu University Health Sciences Institute. A demographic information form, an organ donation knowledge form, and the validated Turkish version of the Organ Donation Attitude Scale (ODAS) were used. Data were collected online via Google Forms, except for 10 students who filled out paper forms due to email issues. Independent variables included age, marital status, education programs, alcohol and cigarette use, and awareness of organ donation, while dependent variables were ODAS total and subdimension scores. Results: A total of 324 postgraduate students completed the survey. Despite 96.5% recognizing the necessity of organ donation, only 16.9% reported having registered as donors. Religious beliefs were important for 92.5% of postgraduate students, influenced major decisions for 62.2%, and 65.8% believed organ donation was compatible with Islam. The ODAS total scores showed no significant differences based on gender (p = 0.073), marital status (p = 0.483), education program (p = 0.051), or the influence of religious beliefs on life decisions (p = 0.135). Doctoral postgraduate students were more aware of the fatwa on organ donation (p = 0.010). Postgraduate students who had not donated an organ were significantly more likely to believe that brain death is reversible (p < 0.001), to disapprove of organ donation from a Muslim to a non-Muslim (p = 0.004), and to consider organ donation incompatible with Islam (p < 0.001). The Cronbach's alpha value of the ODAS scale was 0.841, indicating good internal consistency. Conclusion: Although religious beliefs influenced major life decisions for most postgraduate students, they did not significantly alter attitudes toward organ donation, as measured by ODAS scores. Misconceptions about brain death and religious permissibility persist, highlighting the need for targeted educational programs, especially considering that postgraduate students, as future health professionals, can play a crucial role in promoting organ donation awareness.
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 Balikci
Background 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.
Classification of colorectal cancer based on gene sequencing data with XGBoost model: An application of public health informatics
(Cukurova Univ, Fac Medicine, 2022) Akbulut, Sami; Kucukakcali, Zeynep; Colak, Cemil
Purpose: This study aims to classify open-access colorectal cancer gene data and identify essential genes with the XGBoost method, a machine learning method. Materials and Methods: The open-access colorectal cancer gene dataset was used in the study. The dataset included gene sequencing results of 10 mucosae from healthy controls and the colonic mucosa of 12 patients with colorectal cancer. XGboost, one of the machine learning methods, was used to classify the disease. Accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, and negative predictive value performance metrics were evaluated for model performance. Results: According to the variable selection method, 17 genes were selected, and modeling was performed with these input variables. Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score obtained from modeling results were 95.5%, 95.8%, 91.7%, 1%, 1%, and 90.9%, and 95.7%, respectively. According to the variable impotance acquired from the XGboost technique results, the CYR61, NR4A, FOSB, and NR4A2 genes can be employed as biomarkers for colorectal cancer. Conclusion: As a consequence of this research, genes that may be linked to colorectal cancer and genetic biomarkers for the illness were identified. In the future, the detected genes' reliability can be verified, therapeutic procedures can be established based on these genes, and their usefulness in clinical practice may be documented.
Classification of healthy controls and Covid-19 cases established on transcriptomic analysis using proposed ensemble model
(2021) Kucukakcali, Zeynep; Yasar, Seyma; Çolak, Cemil
COVID-19, which is a highly contagious disease, has different symptoms in humans. Therefore, the scientific and genetic status of the virus should be clarified as soon as possible. This study aims to classify COVID-19 and determine the important genes related to the disease by applying the ensemble learning techniques on the public COVID-19 dataset. The data set consists of 579 genes belonging to 32 individuals. While 10 of these people are not COVID-19, 22 are people with COVID-19. In this study Lasso, one of the feature selection methods was used. The ensemble learning methods (Bagging, Boosting, and Stacking) were applied to the public dataset. The performance of the models used was evaluated with accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. Of the constructed ensemble models, the Stacking technique produced the best classification performance compared to the Bagging and Boosting methods. Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score obtained from the Stacking technique were 99.85%, 99.91%, 99.82%, 99.64%, 99.95%, and 99.89respectively. CD22, CD19, C4BPA, ARHGDIB, AICDA, CCR5, CCL7, CCL26, CCL22 and CCL16 genes calculated from the Stacking method were the most important genes related to COVID-19. The genes determined from the model may be determinants for early diagnosis and treatment of the COVID-19 disease.
