Yazar "Bulut, Bensu" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A comparative analysis of the performance of large language models in the basic life support exam: comprehensive evaluation of ChatGPT-4o, Gemini 2.0, Claude 3.5, and DeepSeek R1(Bayrakol Medical Publisher, 2025) Bulut, Bensu; Öz, Medine Akkan; Genç, Murat; Gür, Ayşenur; Yortanlı, Mehmet; Yortanlı, Betül Çiğdem; Yazıcı, Ramiz; Mutlu, Hüseyin; Kotanoğlu, Mustafa Sırrı; Çınar, ErayConsidering the growing role artificial intelligence technologies play in medical education, this study aims to provide a comparative evaluation of the performances of large language models ChatGPT-4o, Gemini 2.0, Claude 3.5 , DeepSeek R1 in the Basic Life Support (BLS) Exam. Materials , Methods: In this observational study, we presented four large language models with 25 multiple-choice questions based on the American Heart Association (AHA) guidelines. Questions were divided into two categories as knowledge-based (n = 14, 56%) and case-based (n = 11, 44%). Response consistency was ensured by presenting each question on three separate days to all models. Models' accuracy rates were assessed using overall accuracy, strict accuracy, and ideal accuracy criteria. Results: In the overall accuracy assessment, ChatGPT-4o and DeepSeek R1 models showed 100% success, and Gemini 2.0 and Claude 3.5 models achieved 96% success rate. All models performed perfectly on the case-based questions. On the knowledge-based questions, ChatGPT-4o and DeepSeek R1 scored full points, while Gemini 2.0 and Claude 3.5 achieved 90.9% success. Statistical analysis showed no significant difference between results (p = 0.368). Discussion: Large language models show high accuracy rates in BLS training. These technologies can be used in supportive roles in medical education, but human supervision is critical in clinical decision-making.Öğe All-terrain vehicle related trauma: Analysis of injury patterns, safety equipment use and mortality(Effect Publishing Agency ( EPA ), 2025) Bulut, Bensu; Genç, Murat; Öz, Medine Akkan; Ecevit Kaya, Aynur; Topuz, Muhammed Ali; Borazan, İsmail; Kokulu, Kamil; Sert, Ekrem Taha; Mutlu, Hüseyin; Yazıcı, RamizTo determine age-specific patterns, effects of protective equipment use, and predictors of mortality in all-terrainvehicle (ATV)-related injuries. A total of 55 ATV-related trauma patients were retrospectively analyzed during the study period. Demographic characteristics, injury mechanisms, clinical findings and outcomes were evaluated. Injury patterns were compared according to age groups. Risk factors for mortality were determined by multivariate logistic regression analysis. The mean age of the patients was 22.3±12.8 years and 67.3% were male. Half of the victims (50.9%) were aged 18 years or younger. The majority of accidents occurred with drivers (70.9%) and on the street (70.9%). The rate of protective equipment use at the time of the accident was 21.8%. The most common mechanism of injury was ejection from the vehicle (63.6%), followed by impingement injuries (21.8%) and direct collisions (14.5%). Limb injuries were more common in patients younger than 18 years of age (68.2% vs. 43.5%), while more severe thoracic trauma was observed in patients older than 40 years. Off-road accidents were associated with higher injury severity scores than street/street accidents (mean Injury Severity Score (ISS) 22.6 vs. 16.8, p25 (odds ratio (OR), 8.64), severe head injury (OR 6.92), multiple system involvement (OR 5.78) and lack of protective equipment (OR 4.23) were independent predictors of mortality. ATV accidents are an important public health problem that can lead to serious injuries and fatalities. Injury patterns differ according to age groups. Inadequate use of protective equipment and the severity of off-road accidents are noteworthy. It is important to develop safety measures specific to age groups and to expand the use of protective equipment.