In order to limit the spread of the novel betacoronavirus (SARS-CoV-2), it is necessary to detect positive cases as soon as possible and isolate them. For this purpose, machine-learning algorithms, as a field of artificial intelligence, have been recognized as a promising tool. The aim of this study was to assess the utility of the most common machine-learning algorithms in the rapid triage of children with suspected COVID-19 using easily accessible and inexpensive laboratory parameters. A cross-sectional study was conducted on 566 children treated for respiratory diseases: 280 children with PCR-confirmed SARS-CoV-2 infection and 286 children with respiratory symptoms who were SARS-CoV-2 PCR-negative (control group). Six machine-learning algorithms, based on the blood laboratory data, were tested: random forest, support vector machine, linear discriminant analysis, artificial neural network, k-nearest neighbors, and decision tree. The training set was validated through stratified cross-validation, while the performance of each algorithm was confirmed by an independent test set. Random forest and support vector machine models demonstrated the highest accuracy of 85% and 82.1%, respectively. The models demonstrated better sensitivity than specificity and better negative predictive value than positive predictive value. The F1 score was higher for the random forest than for the support vector machine model, 85.2% and 82.3%, respectively. This study might have significant clinical applications, helping healthcare providers identify children with COVID-19 in the early stage, prior to PCR and/or antigen testing. Additionally, machine-learning algorithms could improve overall testing efficiency with no extra costs for the healthcare facility.

Background: The influenza virus and the novel beta coronavirus (SARS-CoV-2) have similar transmission characteristics, and it is very difficult to distinguish them clinically. With the development of information technologies, novel opportunities have arisen for the application of intelligent software systems in disease diagnosis and patient triage. Methods: A cross-sectional study was conducted on 268 infants: 133 infants with a SARS-CoV-2 infection and 135 infants with an influenza virus infection. In total, 10 hematochemical variables were used to construct an automated machine learning model. Results: An accuracy range from 53.8% to 60.7% was obtained by applying support vector machine, random forest, k-nearest neighbors, logistic regression, and neural network models. Alternatively, an automated model convincingly outperformed other models with an accuracy of 98.4%. The proposed automated algorithm recommended a random tree model, a randomization-based ensemble method, as the most appropriate for the given dataset. Conclusions: The application of automated machine learning in clinical practice can contribute to more objective, accurate, and rapid diagnosis of SARS-CoV-2 and influenza virus infections in children.

As oxidative stress has been implicated in the pathogenesis of diabetes mellitus and periodontitis, it may serve as a link between these conditions. Therefore, as a part of the present study, salivary lipid peroxidation (LP) in periodontitis patients with and without diabetes mellitus type 2 (DM2) was evaluated, along with the periodontal therapy effectiveness. The study sample comprised of 71 DM2 patients with periodontitis and 31 systemically healthy controls suffering from periodontitis of comparable severity. In all participants, periodontal indices—plaque index (PI), gingival index (GI), papilla bleeding index (PBI), probing pocket depth (PPD), and clinical attachment level (CAL)—were recorded, and salivary LP was measured using a spectrophotometric method prior to treatment initiation and three months post-treatment. At baseline, mean salivary LP in DM2 patients was higher than that measured for the control group, but the difference did not reach statistical significance (p > 0.05), whereas a positive significant correlation was found between PPD and LP in both groups. Three months after nonsurgical periodontal therapy, clinical periodontal parameters and salivary LP levels were significantly reduced in both groups (p < 0.05). These findings indicate that the improvement in clinical periodontal status following nonsurgical periodontal therapy is accompanied by a significant decrease in salivary LP in DM2 patients, suggesting that periodontitis, rather than diabetes, is the primary driver of the elevated salivary LP in this group.

