Background/Objectives: Optimization algorithms are acknowledged to be critical in various fields and dynamical systems since they provide facilitation in identifying and retrieving the most possible solutions concerning complex problems besides improving efficiency, cutting down on costs, and boosting performance. Metaheuristic optimization algorithms, on the other hand, are inspired by natural phenomena, providing significant benefits related to the applicable solutions for complex optimization problems. Considering that complex optimization problems emerge across various disciplines, their successful applications are possible to be observed in tasks of classification and feature selection tasks, including diagnostic processes of certain health problems based on bio-inspiration. Sepsis continues to pose a significant threat to patient survival, particularly among individuals admitted to intensive care units from emergency departments. Traditional scoring systems, including qSOFA, SIRS, and NEWS, often fall short of delivering the precision necessary for timely and effective clinical decision-making. Methods: In this study, we introduce a novel, interpretable machine learning framework designed to predict in-hospital mortality in sepsis patients upon intensive care unit admission. Utilizing a retrospective dataset from a tertiary university hospital encompassing patient records from January 2019 to June 2024, we extracted comprehensive clinical and laboratory features. To address class imbalance and missing data, we employed the Synthetic Minority Oversampling Technique and systematic imputation methods, respectively. Our hybrid modeling approach integrates ensemble-based ML algorithms with deep learning architectures, optimized through the Red Piranha Optimization algorithm for feature selection and hyperparameter tuning. The proposed model was validated through internal cross-validation and external testing on the MIMIC-III dataset as well. Results: The proposed model demonstrates superior predictive performance over conventional scoring systems, achieving an area under the receiver operating characteristic curve of 0.96, a Brier score of 0.118, and a recall of 81. Conclusions: These results underscore the potential of AI-driven tools to enhance clinical decision-making processes in sepsis management, enabling early interventions and potentially reducing mortality rates.

Background Fournier's gangrene (FG) is a disease with high mortality rate. The first diagnosis is performed in the emergency department (ED). In this study, we investigated the importance of the time period for diagnosis in the ED. Methods The data of patients who were treated for FG between 1 January 2010 and 2020 were retrospectively analysed. Waiting period of the patients in ED was calculated. Risk factor score calculations were calculated to predict FG mortality and prognosis. The effects of the ED waiting period on the duration of admission to the hospital, the number of debridements and mortality status and relationship with FG mortality risk factor scores were investigated. Results In a 10-year period, a total of 66 patients were included in the study. It was found that the median age of the patients was 56 years. ED waiting period median (IQR) was 105 (115) minutes. It was observed that there was a significant positive correlation between the ED waiting period, duration of admission to hospital (rs: 0.537, P < .001) and patients mortality status (rs: 0.482, P < .001). The ED waiting period was higher in patients with FG mortality. It was observed that the ED waiting period holds a diagnostic value in predicting mortality (P < .001). The cut-off limit predicted for this value was determined as 136 minutes. Conclusion FG is a urological emergency. ED waiting period affects mortality rate and length of hospital stay. The earlier the diagnosis and treatment is conducted in the ED, the lower the mortality rate and length of stay in the hospital will be.

Introduction: The coronavirus disease 2019 (COVID-19) pandemic negatively affected the mental and sexual health of individuals, especially healthcare professionals. In this study, we aimed to investigate the changes in anxiety and sexual activity of male healthcare professionals following vaccination. Methodology: This prospective cross-sectional and descriptive online survey was conducted between July 1, 2021 and November 1, 2021, involving a total of 170 healthcare professionals. Socio-demographic characteristics, pre- and post-vaccination anxiety and sexual activity levels of the participants were compared. Results: There was a significant increase in only the intercourse times of the participants post vaccination (p = 0.034). The Beck anxiety inventory score decreased from median: 19 (minimum (min): 16, maximum (max): 47) before vaccination to median: 17, (min: 10, max: 43) after vaccination (p < 0.001). Likewise, Arizona Sexual Experiences Scale (ASEX) scores decreased after vaccination (median: 10, min: 5, max: 20) compared to before vaccination (median: 12, min: 5, max: 18) (p < 0.001). International Index of Erectile Function (IIEF) score also increased after vaccination (25.49 ± 6.50) compared to before vaccination (24.71 ± 7.10) (p < 0.001). Orgasmic function, sexual desire, intercourse satisfaction and overall satisfaction scores also improved (p = 0.013, p < 0.001, p = 0.027, p < 0.001). Conclusions: Mental and sexual disorders increased with the COVID-19 pandemic. In addition to immunity, the vaccine also had positive effects on anxiety and sexual activity.