Öğe Clinical outcomes of patients transported to the obstetric emergency department directly by ambulance and via inter-hospital transfer(Effect Publishing Agency ( EPA ), 2025) Kaya, Seray; Genç, Murat; Bulut, Bensu; Akkan Öz, Medine; Yazıcı, Ramiz; Mutlu, Hüseyin; Önder Gönen, MustafaThe aim of this study was to investigate the characteristics of pregnant patients transported directly by ambulance or by transfer between hospitals to the obstetric emergency department. The study was conducted among patients aged 18 years and over who were presented to the obstetric emergency department by ambulance between January 2024 and June 2024. Patients were divided into two groups as direct admission and inter-hospital transfer. Demographic characteristics, triage categories, indications for transfer, hospitalisation rates and length of hospital stay were recorded. Data were statistically analysed. A total of 600 patients were included in the study. In the inter-hospital transfer group, the hospitalisation rate and mean length of stay were significantly higher than in the direct admission group (30% vs 15% and 7 days vs 3 days, respectively). The rate and length of stay of patients in the Code Red triage category were higher in the transfer group. The most common indication for transfer was the need for a specialist. The rate and length of stay for patients requiring intensive care were higher than for other indications of transfer. Inter-hospital transfer is an important factor that may affect patient outcomes in the obstetric emergency department. Transferred patients were found to be more likely to be hospitalised and to have a longer length of stay. Optimising the transfer process is essential to ensure patient safety and minimise adverse outcomes.Öğe Comparison of first admission hemogram parameters and chest computed tomography findings of pediatric COVID-19 patients(Bayrakol MP, 2022) Sarı, Eyüp; Yazıcı, Ramiz; Bulut, Bensu; Çoban, Gülnur; Atik, Dilek; Kılıçaslan, CengizhanAim : We use computed tomography, which is one of the frequently used imaging tests, both as a disease diagnosis method and to follow the clinical course in COVID-19 patients. This also means radiation exposure. Radiation exposure, especially in pediatric patients, can cause life-threatening diseases. Is there a blood parameter that will reduce this undesirable event and allow estimation of computed tomography findings? Are hemogram analysis, one of the most commonly used blood tests, and tomography findings of the disease related? We designed this study based on the questions. Material and Methods: Among the patients under the age of 18 who applied to the emergency department, those with a positive reverse transcription-polymerase chain reaction (RT-PCR) and chest CT and hemogram were included in the study. Chest CT findings were classified according to the CO-RADS classification. We compared the CO-RADS classification with hemogram parameters and the ratios of these parameters. Results: Platelet-to-lymphocyte ratio (PLR) rates were found to be significantly lower as imaging findings became more severe (<0.05). The ratio of MedianPlatelet Volume and Platelet (MPV/Plt) was found to be significantly higher as the imaging findings worsened (p<0.05). When the relationship between laboratory parameters according to imaging groups in our study was evaluated, there was a moderate negative correlation between lymphocyte and platelet levels and imaging findings (p<0.05). A moderate positive correlation with the monocyte level was found (p<0.05). Discussion: For the CO-RADS classification, it can be said that the patient was established to classify possible COVID-19 patients only according to chest CT. There is no study in the literature on the classification of pediatric patients with RT-PCR positive definite COVID-19 according to chest CT scans and the comparison of laboratory findings of patients with this classification. The combination of laboratory parameters and CO-RADS classification will guide clinicians in pediatric COVID-19 patient management.