Febrile neutropenia (FN) is an important complication that causes high rates of morbidity and mortality in patients with malignancies. We aimed to investigate the etiology, epidemiological distribution and its change over the years, clinical courses, and outcomes of FN in children with acute leukemia. We retrospectively analyzed the demographic data, clinical characteristics, laboratory results, severe complications, and mortality rates of pediatric patients with FN between January 2010 and December 2020. In 153 patients, a total of 450 FN episodes (FNEs) occurred. Eighty-four (54.9%) of these patients were male, the median age of the patients was 6.5 (range: 3-12.2) years, and 127 patients (83%) were diagnosed with acute lymphoblastic leukemia. Fever with a focus was found in approximately half of the patients, and an etiology was identified for 38.7% of the patients. The most common fever focus was bloodstream infection (n=74, 16.5%). Etiologically, a bacterial infection was identified in 22.7% (n=102), a viral infection in 13.3% (n=60), and a fungal infection in 5.8% (n=26) of the episodes. Twenty-six (23.2%) of a total of 112 bacteria were multidrug resistant (MDR) The rate of severe complications was 7.8% (n=35) and the mortality rate was 2% (n=9). In logistic regression analysis, refractory/relapsed malignancies and high C-reactive protein (CRP) at first admission were found to be the most important independent risk factors for mortality. Prolonged neutropenia after chemotherapy, diagnosis of acute myeloid leukemia, identification of fever focus or etiological agents, invasive fungal infections, polymicrobial infections, and need for intravenous immunoglobulin treatment increased the frequency of severe complications. We found that there was no significant change in the epidemiological distribution or frequency of resistant bacteria in our center in the last 10 years compared to previous years. Prolonged duration of fever, relapsed/refractory malignancies, presence of fever focus, and high CRP level were significant risk factors for poor clinical course and outcome.

Objective: This study explores the utility of electrocardiogram parameters in conjunction with machine learning models for the early diagnosis of neonatal transient tachypnea (TTN). TTN is a common cause of respiratory distress in neonatal intensive care units, and early diagnosis has the potential to reduce invasive interventions and shorten hospital stays. Methods: The study retrospectively examined data from 101 neonates diagnosed with TTN and 82 healthy neonates, utilizing parameters such as P, QRS, T angles, and frontal QRS-T angle obtained from ECG. Results: Decision Tree, Neural Network, Random Forest, Boosting, and Support Vector Machine models were utilized among the machine learning algorithms. The dataset was split into 65% for training, 20% for validation, and 15% for testing. According to the findings, the Random Forest classification model demonstrated superior performance compared to other models, achieving 71.4% test accuracy, an average AUC value of 0.790, and a Matthews Correlation Coefficient of 0.443. The MCC value indicated that the Random Forest model possesses reliable predictive power even with imbalanced datasets. Notably, ECG parameters such as PR interval, V2 T voltage, and SV1 voltage were identified as the most significant features influencing the model's predictive performance. Conclusions: These findings suggest that ECG-based machine learning models can enhance clinical decision-making by facilitating non-invasive, rapid, and accurate diagnosis of TTN. Such artificial intelligence-driven systems hold the potential to mitigate unnecessary interventions, expedite treatment initiation, and improve neonatal prognoses. Future efforts should focus on enhancing model interpretability through the incorporation of explainable AI methodologies to facilitate their seamless integration into clinical practice.