Diabetes and periodontitis are complex chronic diseases that are potentially interrelated, as well as associated with oxidative stress. Thus, the aim of the present study was to evaluate the influence of nonsurgical periodontal treatment on salivary 8-hydroxy-deoxyguanosine (8-OHdG) levels and glycemic control in patients suffering from both diabetes mellitus type 2 (DM2) and periodontitis. The study sample included 53 DM2 patients, while 31 systemically healthy patients served as controls. Participants in both groups suffered from periodontitis of comparable severity. Periodontal clinical parameters, namely plaque index (PI), gingival index (GI), papilla bleeding index (PBI), probing pocket depth (PPD), and clinical attachment level (CAL) were recorded, along with salivary 8-OHdG levels and glycated hemoglobin (HbA1c). Levels of 8-OHdG were analyzed by ELISA. All aforementioned parameters were evaluated prior to commencing the study and at 90-day follow-up upon nonsurgical periodontal therapy completion. At baseline, salivary levels of 8-OHdG in DM2 patients were significantly higher (1.17 ng/mL) than those measured for the control group (0.75 ng/mL) and showed significant positive correlation with GI and PPD (p < 0.05). Three months after nonsurgical periodontal therapy, the salivary 8-OHdG levels were significantly reduced in DM2 patients (p < 0.05). Analysis results also revealed statistically significant changes in all measured clinical parameters between baseline and three-month follow-up in both groups (p < 0.05). Upon treatment completion, a decline in the HbA1c level was noted in DM group, but it did not reach statistical significance (p > 0.05). It can be concluded that DM2 patients benefit from non-surgical periodontal therapy, as indicated by a marked reduction in their salivary 8-OHdG level and a modest improvement in glycemic control. Short-term clinical benefits noted in the DM group were similar to those observed in the non-diabetic periodontal patients.

Background/Objectives: Vitamin D deficiency in children has been linked to various metabolic disturbances, including dyslipidemia, which contributes to cardiovascular risk. This study aims to investigate the relationship between vitamin D levels and lipid profiles in children. Methods: A cohort of 332 children with either normal vitamin D or diagnosed vitamin D deficiency was recruited. Serum vitamin D levels were measured, and lipid profiles, including total cholesterol, low-density lipoproteins (LDLs), high-density lipoproteins (HDLs), and triacylglycerols (TAGs), were assessed. The data were analyzed using statistical methods. Results: This study found that children with higher serum vitamin D concentrations had significantly lower TAG (p = 0.033) and very-low-density lipoprotein (VLDL) (p = 0.038) levels and higher HDL levels (p = 0.042), indicating a more favorable lipid profile compared to those with lower vitamin D levels. Conclusions: This study demonstrates that vitamin D deficiency can be associated with dyslipidemia in children. These findings suggest that vitamin D supplementation may be an effective strategy for managing dyslipidemia and reducing cardiovascular risk in pediatric populations. Further research is needed to determine the long-term effects and optimal dosing of vitamin D in this context.

Newborn screening (NBS) is a well-established public health program that enables early detection and treatment of rare disorders in newborns, preventing severe complications or death. Despite its recognized importance, the scope and implementation of NBS programs vary across Southeastern (SE) and Central Europe. This study aimed to evaluate the current status of NBS in 16 countries of SE and Central Europe and assess progress since the previous survey in 2021. A structured questionnaire was distributed to national experts between April and December 2025, collecting data on program organization, coverage, diseases included, laboratory methods, confirmatory testing, consent practices, and future expansion plans. All countries reported universal screening for congenital hypothyroidism, except Kosovo, where a national NBS is in the process of being established. Expanded NBS using tandem mass spectrometry was available in Austria, Bulgaria, Croatia, Cyprus, Greece, Hungary, North Macedonia, Romania, and Slovenia. Spinal muscular atrophy screening became universal in Austria, Croatia, Hungary, Serbia, and Slovenia. Most countries reported plans for further expansion, with congenital adrenal hyperplasia, severe combined immunodeficiency, spinal muscular atrophy, and cystic fibrosis being the most frequently targeted conditions. Although notable infrastructural progress has been achieved, financial constraints, lack of staff, and organizational barriers remain key challenges. The study’s assessment of program effectiveness was further limited by the absence of region-wide systems for capturing end-to-end performance indicators, such as the age of the infant at treatment initiation or missed cases. Regional collaboration and adoption of best practices are therefore vital to ensure equitable access and continuous advancement of NBS programs.