Background: Accurate and timely detection of pneumothorax on chest radiographs is critical in emergency and critical care settings. While subtle cases remain challenging for clinicians, artificial intelligence (AI) offers promise as a diagnostic aid. This retrospective diagnostic accuracy study evaluates a deep learning model developed using Google Cloud Vertex AI for pneumothorax detection on chest X-rays. Methods: A total of 152 anonymized frontal chest radiographs (76 pneumothorax, 76 normal), confirmed by computed tomography (CT), were collected from a single center between 2023 and 2024. The median patient age was 50 years (range: 18– 95), with 67.1% male. The AI model was trained using AutoML Vision and evaluated in both cloud and edge deployment environments. Diagnostic accuracy metrics—including sensitivity, specificity, and F1 score—were compared with those of 15 physicians from four specialties (general practice, emergency medicine, thoracic surgery, radiology), stratified by experience level. Subgroup analysis focused on minimal pneumothorax cases. Confidence intervals were calculated using the Wilson method. Results: In cloud deployment, the AI model achieved an overall diagnostic accuracy of 0.95 (95% CI: 0.83, 0.99), sensitivity of 1.00 (95% CI: 0.83, 1.00), specificity of 0.89 (95% CI: 0.69, 0.97), and F1 score of 0.95 (95% CI: 0.86, 1.00). Comparable performance was observed in edge mode. The model outperformed junior clinicians and matched or exceeded senior physicians, particularly in detecting minimal pneumothoraces, where AI sensitivity reached 0.93 (95% CI: 0.79, 0.97) compared to 0.55 (95% CI: 0.38, 0.69) – 0.84 (95% CI: 0.69, 0.92) among human readers. Conclusion: The Google Cloud Vertex AI model demonstrates high diagnostic performance for pneumothorax detection, including subtle cases. Its consistent accuracy across edge and cloud settings supports its integration as a second reader or triage tool in diverse clinical workflows, especially in acute care or resource-limited environments.

Anti-tumor necrosis factor agents are widely used in treating ankylosing spondylitis, but they increase the risk of infection by suppressing the immune response. Therefore, physicians should be careful about recurrent infections in patients under anti-tumor necrosis factor agents.

Burnout syndrome is a condition in which people working in businesses that require face-to-face communication, with prolonged stress where personal coping methods fail. Healthcare professionals are one of the most risky occupational groups in terms of burnout syndrome due to their heavy workload. In addition to the workload, the need to provide emotional support, providing care for severe and deadly patients, disturbed sleep patterns, and the high number of duties increase burnout in major stressors on healthcare professionals. In this study, our primary aim is to evaluate the relationship between burnout level and sleep quality in emergency medicine assistants. This study is a descriptive and cross-sectional study. According to the data obtained from the Higher Education Board, the personal information form and maslach burnout scale and pitsburg sleep quality scale surveys were sent to all Burnout syndrome is a condition in which people working in businesses that require face-to-face communication, with prolonged stress where personal coping methods fail. Healthcare professionals are one of the most risky occupational groups in terms of burnout syndrome due to their heavy workload. In addition to the workload, the need to provide emotional support, providing care for severe and deadly patients, disturbed sleep patterns, and the high number of duties increase burnout in major stressors on healthcare professionals. In this study, our primary aim is to evaluate the relationship between burnout level and sleep quality in emergency medicine assistants. This study is a descriptive and cross-sectional study. According to the data obtained from the Higher Education Board, the personal information form and maslach burnout scale and pitsburg sleep quality scale surveys were sent to all emergency assistants receiving training in Turkey. A total of 94 people working as emergency medical assistants participated in our study. According to the maclach burnout scale subgroup emotional exhaustion, 84% (n= 79) of the participants had a high level of emotional exhaustion and 16% (15) had moderate emotional exhaustion. When the MBI subgroup desensitization was evaluated, 87.2% (n= 82) was found high and 12.8% (n= 12) was found moderate. When the personal success of the MBI subgroup was evaluated, 97.9% (n= 92) was found low and 2.1% (n= 2) was found moderate. When the correlation between the MBI subgroups and the PSQS scoring was evaluated, a moderate positive correlation was found between emotional exhaustion and PSQS (p≤0.001). When the sleep quality with MBI is evaluated by regression analysis, it is seen that the state of exhaustion affects quality of sleep by 13.1%. High level of burnout during the education period of the emergency medicine assistant causes sleep quality deterioration. This situation causes difficulties in business and private life over time. We think that it will be beneficial to regulate the monthly working hours in order to decrease the burnout levels and increase sleep quality for keeping EMAs physically and mentally healthy, to increase the training staff to make them feel safe, and to organize programs to increase non-work social activities.

Objective: This study aimed to evaluate the diagnostic performance of point-of-care ultrasound (POCUS) for detecting and grading hydronephrosis in patients presenting to the emergency department (ED) with suspected renal colic, using non-contrast computed tomography (CT) as the reference standard. Material and Methods: This prospective observational diagnostic accuracy study included 106 adult patients who underwent both renal POCUS and non-contrast CT during the same ED visit. Hydronephrosis was classified as none, mild, moderate, or severe. The diagnostic performance of POCUS was assessed for detecting any hydronephrosis (grade ≥2) and moderate-to-severe hydronephrosis (grade ≥3). Agreement between POCUS and CT grading was evaluated using kappa coefficients.Results: CT demonstrated hydronephrosis in 58 patients (54.7%). For any hydronephrosis, POCUS showed a sensitivity of 86.2%, specificity of 83.3%, and overall accuracy of 84.9% (κ=0.695; p<0.001). Exact agreement across the four grades was 62.3%, while within-one-grade agreement was 98.1%. Linear-weighted and quadratic-weighted κ values were 0.626 and 0.777, respectively. POCUS assigned a higher grade than CT in 30 cases and a lower grade in 10 cases (p=0.001). For moderate-to-severe hydronephrosis, sensitivity was 88.9%, specificity was 82.3%, and negative predictive value was 95.6%.Conclusion: POCUS provides good diagnostic performance for the rapid, radiation-free assessment of hydronephrosis in renal colic. However, because it tends to overestimate hydronephrosis severity compared with CT, high-grade POCUS findings should not be considered directly equivalent to the corresponding CT grade.