Effect of the COVID-19 Pandemic on the Management of Breast Cancer Patients
(Mdpi, 2024) Dalda, Yasin; Akbulut, Sami; Kucukakcali, Zeynep; Ogut, Zeki; Dalda, Ozlem; Alan, Saadet; Isik, Burak
Background: The COVID-19 pandemic has significantly affected breast cancer patients by causing delays in diagnosis and treatment processes. This study aims to investigate the effects of the pandemic on the treatment process and short-term outcomes of breast cancer patients. Methods: This retrospective, cross-sectional, single-center study included 414 patients who underwent surgery for breast cancer at the Inonu University General Surgery Clinic between March 2018 and June 2021. The patients were divided into two groups: pre-pandemic (Pre-COVID-19; n = 240) and pandemic (COVID-19 Era; n = 174) periods. The groups were compared in terms of demographic, clinical, and histopathological variables. Results: During the pandemic period, the use of neoadjuvant therapy (from 21.3% to 34.5%) and preoperative PET-CT imaging (from 80.4% to 90.8%) rates increased, while breast-conserving surgery (from 27.9% to 19.0%) and the presence of comorbid diseases (from 45.0% to 29.9%) decreased significantly. While there was no significant difference between the groups in terms of the time from diagnosis to surgery (25 vs. 28.5 days, p = 0.121), the time to report the pathology result after surgery decreased during the pandemic period (28 vs. 23 days, p < 0.001). There was no significant difference between the groups in terms of immunohistochemical (ER, PR, Ki-67, E-cadherin, and c-erbB2), histopathological (lymphovascular invasion, perineural invasion, comedo necrosis, modified Bloom-Richardson grade, and TNM classification), and clinical (recurrence, metastasis, and axillary lymph node metastasis) features of the tumor. The mortality rate in the Pre-COVID-19 group (7.1%) was significantly higher than in the COVID-19 Era group (2.3%) (p = 0.049). Finally, in terms of the survival analysis, a statistically significant difference was found between the Pre-COVID-19 and COVID-19 Era groups in terms of the mean follow-up duration of the patients (p = 0.044). Conclusions: The study results show that the use of neoadjuvant therapy and radical surgery preference increased in breast cancer treatment during the pandemic period, but there was no significant change in tumor biology and histopathological features. Breast-conserving surgery rates, comorbidity rates, and pathology reporting times were significantly shortened. Long-term follow-up periods of 3 and 5 years are needed to see the impact of the pandemic on breast cancer patients.