Öğe New frontiers in radiologic interpretation: evaluating the effectiveness of large language models in pneumothorax diagnosis(PLOS One, 2025) Bulut, Bensu; Akkan Öz, Medine; Genç, Murat; Gür, Ayşenur; Yortanlı, Mehmet; Yortanlı, Betül Çiğdem; Sarıyıldız, Oğuz; Yazıcı, Ramiz; Mutlu, Hüseyin; Kotanoğlu, Mustafa Sırrı; Çınar, Eray; Uykan, ZekeriyaBackground: This study evaluates the diagnostic performance of three multimodal large language models (LLMs)-ChatGPT-4o, Gemini 2.0, and Claude 3.5-in identifying pneumothorax from chest radiographs. Methods: In this retrospective analysis, 172 pneumothorax cases (148 patients aged >12 years, 24 patients aged ≤12 years) with both chest radiographs and confirmatory thoracic CT were included from a tertiary emergency department. Patients were categorized by age and pneumothorax size (small/large). Each radiograph was presented to all three LLMs accompanied by basic symptoms (dyspnea or chest pain), with each model analyzing each image three times. Diagnostic accuracy was evaluated using overall accuracy (all three responses correct), strict accuracy (≥2 responses correct), and ideal accuracy (≥1 response correct), alongside response consistency assessment using Fleiss' Kappa. Results: In patients older than 12 years, ChatGPT-4o demonstrated the highest overall accuracy (69.6%), followed by Claude 3.5 (64.9%) and Gemini 2.0 (57.4%). Performance was significantly poorer in pediatric patients across all models (20.8%, 12.5%, and 20.8%, respectively). For large pneumothorax in adults, ChatGPT-4o showed significantly higher accuracy compared to small pneumothorax (81.6% vs. 42.2%; p < 0.001). Regarding consistency, Gemini 2.0 demonstrated excellent reliability for large pneumothorax (Kappa = 1.00), while Claude 3.5 showed moderate consistency across both pneumothorax sizes. Conclusion: This study, the first to evaluate these three current multimodal LLMs in pneumothorax identification across different age groups, demonstrates promising results for potential clinical applications, particularly for adult patients with large pneumothorax. However, performance limitations in pediatric cases and with small pneumothoraces highlight the need for further validation before clinical implementation.Öğe Predictive factors of mortality in patients with abdominal trauma(Turkish Association of Trauma and Emergency Surgery, 2025) Turan, Ömer Faruk; Gökdere, Didem Çankaya; Genç, Murat; Bulut, Bensu; Akkanöz Öz, Medine; Mutlu, Hüseyin; Yazıcı, RamizTraumatic injuries, particularly abdominal trauma, are a major cause of mortality worldwide. This study aimed to evaluate predictive factors for mortality and morbidity in abdominal trauma patients using simple, rapid, and accessible clinical and laboratory parameters, with a focus on developing scoring systems for emergency department decision-making. METHODS: A retrospective cohort study was conducted in a Level 1 Trauma Center between October 2022 and March 2024. Patients aged 18 and older with abdominal trauma or multi-trauma were included, while cases with incomplete records, known chronic diseases, or a recent trauma history were excluded. Data on demographics, vital signs, laboratory results, imaging findings, clinical scores, and outcomes were collected. Logistic regression and receiver operating characteristic (ROC) analyses were performed to identify independent mortality predictors and their cut-off values. RESULTS: Out of 693 patients, the mortality rate was 3.6%. The most common mechanisms of trauma were road traffic accidents (59.3%) and falls (23.4%). Independent predictors of mortality included age >= 54 years, Glasgow Coma Scale (GCS) <= 14, Injury Severity Score (ISS) >= 24, and Shock Index >= 1.08. ROC analysis revealed that GCS had the highest predictive value for mortality (area under the curve [AUC]: 0.828), followed by ISS, age, and Shock Index. Elevated levels of alanine aminotransferase (ALT), aspartate aminotransferase (AST), lactate, and creatinine were associated with worse outcomes, aligning with findings in the literature. CONCLUSION: Age, GCS, ISS, and Shock Index are strong predictors of mortality in abdominal trauma patients. Integrating these parameters into clinical decision-making can enhance risk stratification and improve patient management. Prospective multicenter studies and national trauma registries are necessary to refine trauma care and reduce mortality rates.