Aleksandra Simovic

This study focuses on developing a model for the precise determination of ultrasound image density and classification using convolutional neural networks (CNNs) for rapid, timely, and accurate identification of hypoxic-ischemic encephalopathy (HIE). Image density is measured by comparing two regions of interest on ultrasound images of the choroid plexus and brain parenchyma using the Delta E CIE76 value. These regions are then combined and serve as input to the CNN model for classification. The classification results of images into three groups (Normal, Moderate, and Intensive) demonstrate high model efficiency, with an overall accuracy of 88.56%, precision of 90% for Normal, 85% for Moderate, and 88% for Intensive. The overall F-measure is 88.40%, indicating a successful combination of accuracy and completeness in classification. This study is significant as it enables rapid and accurate identification of hypoxic-ischemic encephalopathy in newborns, which is crucial for the timely implementation of appropriate therapeutic measures and improving long-term outcomes for these patients. The application of such advanced techniques allows medical personnel to manage treatment more efficiently, reducing the risk of complications and improving the quality of care for newborns with HIE.

This research addresses the respiratory distress syndrome (RDS) in preterm newborns caused by insufficient surfactant synthesis, which can lead to serious complications, including pneumothorax, pulmonary hypertension, and pulmonary hemorrhage, increasing the risk of a fatal outcome. By analyzing chest radiographs and blood gases, we specifically focus on the significant contributions of these parameters to the diagnosis and analysis of the recovery of patients with RDS. The study involved 32 preterm newborns, and the analysis of gas parameters before and after the administration of surfactants and inhalation corticosteroid therapy revealed statistically significant changes in values of parameters such as FiO₂, pH, pCO₂, HCO₃, and BE (Sig. < 0.05), while the pO₂ parameter showed a potential change (Sig. = 0.061). Parallel to this, the research emphasizes the development of a lung segmentation algorithm implemented in the MATLAB programming environment. The key steps of the algorithm include preprocessing, segmentation, and visualization for a more detailed understanding of the recovery dynamics after RDS. These algorithms have achieved promising results, with a global accuracy of 0.93 ± 0.06, precision of 0.81 ± 0.16, and an F-score of 0.82 ± 0.14. These results highlight the potential application of algorithms in the analysis and monitoring of recovery in newborns with RDS, also underscoring the need for further development of software solutions in medicine, particularly in neonatology, to enhance the diagnosis and treatment of preterm newborns with respiratory distress syndrome.

Immune and physiological changes that occur during pregnancy may increase the risk of developing serious SARS-CoV-2 infections. In this paper a case report was presented about the non-infected newborn with 5-minute Apgar score of 8 who developed massive pulmonary thromboembolism in the first 36 hours of being born, from a SARS-CoV-2 positive mother without any symptoms. Careful monitoring of the newborn and determination of the coagulation status and inflammation markers on a daily basis could be justified in SARS-CoV-2 positive pregnancy.

This research addresses the respiratory distress syndrome (RDS) in preterm newborns, caused by insufficient surfactant synthesis, which can lead to serious complications, including pneumothorax, pulmonary hypertension, and pulmonary hemorrhage, increasing the risk of a fatal outcome. By analyzing chest radiographs and blood gases, we specifically focus on the significant contributions of these parameters to the diagnosis and analysis of the recovery of patients with RDS. The study involved 32 preterm newborns, and the analysis of gas parameters before and after the administration of surfactants and inhalation corticosteroid therapy revealed statistically significant changes in values of parameters such as FiO2, pH, pCO2, HCO3 and BE (Sig.<0.05), ehile the pO2 parameter showed a potential change (Sig.=0.061). Parallel to this, the research emphasizes the development of a lung segmentation algorithm implemented in the MATLAB programming environment. The key steps of the algorithm include preprocessing, segmentation, and visualization for a more detailed understanding of the recovery dynamics after RDS. These algorithms have achieved promising results, with a global accuracy of 0.93±0.06, precision 0.81±0.16 and an F-score of 0.82±0.14. These results highlight the potential application of algorithms in the analysis and monitoring of recovery in newborns with RDS, also underscoring the need for further development of software solutions in medicine, particularly in neonatology, to enhance the diagnosis and treatment of preterm newborns with respiratory distress syndrome.