Effect of the COVID-19 Pandemic on the Psychological Health of Patients Who Underwent Liver Transplantation Due to Hepatocellular Carcinoma
(Mdpi, 2023) Akbulut, Sami; Kucukakcali, Zeynep; Saritas, Hasan; Bozkir, Cigdem; Tamer, Murat; Akyuz, Musap; Bagci, Nazlican
Background: The primary aim of this study was to compare liver transplant (LT) recipients with and without hepatocellular carcinoma (HCC) in terms of COVID-19-related depression, anxiety, and stress. Method: A total of 504 LT recipients with (HCC group; n = 252) and without HCC (non-HCC group; n = 252) were included in the present case-control study. Depression Anxiety Stress Scales (DASS-21) and Coronavirus Anxiety Scale (CAS) were used to evaluate the depression, stress, and anxiety levels of LT patients. DASS-21 total and CAS-SF scores were determined as the primary outcomes of the study. Poisson regression and negative binomial regression models were used to predict the DASS and CAS scores. The incidence rate ratio (IRR) was used as a coefficient. Both groups were also compared in terms of awareness of the COVID-19 vaccine. Results: Poisson regression and negative binomial regression analyses for DASS-21 total and CAS-SF scales showed that the negative binomial regression method was the appropriate model for both scales. According to this model, it was determined that the following independent variables increased the DASS-21 total score: non-HCC (IRR: 1.26; p = 0.031), female gender (IRR: 1.29; p = 0.036), presence of chronic disease (IRR: 1.65; p < 0.001), exposure to COVID-19 (IRR: 1.63; p < 0.001), and nonvaccination (IRR: 1.50; p = 0.002). On the other hand, it was determined that the following independent variables increased the CAS score: female gender (IRR:1.75; p = 0.014) and exposure to COVID-19 (IRR: 1.51; p = 0.048). Significant differences were found between the HCC and non-HCC groups in terms of median DASS-21 total (p < 0.001) and CAS-SF (p = 0.002) scores. Cronbach's alpha internal consistency coefficients of DASS-21 total and CAS-SF scales were calculated to be 0.823 and 0.783, respectively. Conclusion: This study showed that the variables including patients without HCC, female gender, having a chronic disease, being exposed to COVID-19, and not being vaccinated against COVID-19 increased anxiety, depression, and stress. High internal consistency coefficients obtained from both scales indicate that these results are reliable.
Ensemble learning-based prediction of COVID-19 positive patient groups determined by IL-6 levels and control individuals based on the proteomics data
(2021) Yasar, Seyma; Kucukakcali, Zeynep; Doganer, Adem
Coronavirus disease (COVID-19) is a newly found coronavirus that causes an infectious disease. COVID-19, which has a detrimental impact on many people, has varied effects on different people. Therefore, proteomic analysis is an important approach used to develop early diagnosis and treatment strategies. This research to classify COVID-19 positive patient groups represented by interleukin 6 (IL-6) levels (low, medium, high) and control groups based on proteomic analysis using ensemble learning methods (Adaboost, Bagging, Stacking, and Voting). The public dataset from a website consists of 49 subjects (31 COVID-19 positives and 18 controls) and 493 proteins achieved from blood samples. The dataset was handled to estimate the relation between disease severity and proteins using ensemble learning approaches (Adaboost, Bagging, Stacking, and Voting) using ten-fold cross-validation. Predictions were evaluated with accuracy, sensitivity,etc. performance metrics. The accuracy of Adaboost (96.00%) was higher as compared to Voting (93.88%) and Bagging (91.84%). However, the Stacking ensemble learning method produced the highest accuracy (97.92%). IL6, SERPINA3, SERPING1, SERPINA1, and GSN were the five most important proteins associated with disease severity. In comparison to the other methods, the suggested ensemble learning model (Stacking) produced the best estimation of disease severity based on proteins. The results indicate that changes in blood protein levels correlated with the severity of COVID-19 may be benefited to follow early diagnosis/treatment of the COVID-19 disease.
Evaluating Ensemble-Based Machine Learning Models for Diagnosing Pediatric Acute Appendicitis: Insights from a Retrospective Observational Study
(Mdpi, 2025) Kucukakcali, Zeynep; Akbulut, Sami; Colak, Cemil
Background: Pediatric acute appendicitis (AAP) is a common cause of abdominal pain in children, yet accurate classification into negative, uncomplicated, and complicated forms remains clinically challenging. Misclassification may lead to unnecessary surgeries or delayed treatment. This study aims to evaluate and compare the diagnostic accuracy of five machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) for classifying pediatric AAP subtypes. Methods: In this retrospective observational study, a dataset of 590 pediatric patients was analyzed. Demographic information and laboratory parameters-including C-reactive protein (CRP), white blood cell (WBC) count, neutrophils, lymphocytes, and appendiceal diameter-were included as features. The cohort consisted of negative (19.8%), uncomplicated (49.2%), and complicated (31.0%) AAP cases. Five ensemble machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) were trained on 80% of the dataset and tested on the remaining 20%. Model performance was evaluated using accuracy, sensitivity, specificity, and F1 score, with cross-validation employed to ensure result stability. Results: Random Forest demonstrated the highest overall accuracy (90.7%), sensitivity (100.0%), and specificity (61.5%) for distinguishing negative and uncomplicated AAP cases. Meanwhile, XGBoost outperformed other models in identifying complicated AAP cases, achieving an accuracy of 97.3%, sensitivity of 100.0%, and specificity of 78.3%. The most influential biomarkers were neutrophil count, appendiceal diameter, and WBC levels, highlighting their predictive value in AAP classification. Conclusions: ML models, particularly Random Forest and XGBoost, exhibit strong potential in aiding pediatric AAP diagnosis. Their ability to accurately classify AAP subtypes suggests that ML-based decision support tools can complement clinical judgment, improving diagnostic precision and patient outcomes. Future research should focus on multi-center validation, integrating imaging data, and enhancing model interpretability for broader clinical adoption.
