Background/Objectives: In this study, a vision transformer (ViT) based ensemble architecture was developed for the classification of normal, benign, and malignant diseases from breast ultrasound images. The breast ultrasound images (BUSI) dataset was used for the implementation of the proposed method. This dataset includes 133 normal, 437 benign, and 210 malignant ultrasound images. Methods: ROI segmentation and image preprocessing were applied to the dataset to select only the tumor region and use it in the model. Thus, a better performance was achieved using only the lesion regions. Image augmentation was performed using the Albumentations library to increase the number of images. Feature extraction was performed on the obtained images using three ViT-based models (ViT-Base, DeiT, ViT-Small). The purpose of using three different models is to achieve high accuracy. The extracted features were classified using a multilayer perceptron (MLP). Training was performed using 10-fold stratified cross-validation. Results: The purpose of stratified cross-validation is to include a certain number of images from all three classes in each cross-validation proposed model provided 96.2% precision and 86.3% recall for the benign class and 92.9% recall and 76.4% precision for the malignant class. The normal class achieved 100% success. The area under the curve (AUC) values were 0.97, 0.96, and 1.00 for benign and malignant tumors, respectively, and 1.00 for normal tumors. Conclusions: The ROI-based ViT + MLP + Ensemble architecture provided higher accuracy and explainability compared to traditional convolutional neural network (CNN) based methods in medical image classification. It demonstrated a stable success, especially in minority classes, and presented a potential, reliable, and flexible solution in clinical decision support systems.

Objectives: This study aimed to investigate the potential roles of proprotein convertase subtilisin/ kexin type 9 (PCSK9) and apelin in the etiology of fibromyalgia syndrome (FS). Patients and methods: The retrospective study was conducted between May 2022 and February 2023. Fifty-eight female FS patients (mean age: 45.2±9.9 years; range, 25 to 66 years) and 30 age- and body mass index-matched control subjects (mean age: 43.1±9.9 years; range, 26 to 67 years) were included in the study. Apelin and PCSK9 levels of all individuals were measured using appropriate methods. Results: The levels of PCSK9 (173.2±62.2 vs. 75.1±44.1, p

Objective: This study aims to construct a high-precision decision support model by integrating explainable artificial intelligence (XAI) techniques utilizing urinary and plasma biomarkers. Methods: We used an open-access dataset published by Debernardi et al. (2020) containing the biomarkers Lymphatic Vessel Endothelial Hyaluronan Receptor 1 (LYVE1), Regenerating Family Member 1 Beta (REG1B), Trefoil Factor 1 (TFF1), and plasma CA19-9. The preprocessing phase involved missing value imputation, Z-score normalization, and feature engineering. An autoencoder (AE)-based unsupervised learning framework was employed for dimensionality reduction. Classification was performed using an XGBoost algorithm optimized via the Optuna framework. Class imbalance was addressed through the Synthetic Minority Over-sampling Technique (SMOTE). Model interpretability was ensured using SHapley Additive Explanations (SHAP). Results: The proposed Autoencoder–XGBoost model optimized with Optuna outperformed conventional methods, achieving an accuracy of 95.8%, 95% precision, 93% recall, 93% F1-score, and an AUC of 0.984. SHAP analysis identified plasma CA19-9, LYVE1, creatinine, and age as the most influential predictors contributing to model decisions. Conclusion: The developed XAI framework offers high diagnostic accuracy and transparent decision logic for the early detection of PDAC. By leveraging the clinical potential of urinary biomarkers, the model demonstrates strong applicability for integration into screening and risk stratification modules of clinical decision support systems.