Öğe Prehospital and emergency data analysis in burn patients: Mortality predictors and response times over five years(Turkish Association of Trauma and Emergency Surgery, 2025) Bulut, Bensu; Genç, Murat; Öz, Medine Akkan; Yazıcı, Ramiz; Mutlu, Hüseyin; Sert, Ekrem Taha; Kokulu, Kamil; Borazan, İsmail; Turan, Ömer Faruk; Kahraman, Fatih Ahmet; Ay, SerdenBackground: This study aimed to retrospectively examine the prehospital and emergency department processes of burn cases to evaluate process effectiveness, establish regional data, and identify factors affecting mortality in burn patients. Methods: The study included 784 burn cases treated by Ankara 112 Emergency Health Services and transferred to Ankara Bilkent City Hospital Emergency Department between January 1, 2019 and December 31, 2023. Demographic data, burn characteristics, response times of 112 emergency health services, and patient outcomes were retrospectively analyzed. Results: The mean age of the patients included in the study was 23.4+-20.7 years, with 36.7% being female. The most common type of burn was hot liquid burns (49.9%) and 73.7% of cases involved second-degree burns. The overall mortality rate was 5%. Logistic regression analysis identified advanced age (odds ratio [OR]: 1.02), presence of inhalation burns (OR: 3.33), and burn percentage as independent risk factors for mortality. Receiver operating characteristic (ROC) analysis showed that age >44 years (38.5% sensitivity, 83.8% specificity) and burn surface >16% (89.7% sensitivity, 77.5% specificity) were predictive thresholds for mortality. Conclusion: Advanced age, extensive burn surface area, residence in rural areas, and inhalation injuries are key predictors of mortality in burn patients. Enhancing prehospital emergency services, implementing community education programs, and adopting a multidisciplinary approach are critical for preventing and effectively managing burn injuries.Öğe Prevalence and risk factors of attention deficit hyperactivity disorder in children admitted to the emergency department due to traumas(Turkish Association of Trauma and Emergency Surgery, 2024) Yazıcı, Ramiz; Mutlu, Hüseyin; Kılıçaslan, Cengizhan; Sert, Ekrem Taha; Kokulu, Kamil; Kara, Halil; Kılıçaslan, Murat; Ekici, Mustafa; Bulut, BensuThis study aims to determine the prevalence of Attention Deficit Hyperactivity Disorder (ADHD) symptoms and the associated risk factors in children admitted to the Emergency Department (ED) due to traumas. METHODS: EChildren aged 3-16 years admitted to the ED for traumas were included in the study. The control group consisted of children aged between 3-16, who visited the pediatric ED for non-traumatic reasons. The Revised Conners Parent Rating Scale (CPRS-R) was administered to parents who agreed to participate following initial intervention and stabilization. Trauma patients were divided into two groups: those diagnosed with ADHD and those without ADHD. Risk factors likely to increase the identification of ADHD were assessed. RESULTS: The study included 917 children, with both groups showing similar characteristics regarding age, sex, demographic, and cultural factors. The most common reason for ED visits was extremity traumas, accounting for 296 (35.2%) cases. The majority of trauma patients (95.9%) were discharged from the ED after outpatient interventions. All subscale scores of the CPRS-R, except for the social problems subscale, were significantly higher in the study group compared to the control group. Factors that increased the risk of ADHD included admission with extremity traumas (p<0.001), previous ED admissions due to traumas (p<0.001), and having a family member previously diagnosed with ADHD (p<0.001). CONCLUSION: The prevalence of ADHD symptoms may be higher in children admitted to the ED due to traumas. Furthermore, extremity traumas, previous trauma-related ED-admissions, and a family history of ADHD increase