Evaluation of Bone Mineral Metabolism After Liver Transplantation by Bone Mineral Densitometry and Biochemical Markers
(Elsevier Science Inc, 2023) Sarici, Kemal Baris; Akbulut, Sami; Uremis, Muhammed Mehdi; Garzali, Ibrahim Umar; Kucukakcali, Zeynep; Koc, Cemalettin; Turkoz, Yusuf
Aim. This study aimed to evaluate the course of bone and mineral metabolism after liver trans-plantation (LT) in patients with chronic liver disease.Methods. One hundred four patients who had undergone LT and had a minimum of 6 months of follow-up after LT were included in this prospective cohort study. The following parameters were evaluated for each patient: preoperative and postoperative (postoperative day [POD]30, POD90, POD180) osteocalcin, bone-specific alkaline phosphatase (BALP), type 1 collagen, beta-C-terminal end telopeptide (b-CTx), vitamin D, parathyroid hormone (PTH), ALP, calcium, phosphate, sedimentation, and bone mineral densitometer scores (L2, L4, L total, and F total). The parameters were compared in terms of sex, presence of liver tumor (hepatocellular carci-noma [HCC; n = 19] vs non-HCC [n = 85]), and presence of autoimmune liver disease (autoim-mune liver disease [ALD; n = 8] vs non-ALD [n = 96]). Results. The median age of the patients (n = 81 men and n = 23 women) was 52 years (95% CI, 50-56). There was a significant change in the defined time intervals in parameters such as osteocalcin (P < .001), BALP (P < .001), b-CTx (P < .001), vitamin D (P < .001), PTH (P < .001), ALP (P = .001), calcium (P < .001), phosphate (P = .001), L2 (P = .038), L total (P = .026), and F total (P < .001) scores. There was a significant difference in POD90 ALP (P = .033), POD180 calcium (P = .011), POD180 phosphate (P = .011), preoperative sedimentation (P = .032), and POD180 F total (P = .013) scores between both sexes. There was a significant difference in POD180 osteocalcin (P = .023), POD180 b-CTx (P = .017), and preOP calcium (P = .003) among the HCC and non-HCC groups. Furthermore, we found significant differences in preoperative ALP (P = .008), preop-erative sedimentation (P = .019), POD90 (P = .037) and POD180 L2 (P = .005) scores, preoperative (P = .049) and POD180 L4 (P = .017), and POD180 L total (P = .010) and F total (P = .022) scores between the patients with and without ALD. Conclusion. This study shows that the bone and mineral metabolism of the LT recipients was negatively affected after LT. In addition, we showed that bone and mineral metabolism was more prominent in patients with HCC, and bone mineral density scores were higher in patients with ALD.
