Sonja Golob Jančič

Background/Objectives: Child malnutrition is a global health challenge linked to poor growth, impaired development, weakened immunity, and adverse outcomes. Early risk detection is essential, but current screening tools differ in accuracy and feasibility. This study aimed to develop and validate new bedside pediatric malnutrition screening models based on machine learning and evolutionary computation methods that can capture complex patterns in non-invasive clinical indicators while remaining practical for routine ward use. Methods: We conducted a cross-sectional study including 180 hospitalized children (1 month–18 years) recruited consecutively from six pediatric wards. The required sample size (minimum 138 participants) was calculated a priori using national prevalence estimates of pediatric undernutrition (4–9.5%) to ensure adequate precision at a 95% confidence level. Data collection included a questionnaire, anthropometry, subjective malnutrition risk assessment, and the Subjective Global Nutritional Assessment (SGNA) tool. Screening models were developed using decision trees, random forests, XGBoost, lasso regression, artificial neural networks, ANFIS, and genetic programming. Their performance was evaluated against the SGNA tool and physician-based subjective malnutrition risk assessment using sensitivity, specificity, AUC, and Cohen’s κ. Results: Machine learning and intelligent evolutionary models (GP, ANN, and ANFIS) showed the best performance in this sample, with substantial to high agreement (κ = 0.81–1.00) and high diagnostic accuracy (AUC = 0.92–1.00) with the subjective malnutrition risk assessment. The GP model demonstrated the highest apparent accuracy in this dataset, but also higher complexity, whereas simpler models such as decision trees showed lower accuracy but greater interpretability and feasibility for routine clinical use. However, validation was performed on a relatively small independent sample, and no external validation was conducted, which may limit the generalizability of the findings. Conclusions: While complex models may serve as digital assessment instruments, simpler models are rapid and more suitable for bedside screening. All developed models are non-invasive and cost-effective and show potential for supportive approaches for early detection of malnutrition risk at hospital admission. However, given the limited validation sample and the absence of external validation, these findings should be interpreted with caution, and further large-scale, multicenter studies are required to confirm generalizability and clinical applicability.

Hypertension is increasingly recognized among children. The etiology and presentation depend crucially on the child’s age. In infancy, secondary caus

Background/Objectives: Oxidative stress and systemic inflammation are significant contributors to the development and progression of cardiovascular disease, causing adverse effects on vascular health and atherosclerosis from an early age. Patients with established cardiovascular risk factors commonly exhibit markers indicating heightened oxidative stress and inflammation. Our study sought to assess the levels of interleukin-2 receptor, which could serve as an early indicator of cardiovascular damage due to oxidative stress and inflammation in at-risk children. Methods: The study comprised 46 paediatric patients with chronic kidney disease, 50 paediatric patients with hypertension, and 33 healthy controls. Anthropometric measurements, pulse wave velocity, body composition, routine laboratory tests, and measurements of interleukin-2 receptor levels were conducted for all participants. Results: Interleukin-2 receptor levels were notably lower in patients with hypertension (p < 0.001) and those with overweight/obesity (p < 0.001) with several associated measures. Interleukin-2 receptor levels exhibited significant negative correlations with various anthropometric measurements, body composition, and liver damage and a positive correlation with kidney function tests. Conclusions: Children diagnosed with hypertension or obesity exhibited notably lower interleukin-2 receptor levels.

Estimated glomerular filtration rate (eGFR) based on different formulas is commonly used as a bedside tool to assess kidney function in children and young adults. The purpose of this study was to perform a measurement of glomerular filtration rate (mGFR) in children with chronic kidney disease (CKD) with a standard 5-point protocol using iohexol clearance and compare it to a simplified protocol for mGFR determination and to some of the most commonly used eGFR formulas. A 5-point standard protocol using iohexol clearance was used for determination of mGFR in 50 children with mild stages of CKD. The result was compared to 2- and 3-point sampling protocol as well as with some standard children eGFR formulas. We calculated the prediction performance for eGFR formulas to distinguish CKD1 and CKD 2 stages, formulas’ accuracy, and cutoff values. Data were prospectively collected. All eGFR formulas exhibited a statistically significant positive correlation with mGFR. The best correlation was found with CKID2012 eGFR formula and with cystatin C–based eGFR formulas. The correlation between standard and simplified protocols for mGFR determination was also strong, while creatinine clearance did not prove to be a reliable method for estimating GFR. The error distribution with simplified protocols was not dispersed. The prediction value was strong for CKID2012 and bedside Schwartz formula. Conclusion: Fewer sampling points can be safely used for measuring GFR in children. eGFR formulas that are not based solely on creatinine should be considered more often in GFR estimation. What is Known? • Iohexol clearance is an established method of measuring GFR in children and adolescents using different protocols. • Estimating GFR in children and adolescents is troublesome and is done using different formulas with anthropometric and biochemical markers in children and adolescents. What is New ? • Iohexol measurement with two or three blood withdrawals can reliably distinguish between CKD1 and CKD2 patients. • eGFR formulas have moderate reliability to predict distinguish between CKD1 and CKD2 patients, of which CKID2012 and bedside Schwartz formula were the most accurate in our study.