the risk of ADHDÖğe Prognostic indicators in patients with isolated thoracic trauma: A retrospective cross-sectional study(Turkish Association of Trauma and Emergency Surgery, 2024) Yazıcı, Ramiz; Bulut, Bensu; Genc, Murat; Akkan Öz, Medine; Hanalıoğlu, Damla; Kokulu, Kamil; Sert, Ekrem Taha; Mutlu, HüseyinThoracic trauma is a significant cause of mortality, especially among those arriving at hospitals. This study explores the associations between mortality, the shock index (SI), and specific metabolic and biochemical markers in patients with isolated thoracic trauma. METHODS: This retrospective cross-sectional study included all consecutive adult patients presenting with isolated thoracic trauma to a high-volume emergency department from January 2019 to December 2023. The predictive capability of SI levels and selected biomarkers upon admission for estimating mortality was assessed by determining the areas under the receiver operating characteristic curves (AUCs). Optimal cutoff values were determined using the Youden index method. RESULTS: The study involved 352 patients, with 285 (81%) being males and an average age of 50.0±17.7 years. The mortality rate was 9.6%. Mortality was significantly associated with higher shock index (odds ratio [OR]: 14.02, [95% confidence interval [CI] 0.8470.916], AUC=0.885, p=0.001), glucose/potassium ratio (OR: 1.24 [95% CI 1.14-1.35], AUC=0.869, p<0.001), and lactate levels (OR: 4.30 [95% CI 2.29-8.07], AUC=0.832, p<0.001). The optimal cutoff values determined for the shock index, glucose/potassium ratio, ionized calcium, and lactate were 1.02 (sensitivity, 94.1%; specificity 69.5%; positive predictive value [PPV], 24.8; negative predictive value [NPV], 99.1), 36.85 (sensitivity, 76.5%; specificity, 87.7%; PPV, 40.0; NPV, 97.2), 1.23 (sensitivity, 94.1%; specificity, 56.0%; PPV, 18.6; NPV, 98.9), and 1.98 (sensitivity, 70.6%; specificity, 80.5%; PPV, 27.9; NPV, 96.2), respectively. CONCLUSION: This study demonstrates that higher shock index, glucose/potassium ratio, and lactate levels are significantly associated with increased mortality in patients with isolated thoracic trauma. These findings suggest that these markers can be effective prognostic indicators, potentially guiding clinical decision-making and improving patient outcomes.Öğe Prognostic value of glucose-to-potassium ratio and other biomarkers in in-hospital cardiac arrest(MRE Press, 2025) Vişneci, Emin Fatih; Demirci, Osman Lütfi; Tekin, Fatih Cemal; Kadıoğlu, Emine; Mutlu, Hüseyin; Genç, Murat; Bulut, Bensu; Akkan Öz, Medine; Yazıcı, RamizThis study aimed to evaluate the prognostic value of the serum glucose/potassium ratio (GPR) for sustained return of spontaneous circulation (ROSC) and 30-day mortality in patients with in-hospital cardiac arrest (IHCA). Methods: Patients aged 18 years or older who underwent cardiopulmonary resuscitation (CPR) for cardiac arrest in the emergency department (ED) were included. Routine laboratory parameters were obtained from the first blood sample collected during CPR in the ED. The neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) were calculated by dividing the absolute number of neutrophils and platelets, respectively, by the absolute number of lymphocytes. The GPR was calculated as serum glucose divided by potassium levels. Results: The 30-day mortality rate was 82.2% (n = 291). Multivariate logistic regression analysis identified lactate, NLR, PLR and GPR as independent predictors of mortality. Among these markers, lactate exhibited the highest predictive power for mortality, with an area under the curve (AUC) of 0.817, compared to NLR (AUC: 0.676), PLR (AUC: 0.679) and GPR (AUC: 0.688). The optimal cut-off values for predicting mortality were 7.83 for lactate (sensitivity: 75.3%, specificity: 89.4%), 1.68 for NLR (sensitivity: 78.8%, specificity: 71.7%), 199.26 for PLR (sensitivity: 76.4%, specificity: 92.3%) and 57.81 for GPR (sensitivity: 71.8%, specificity: 84.1%). Conclusions: Our findings suggest that GPR is a promising prognostic marker for predicting mortality in patients with IHCA.
