With the increasing global demand for artificial intelligence solutions, their role in medicine is also expected to grow as a result of their advantage of easy access to clinical data. Machine learning models, with their ability to process large amounts of data, can help solve clinical issues. The aim of this study was to construct seven machine learning models to predict the outcomes of emergency department patients and compare their prediction performance. Data from 75,803 visits to the emergency department of a public hospital between January 2022 to December 2023 were retrospectively collected. The final dataset incorporated 34 predictors, including two sociodemographic factors, 23 laboratory variables, five initial vital signs, and four emergency department-related variables. They were used to predict the outcomes (mortality, referral, discharge, and hospitalization). During the study period, 316 (0.4%) visits ended in mortality, 5285 (7%) in referral, 13,317 (17%) in hospitalization, and 56,885 (75%) in discharge. The disposition accuracy (sensitivity and specificity) was evaluated using 34 variables for seven machine learning tools according to the area under the curve (AUC). The AUC scores were 0.768, 0.694, 0.829, 0.879, 0.892, 0.923, and 0.958 for Adaboost, logistic regression, K-nearest neighbor, LightGBM, CatBoost, XGBoost, and Random Forest (RF) models, respectively. The machine learning models, especially the discrimination ability of the RF model, were much more reliable in predicting the clinical outcomes in the emergency department. XGBoost and CatBoost ranked second and third, respectively, following RF modeling.

Introduction: The aim of this prospective observational study was to compare the predictive ability of the Triage Risk Stratification Tool and Identification of Seniors at Risk in identifying elderly people at risk of adverse outcomes (return to the emergency department, hospital admission, and death) within 30 days following discharge from the emergency department. Materials and Methods: 396 patients aged between 65 and 98 (mean 76.89±7.59) accessing the emergency department were evaluated over a 1-month period. Both screening tool were administered in the emergency department by emergency specialist physicians. Risk factors were assigned a score based on their regression co-efficient estimate and a total risk score was created. This score was evaluated for sensitivity and specificity. Results: Of the 396 participants, 198 (50%) were female. A significant correlation was not observed between risk of adverse outcomes and characteristics of the participant (p>0.005). The Identification of Seniors at Risk (cutoff of ≥3) was positive in 61.3% of the patients, whereas 79% were Triage Risk Stratification Tool-positive (cutoff of ≥2). The two scores were significantly correlated and had similar areas under the receiver operating characteristic curves in predicting hospital admission (Identification of Seniors at Risk, 0.63; Triage Risk Stratification Tool, 0.59). Conclusions: The predictive accuracy of the scoring systems for hospital admission after 30 days was significant at cutoff values of ≥3 for Identification of Seniors at Risk and ≥2 for Triage Risk Stratification Tool. The Identification of Seniors at Risk had slightly higher sensitivity and lower specificity than the Triage Risk Stratification Tool. Key Words: Emergency Service, Hospital; Geriatric Assessment; Risk Assessment; Aged.

Background: During the COVID-19 pandemic period, the unnecessary use of the emergency department (ED) affects the motivation of health care providers leading the healthcare services to be far from being efficient, delays the care of the patients having an actual emergency situation and reduces the quality of education in teaching clinics. Methods: Diagnoses in the visits were classified based on International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) categories and were analyzed into subgroups based on common reasons for ED visits. Results: While the number of ED visits in the first year of the pandemic period decreased by 26% compared to the previous year, the frequency of admissions in the circulatory system (CS), stomach and intestinal system (SIS), nervous system (NS), trauma (T), infectious disease (ID), endocrine system (ES), muscular system and connective tissues (MCT), gynecology and pregnancy (GP), environmental emergency (EE), mental and behavioral disorders (MBD), examination and encounter for administrative purposes (EEAP) was higher than expected and the frequency of admission and referral was also significantly more than the expected value (P < 0.001). Conclusion: In addition to the significant decrease in the number of ED visits during the pandemic, the fact that higher admission and referral frequency were observed indicating that the patients visited the emergency service in the late phases with severe clinical conditions. Key Words: COVID-19 pandemic, Emergency Departments, ICD Codes, Patient Admission, Outpatients,

Acil servislerde iş akışlarındaki temel problemler; yoğunluk, gereksiz kullanım eğilimleri ve uzun bekleme süreleri olarak özetlenebilir. Covid-19 pandemisi sırasında kırılma noktasını yaşayan acil servis yönetiminde yeni yaklaşımlar gündeme gelmiştir. Sağlık hizmeti sağlayıcıları, dünya çapında bu zorlukların çözümü olarak, yapay zekâ uygulamalarını acil servis iş süreçlerine dâhil etmeye başlamışlardır. Yapay zeka tabanlı makine öğrenimi modelleri, gelecekte klinik karar destek sistemlerine entegre edilerek hekimlerin iş yükünü azaltmalarının yanında acil servis işleyişleri için de yardımcı rol oynayacaklar gibi görünmektedir. Biz bu yazımızda, acil serviste makine öğrenimi birlikteliğine götüren nedenler temelinde modellemelerin acil servis hizmetlerindeki güncel durumu özetlemeye çalıştık. Makine öğrenimi modellerinin klinisyenlerin karar verme yetilerini geliştirdiği, tanısal hataları ve bilişsel yüklenmeyi azalttığı görüşleri öne çıkmaktadır.

Bu metin, çocukluk çağı düşmelerinin epidemiyolojisini, risk faktörlerini ve önlenmesine yönelik stratejileri kapsamlı bir şekilde ele almaktadır. Düşmelerin dünya genelinde çocuk yaralanmalarının en yaygın nedenlerinden biri olduğu vurgulanırken; yaş, cinsiyet ve sosyoekonomik durumun bu olaylardaki belirleyici rolleri incelenmektedir. Çalışma, özellikle düşük ve orta gelirli ülkelerdeki yüksek mortalite oranlarına dikkat çekerek, ev ve oyun alanlarında alınabilecek basit ama etkili güvenlik önlemleri ile eğitimin önemini ortaya koymaktadır.This text provides a comprehensive analysis of the epidemiology, risk factors, and prevention strategies regarding childhood falls. Highlighting that falls are among the most common causes of pediatric injuries worldwide, it examines the decisive roles of age, gender, and socioeconomic status. The study draws attention to high mortality rates, particularly in low- and middle-income countries, and emphasizes the importance of education alongside simple yet effective safety measures in homes and play areas.