Evaluation of the cardiopulmonary effects of repurposed COVID-19 therapeutics in healthy rats
(Nature Portfolio, 2026) Ozhan, Onural; Yildiz, Azibe; Bakar, Busra; Ulu, Ahmet; Kucukakcali, Zeynep; Karaca, Elif; Vardi, Nigar
Hydroxychloroquine (HCLQ), favipiravir (FAVI), molnupiravir (MOL) and dexamethasone (DEX) are recently used drugs, some of which are currently used in the treatment of Coronavirus Disease (COVID-19). We aimed to investigate the cardiovascular and pulmonary effects of MOL, HCLQ, FAVI and DEX-drugs repurposed or used in COVID-19 treatment-independently of SARS-CoV-2 infection, using a healthy rat model. Wistar albino rats were divided into seven groups by simple randomization. (1) Control, (2) HCLQ, (3) FAVI, (4) MOL, (5) HCLQ + FAVI, (6) MOL + DEX, (7) HCLQ + FAVI + DEX. The doses of drugs to be administered to the experimental groups were adapted to rat doses with reference to the clinical treatment protocol. At the end of the experimental period, hemodynamic parameters of the rats were measured invasively. After that, the heart, lung and thoracic aortic tissues of the rats were removed and evaluated biochemically, histopathologically and immunohistochemically. When the hemodynamic parameters of the rats were compared, a statistically significant difference was found between the groups only in the PR interval (p < 0.001). Compared to the control group, the histopathologic changes observed in the HCLQ + FAVI + DEX group were significantly higher (p < 0.05), while all other groups had a normal histologic appearance similar to the control group. Vimentin immunoreactivity was significantly higher in MOL, HCLQ + FAVI and MOL + DEX groups compared to the other groups (p < 0.05). Receptor interacting protein kinase 3 immunoreactivity observed in the cytoplasm of cardiomyocytes was significantly higher in the HCLQ + FAVI group compared to all other groups except the FAVI group (p < 0.05). In contrast, caspase-3 immunoreactivity was found to be significantly higher in the FAVI group compared to the control group (p < 0.05). Drugs used alone or in combination in the treatment of COVID-19 show immunoreactions using different pathways related to apoptosis and necroptosis. Further studies are needed to elucidate the effects of these drugs.
Evaluation of the Relationship Between Neurologic Manifestations and Genetic Mutations in Wilson's Disease with Next-Generation Sequencing
(Mdpi, 2025) Akbulut, Sami; Is, Seyma; Koprulu, Tugba Kul; Varol, Fatma Ilknur; Kucukakcali, Zeynep; Colak, Cemil; Koc, Ahmet
Background: Wilson's disease (WD) is a rare autosomal recessive disorder caused by mutations in the ATP7B gene, leading to copper accumulation in the liver and brain. Given the clinical heterogeneity of the disease, this study aimed to characterize the mutational spectrum of ATP7B and explore genotype-phenotype correlations in Turkish patients. Methods: Whole-exome sequencing (WES) was performed in 17 Turkish patients clinically diagnosed with WD. Variants were annotated and evaluated using five in silico prediction tools (REVEL, CADD, PolyPhen, SIFT, MutationTaster). Copy number variation (CNV) analysis was conducted using the CLC Genomics Server (Version 22.0.2). Results: A total of 14 distinct ATP7B variants were identified, comprising 12 missense, 1 nonsense, and 1 frameshift mutation. Variant distribution showed some phenotype-specific patterns: four variants were found more frequently in hepatic cases and three in neurological cases, although no statistically significant or consistent correlation between genotype and clinical presentation could be established. The most frequent mutation was p.His1069Gln, present in both phenotypes. All missense variants were predicted to be pathogenic by at least three computational tools, with high concordance among platforms. No pathogenic CNVs were detected. Conclusions: This study expands the mutational landscape of ATP7B in Turkish patients with WD and supports the utility of WES combined with in silico tools for accurate variant classification. The results emphasize the genetic heterogeneity of WD and suggest possible associations between certain mutations and clinical phenotypes.
Explainable Machine Learning for the Early Clinical Detection of Ovarian Cancer Using Contrastive Explanations
(Mdpi, 2025) Kucukakcali, Zeynep; Cicek, Ipek Balikci; Akbulut, Sami
Background: 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.
