Mercury (Hg) is a toxic heavy metal with extensive applications. In children, mercury exposure often occurs inadvertently through laboratories, thermometers, or fluorescent lamps. Inhalation of elemental mercury can affect the central nervous system and urinary system. Early diagnosis and treatment are crucial to prevent severe complications. A retrospective evaluation was conducted on 82 pediatric cases of mercury poisoning who presented to Bingöl State Hospital on January 15, 2020. Blood and urine mercury levels were measured. Patients with mercury levels > 10 μg/L received intravenous treatment with 2,3-dimercaptopropane sulfonic acid (DMPS) for 5 days. Plasma and urine mercury levels were analyzed before and after treatment. Adverse effects of treatment and follow-up processes were also examined. Of the patients, 43.9% were female, and 56.1% were male, with a mean age of 9.4 ± 3.2 years. A total of 42.7% of cases were symptomatic, with headache being the most common symptom (26.8%). Significant reductions in blood and urine mercury levels were observed after treatment (p < 0.001). Adverse effects of the drug were reported in 43.9% of cases, with nausea (50%) and itching (25%) being the most frequent. Conclusion: Chelation therapy was effective in significantly reducing mercury levels in cases of mercury poisoning. Adverse effects must be carefully managed, and long-term follow-up is essential. This study provides significant contributions to the literature on mass mercury poisoning cases. What is Known:• Symptoms of mercury poisoning.What is New:• Long-term outcomes of DMPS therapy in 82 patients.
Background/Objectives: Pneumonia remains a leading cause of childhood morbidity and mortality worldwide. Accurate interpretation of pediatric chest radiographs is challenging because of anatomical variability, subtle radiographic findings, and inter-observer variability. This study evaluates different CNN–Transformer ensemble strategies for pediatric pneumonia detection by combining complementary local and global image representations. Methods: Experiments were conducted on the publicly available Pediatric Pneumonia Chest X-ray dataset containing 5856 radiographs. EfficientNetV2-S was used to extract local features, whereas Swin Transformer-T modeled global anatomical relationships. Soft voting, weighted voting, and stacking were evaluated under a unified training protocol. Image preprocessing, data augmentation, and Weighted Random Sampling were applied to improve robustness and address class imbalance. Performance was assessed using an independent hold-out test set and five-fold cross-validation. Grad-CAM was used to interpret model predictions. Results: Ensemble learning improved classification performance compared with individual models while revealing different trade-offs among fusion strategies. The Soft Ensemble achieved the highest hold-out accuracy (96.96%) and F1-score (97.59%). The Hybrid CNN–Transformer Stacking model achieved the highest sensitivity (99.49%) and produced the fewest false-negative predictions (n = 2), while demonstrating the most consistent performance across five-fold cross-validation. Grad-CAM visualizations indicated that the CNN and Transformer models captured complementary radiographic information. Conclusions: The proposed framework demonstrates that different ensemble strategies offer distinct advantages. Soft voting provided the best overall hold-out performance, whereas stacking minimized false-negative predictions and achieved the highest sensitivity, indicating its potential for AI-assisted pediatric pneumonia screening.
1 October 2026 in Current Genetic Medicine Reports