Background and Objectives: Gestational diabetes mellitus (GDM), which is becoming increasingly common in contemporary society, is recognized for its considerable psychosocial impact on pregnant women throughout the perinatal phase. The purpose of this research was to explore the possible links between mental health status and dietary habits among pregnant women diagnosed with GDM, alongside examining how these factors correlate with clinical indicators like HbA1c measurements and the necessity for insulin therapy. Materials and Methods: The study included 82 pregnant participants, 37 with gestational diabetes mellitus and 45 without. Blood samples were collected from all participants for biochemical analysis, including fasting blood glucose, postprandial blood glucose, and HbA1c levels, which can be clinical indicators for the presence of gestational diabetes mellitus, and the need for insulin treatment was recorded. Then, participants completed a questionnaire collecting sociodemographic and clinical data as well as the Beck Anxiety Inventory (BAI), Beck Depression Inventory (BDI), Salzburg Emotional Eating Scale (SEES), and REZZY Eating Disorders Scale (REZZY). Data were statistically analyzed. Results: A previous diagnosis of gestational diabetes was more frequent in the case group (18.9%) than in the control group (2.2%) (p = 0.020). OGTT positivity was detected in 56.8% of the case group, whereas all control participants had negative results (p < 0.001). There were no statistically significant differences between the two groups in psychological symptom scores or eating behavior assessments (p > 0.05). Conclusions: Pregnant women with gestational diabetes mellitus were observed to score higher on measures of anxiety, depression, and emotional eating, particularly in response to negative emotions. These findings may indicate a potential association between gestational diabetes and psychological or behavioral factors related to metabolic regulation during pregnancy.

Due to the failure of the neoclassical convergence hypothesis in explaining economic growth, endogenous growth models have turned to alternative macroeconomic parameters. Among these alternative parameters, increasing education and health expenditures aims to enhance societal welfare and total factor productivity. This study examines the effect of education and health expenditures on economic growth in the Fragile Five economies during the period 2004–2021. All three variables exhibit cross-sectional dependence and contain unit roots at their level values. In the short run, a bidirectional causality is observed between education/health expenditures and economic growth, along with a unidirectional causality running from education expenditures to health expenditures. According to the error correction coefficients, the effect of health expenditures on growth emerges in the long run and is less influenced by output cycles. At the country level, causality from health expenditures to output is found only in South Africa, while causality from education expenditures to output is observed in Brazil and South Africa. Finally, there is no evidence of causality from output to health expenditures in any of the economies, whereas causality from output to education expenditures is found only in Turkey. Therefore, it is concluded that in Brazil, public expenditures focus on social transfers; in South Africa, historical inequalities and public health spending have translated into human capital productivity; in India and Indonesia, the efficiency of expenditures directed toward quasi-public goods remains low. In Turkey, findings indicate that economic prosperity does not directly translate into increased investment in education.

Aim: Colonoscopy continues to be the most dependable technique for early detection of colorectal cancer, one of the most prevalent cancers globally. To enhance the effectiveness of colonoscopic procedures, various international quality benchmarks have been established. This study aimed to assess whether colonoscopies conducted at the Endoscopy Unit of the Gastroenterology Clinic at Fırat University Hospital met internationally recognized quality standards. Material and Method: This retrospective study analyzed 2,805 colonoscopy procedures performed between 2015 August and 2019 January. International quality indicators were used for evaluation. Due to the lack of recorded procedure times prior to November 2018, the data were categorized into two periods: 2015 August –2018 October and 2018 November –2019 January. Results: From August 2015 to October 2018, the adenoma detection rate was 36% in males and was 26.4% in females. From November 2018 to January 2019, the adenoma detection rate (ADR) increased to 27.5% in females and 43% in males. The cecal intubation rate was 82% in the earlier period and rose slightly to 84.4% in the latter. Sedation was administered in 91.4% of procedures during the first period and in 98% during the second. Procedure duration, recorded only in the latter period, averaged 13.6 minutes. Conclusion: The ADR observed in this study align with international benchmarks; however, cecal intubation and colorectal cancer detection rates were below the recommended standards. These findings indicate that procedural improvements are necessary to meet international quality criteria more consistently.