Histopathological Features of Gallbladder Specimens Obtained From Liver Recipients
(Elsevier Science Inc, 2023) Sarici, Kemal Baris; Akbulut, Sami; Karabulut, Ertugrul; Sahin, Tevfik Tolga; Kucukakcali, Zeynep; Garzali, Ibrahim Umar; Aloun, Ali
Background. To evaluate the histopathological features of gallbladder specimens obtained from liver transplantation (LT) recipients and to find the correlation between these findings with the clinical features of patients. Methods. The 1985 patients who underwent LT in our institute between March 2002 and January 2021 and whose data regarding pathologic analysis of gallbladder could retrospectively be obtained were included in the study. The data of the patients including age, gender, the reason for LT (fulminant or nonfulminant), presence of ascites, macroscopic characteristics of gallblad-der (the length, diameter, and wall thickness), and microscopic findings were all obtained and analyzed in the present study. Results. A total of 1985 patients (men = 1300 and women = 685) with a median age of 39.4 years were included in this study. LT was performed in 249 patients because of fulminant liver failure, and abdominal ascites were detected in 933 patients during LT. There were statisti-cal differences in terms of age (P < .001), gallbladder length (P < .001). and width (P < .001) among the both gender, but there was no difference in terms of histopathologic characteristics and presence of gallstones. On the other hand, there were significant differences in terms of age (P < .001), gallbladder length (P < .001), width (P < .001), wall thickness (P = .021), presence of gallstones (P < .001), and histopathologic characteristics (P < .001) between the patients with fulminant and nonfulminant liver failure etiologies. Similar results were obtained when characteristics of patients with and without ascites were compared. Conclusions. This the first study analyzing the histopathological analysis of gallbladder specimens in LT recipients. Chronic liver disease, presence of ascites and gender are the factors affecting the macroscopic and microscopic features of the gallbladder.
Immunosuppressive Medication Adherence in Patients With Hepatocellular Cancer Who Have Undergo Liver Transplantation: A Case Control Study
(Elsevier Science Inc, 2023) Akbulut, Sami; Tamer, Murat; Saritas, Serdar; Unal, Ozlem; Akyuz, Musap; Unsal, Selver; Kucukakcali, Zeynep
Background. We aimed to compare the adherence to immunosuppressive medication use in patients who underwent liver transplantation (LT) due to hepatocellular carcinoma (HCC) and non-HCC reasons.Methods. The study population was determined as 242 patients with HCC and 1290 patients with non-HCC who had LT performed in our institute between March 2002 and November 2021; all these patients were contacted by phone in March 2022. The sample size was calculated using the MedCalc software program, and the number of patients required in each group was determined as 111 patients. Furthermore, we used the sample.int function, a random integer generator in the R (version 4.1.2) software program. Whereas demographic and clinical parameters were determined as independent variables, the immunosuppressive medication adherence scale (IMAS) score was determined as a dependent variable. Patients were evaluated by the IMAS. This 11-item IMAS scale evaluates the lowest compliance score as 11 and the highest as 55.Results. Out of a total number of 221 patients, 161 (72%) were men and 60 (27.1%) were women, with a median age of 58 years (IQR: 14); one patient in the non-HCC group was excluded due to lack of data. Among the HCC and non-HCC groups, significant differences were found in terms of the variables of age (P = .003), IMAS score (P < .001), sex (P = .001), working status (P = .004), chronic diseases (P = .008), tacrolimus alone (P < .001), tacrolimus plus everolimus (P < .001), and often medication changes (P < .001). A statistically significant correlation was found between the IMAS score and whether the patients had HCC (P < .001) and frequently changing immunosuppressive drugs (P = .023).Conclusion. This study showed that patients with frequent drug changes or non-HCC etiology had better adherence to immunosuppressive drug use.

Yazar "Kucukakcali, Zeynep" seçeneğine göre listele

Sayfa Başına Sonuç

Sıralama seçenekleri