(1) Background: Ultrasound elastography is a novel ultrasound technique for evaluating tissue elasticity. One of the key factors influencing the measurement in children is excess weight. This study aimed to evaluate the effect of body composition, namely, fat mass, on liver and kidney ultrasound elastography in paediatric patients. (2) Methods: 114 participants, in whom bioimpedance, along with liver and kidney ultrasound elastography, were performed, were included (37 patients with chronic kidney disease, 46 patients with hypertension, and 31 healthy subjects). (3) Results: Bioimpedance analysis showed a significant correlation between liver elastography parameters and the phase angle (p = 0.002), fat-free mass (p = 0.001), body cell mass (p = 0.001), total body water (p = 0.001), extracellular water (p = 0.006), and, to lesser extent, fat mass (p = 0.041). On the contrary, kidney elastography parameters strongly correlated only with fat mass (p < 0.001 for both kidneys). (4) Conclusions: Liver and kidney stiffness increased in overweight participants and showed significant correlation with fat mass, particularly in the case of kidney elastography.

Background Ultrasound elastography is a research method increasingly used to measure tissue elasticity. The aim of the study was to assess its usability in pediatric patients with either chronic kidney disease (CKD) or hypertension. Methods A total of 46 patients with CKD (group 1), 50 patients with hypertension (group 2), and 33 healthy participants as the control group were included. In all, we performed studies assessing their cardiovascular risk along with liver and kidney elastography. Results Liver elastography parameters were increased compared to those in the control group (1.49 m/s, p = 0.007, in group 1 and 1.52 m/s, p < 0.001, in group 2, vs. 1.41 m/s among controls). Kidney elastography parameters were significantly higher in group 2 (1.9 m/s, p = 0.001, and 1.9 m/s, p = 0.003, in each kidney) when compared to group 1 (1.79 m/s and 1.81 m/s). Additionally, all participants were divided according to overweight/obesity and normal weight status, where both liver (1.53 m/s vs. 1.45 m/s, p < 0.001) and kidney parameters (1.96 m/s and 1.92 m/s vs. 1.81 m/s and 1.84 m/s, p = 0.002) were significantly higher in the group of overweight/obese subjects. Conclusions Ultrasound elastography of the liver and kidney is feasible in pediatric patients with either CKD or hypertension, showing increased liver stiffness parameters in both groups, further aggravated by obesity. In obese patients with CKD, kidney stiffness also increased indicating a negative effect of clustering cardiovascular risk factors leading to decreased kidney elasticity. Further research is warranted. Graphical abstract A higher resolution version of the Graphical abstract is available as Supplementary information

Glomerular filtration rate (GFR) measurement is a key tool for determining the degree of chronic kidney disease. The assessment of GFR is even more challenging in children than in adults with more variables in the equation than race and sex. Monitoring the progress of the kidney disease can therefore be difficult as in the initial stages of a decline in kidney function, there are no clinical signs. Due to children’s growth and development, changes in muscle mass and growth impair GFR estimation based solely on serum creatinine values. More invasive methods of GFR measurement are more reliable, but techniques using ionising agents, requiring large volume blood samples or timed voiding, have limited application in children. This paper reviews the methods of measuring and determining glomerular filtration rate and kidney function in children.

(1) Background: The transition of children with chronic kidney disease to adult care has become a well-handled issue. However, other patients with normal or mildly decreased renal function also requiring further management and transition are neglected. (2) Methods: A questionnaire was sent to patients with kidney pathology, aged 17 years and older.(3) Results: The patients were mostly high-school (55%) or college students (39%), living with their parents (94%). One third did not know how their disease affected their choice of profession and reproductive health. Furthermore, 46% of the respondents did not know who would continue with their care, and 44% still had a primary pediatrician. (4) Conclusions: A review of the literature on the topic was performed and summarized here. Regular education is the key for successful transfer, not only in chronic kidney and transplant patients, but also in others in whom a decline in renal function can be expected in the future.

There is no evidence of the most effective nutritional screening tool for hospitalized children. The present study aimed to develop a quick, simple, and valid screening tool for identifying malnutrition risk of hospital admission with non-invasive indicators. A cross-sectional study was conducted. Children`s nutritional baseline using a questionnaire, subjective malnutritional risk, and Subjective Global Nutritional Assessment were assessed on admission. Concurrent validity was assessed using American Society for Parenteral and Enteral Nutrition (ASPEN)and Academy of Nutrition and Dietetics assessment and Subjective Global Nutritional Assessment tool. A new screening tool Simple Pediatric Nutritional risk Screening tool (SPENS) was developed, and sensitivity, specificity and reliability were evaluated. A total of 180 children aged from 1 month to 18 years were included (142 in the development phase and 38 in the validation phase). SPENS consist of four variables and shows almost perfect agreement with subjective malnutritional risk assessment (κ = 0.837) with high sensitivity and specificity (93.3% and 91.3% respectively). Compared with Subjective Global Nutritional Assessment and ASPEN and Academy of Nutrition and Dietetics assessment, SPENS had sensitivity 92.9% and 86.7%, a specificity of 87.5% and 87.0%, and an overall agreement of 0.78 and 0.728, respectively. Due to the fast, simple, easy, and practical to use, screening the SPENS can be performed by nurses, physicians, and dieticians.