Background: Periventricular/intraventricular hemorrhage (PVH/IVH) has a major impact on neurodevelopment due to its complications and sequelae. Objectives: This study aimed to determine the frequency of neurosonographic examination and the length of the monitoring period in children diagnosed with PVH/IVH. Methods: This clinical observational analytical retrospective cohort study was performed on 102 children diagnosed with PVH/IVH. The examinations were done on the third, seventh, fourteenth, and twenty-first days after birth and then in the fourth and sixth weeks and the third and sixth months after birth. The results of the examinations performed over time were subjected to the kappa measure of agreement test, with a significance threshold of 0.05, to determine the period when the most significant changes occur in the patient’s condition, as well as to determine the optimum frequency of the examination. Results: There was statistically significant agreement between the results of all the examinations performed in the observed moments (P < 0.0005). However, it is indicative that the agreement was excellent for the fourth week (kappa agreement was more than 0.85), followed by the sixth week that was very good (kappa agreement was 0.79); however, the agreement for the sixth week and the third month was very small (kappa agreement was less than 0.1). Also, there were no major changes (kappa agreement between results from the third and sixth months was 0.88). Conclusions: The first neurosonographic examination should be conducted in the first 7 days after birth, and the control examination should be conducted at the age of 4 - 6 weeks. If a pathological finding is observed, the examination is repeated after the specified period until a stationary finding is observed. After the third month, no new changes in the finding are observed.

In children, the incidence of Legionnaires’ disease (LD) is unknown, hospital-acquired LD is associated with clinical risk factors and environmental risk, and children with cell-mediated immune deficiency are at high risk of infection. Both newborns were born in the same delivery room; stayed in the same hospital room where they were cared for, bathed, and breastfed; were male; were born on time, with normal birth weight, and with high Apgar score at birth; and survived this severe infection (L. pneumophila, serogroup 2-15) but with different clinical courses. In neonate 1, bleeding in the brain, thrombosis of deep pelvic veins, and necrosis of the lungs, which left behind cystic and cavernous changes in the lungs, were found, while neonate 2 suffered from pneumonia alone. The only difference in risk factors for LD between these two newborns is the number of days of illness until the start of azithromycin treatment (sixth versus the third day of illness). We suggest that a change in the guidelines for diagnosing and treating community-acquired pneumonia and hospital-acquired pneumonia in newborns is needed in terms of mandatory routine testing for Legionella pneumophila. Early initiation of macrolide therapy is crucial for the outcome of LD in the newborn.

Introduction. Elevated cardiac troponin gives excellent accuracy in the identification of myocardial damage in children, but it can also be elevated in a series of other diseases. Case report. We presented two children thirteen years of age with a high serum level of troponin-I after an acute episode of supraventricular tachycardia. We analyzed troponin- I levels in correlation with the maximum heart rate, duration of tachycardia and systolic left ventricular function (ejection fraction and fractional shortening). Conclusion. Abnormal troponin level can be seen in children with sustained supraventricular tachycardia and normal heart. Caution is advised in diagnosing cardiac dysfunction in children with supraventricular tachycardia and elevated troponin levels.

Introduction. The laryngeal hemangioma in children is a benign vascular neoplasm but it could become malignant after localization. Case outline. After two weeks of corticosteroid treatment in a 15-month-old boy, there were no desired results. This case report is a small contribution to the research of targeted Propranolol treatment in infantile laryngeal hemangioma and the role of Epinephrine in the initial treatment in life-threatening conditions. Conclusion. When laryngeal hemangioma has ?bad? localization and any surgical treatment is denied in spite of the vital risk, the choices of treatment are epinephrine (as the first choice) and propranolol.

Asthma, obesity, and irrational use of antibiotics early in a life can be considered to be the three epidemics of modern times, which encourage one another and whose base is the loss of bioavailability. Disruption of the intestinal microbiome early in the life is the basis for the development of metabolic diseases, allergic immunological diseases, and high mortality rate due to infection with resistant strains of bacteria. During the irrational use of penicillin and macrolides postnatally, the composition of the intestinal microbiota and its functions change 12–24 months after the antibiotics treatment, the settlement of advantage intestinal flora with probiotic microorganisms is delayed, the maturation of the intestinal mucosa is compromised. Respiratory and systemic inflammation is strongly influenced by the rich adipocyte metabolism so that the treatment of these children is complex, and their asthma often remains only partially controlled. The phenotype “obese asthma” is characterized by a steroid and bronchodilator resistance. Therapeutic solution could be the body weight reducing, vitamin D3 substitution, and antileukotriene application. The prophylactic therapy of this asthma, using macrolides for a long time, should be supported, mandatory, with the substitution of probiotic/synbiotic during, and at least 6–9 months after discontinuation of therapy with macrolide.

To investigate the role of presepsin obtained from tracheal aspirate of intubated newborns in the diagnosis of early neonatal pneumonia.