Background: This study introduces the Adaptive Graph Fusion Network, an interpretable graph-based learning framework developed for large-scale prediction of intensive care outcomes. The proposed model dynamically constructs patient similarity networks through a density-aware kernel that adjusts neighborhood size based on local data distribution, thereby representing both frequent and rare clinical patterns. Methods: To characterize physiological evolution over time, the framework integrates a short-horizon convolutional encoder that captures acute variations in vital signs and laboratory results with a long-horizon recurrent memory unit that models gradual temporal trends. The approach was trained and internally validated on the publicly available eICU Collaborative Research Database, which includes more than 200,000 admissions from 208 hospitals across the United States. Results: The model achieved a mean area under the receiver operating characteristic curve of 0.91 across six critical outcomes, with in-hospital mortality reaching 0.96, outperforming logistic regression, temporal long short-term memory networks, and calibrated Transformer-based architectures. Feature attribution analysis using SHAP and temporal contribution mapping identified lactate trajectories, creatinine fluctuations, and vasopressor administration as dominant determinants of risk, consistent with established clinical understanding while revealing additional temporal dependencies overlooked by existing scoring systems. Conclusions: These findings demonstrate that adaptive graph construction combined with multi-horizon temporal reasoning improves predictive reliability and interpretability in heterogeneous intensive care populations, offering a transparent and reproducible foundation for future research in clinical machine learning.

OBJECTIVES: This study aims to determine the factors that would lead the doctors in EDs to a more the accurate diagnosis of urinary tract infection (UTI) and the correct initiation of empirical antibiotherapy in the emergency room and reduce the use of unnecessary antibiotherapy. METHODS: This study is a prospective observational study from a single-center, investigating patients with an age of 18 years and older who presented to the emergency department (ED) with the symptoms of UTI between January and May 2018. The guiding parameters to establish a UTI diagnosis and start an empirical antibiotherapy were investigated between the negative (Group 1) and positive (>10³ colonies) (Group 2) groups, as a result of urine culture in terms of urine culture. RESULTS: Our study included a total of 108 patients (59 women and 49 men). The average age was 47.11 ± 14.97. Age and gender were similar among the groups and not a discriminating factor in the diagnosis of UTI. High Charlson Comorbidity Index score, history of chronic kidney failure and cerebrovascular disease, leukocyte esterase, nitrite positivity, and leukocyte cluster presence were higher in Group 2. We suggest that these parameters might be predictive values to detect bacterial growth in urine culture. Empirical antibiotherapy was started in 48.4% of the patients in Group 1 and 95.7% of the patients in Group 2. CONCLUSIONS: In EDs, admission complaints of the patients and physical examination findings do not always result in the diagnosis of UTI. Our study showed that UTI diagnosis could be made more accurately using leukocyte esterase, nitrite positivity, the presence of leukocyte clusters, and the Charlson Comorbidity Index score. We also suggest that regional antibiotic resistance should be considered before starting empirical antibiotherapy.

Amaç: Bu çalışmada PSA seviyesi 4-10 ng/mL olan hastalarda alt üriner sistem semptomalarının prostat adenokanser ve benign prostat hiperplazisini ön görecek bir parametre olup olmadığını araştırmayı amaçladık. Gereç ve Yöntemler: 01 Haziran 2019 - 01 Şubat 2020 tarihleri arasında PSA değeri 4-10 ng/ml olan ilk kez TRUS-Bx uygulanan 75 hasta prospektif olarak çalışmaya dahil edildi. Hastaların yaş, BMI, PSA, Prostat hacmi, PSA dansitesi, uluslararası prostat semptom skorları ve uluslararası erektil fonksiyon skorları kayıt edildi. Patoloji sonucuna göre grup 1 (benign prostat hiperplazisi) ve grup 2 (prostat adenokanser) olarak hastalar 2 gruba ayrılarak belirtilen parametreler ile ilişkisi araştırıldı. Bulgular: PSA değeri 4-10 ng/ml olan ilk kez TRUS-Bx uygulanan 75 hastanın patoloji sonucunda; 57 (%76) hastada Benign Prostat Hiperplazisi (BPH) (grup 1), 18 (%24) hastada Prostat Adenokanser (PCa) (grup 2) saptandı. İncelenen parametrelerden sadece rektal tuşe de sertlik bulgusu (p=0.001) ve IPSS skor düşüklüğü (p=0.022) Grup 2’de grup 1’e göre istatistiksel anlamlı farklılık saptandı. Yapılan korelasyon analizinde de bulgular teyit edildi. Sonuç: PSA 4-10 ng/mL olan hastalar için IPSS skor düşüklüğü, rektal tuşe de sertlik olması kanser saptanma ihtimalini arttırmaktadır.