The corrected blood urea nitrogen predicts the developmental quotient of extremely low-birth-weight infants at the corrected age of 36 months

Development and validation of machine learning-based clinical decision support tool for identifying malnutrition in NICU patients

Hospitalized newborns have an increased risk of malnutrition and, especially preterm infants, often experience malnutrition-related extrauterine growth restriction (EUGR). The aim of this study was to predict the discharge weight and the presence of weight gain at discharge with machine learning (ML) algorithms. The demographic and clinical parameters were used to develop the models using fivefold cross-validation in the software-R with a neonatal nutritional screening tool (NNST). A total of 512 NICU patients were prospectively included in the study. Length of hospital stay (LOS), parenteral nutrition treatment (PN), postnatal age (PNA), surgery, and sodium were the most important variables in predicting the presence of weight gain at discharge with a random forest classification (AUROC:0.847). The AUROC of NNST-Plus, which was improved by adding LOS, PN, PNA, surgery, and sodium to NNST, increased by 16.5%. In addition, weight at admission, LOS, gestation-adjusted age at admission (> 40 weeks), sex, gestational age, birth weight, PNA, SGA, complications of labor and delivery, multiple birth, serum creatinine, and PN treatment were the most important variables in predicting discharge weight with an elastic net regression (R² = 0.748). This is the first study on the early prediction of EUGR with promising clinical performance based on ML algorithms. It is estimated that the incidence of EUGR can be improved with the implementation of this ML-based web tool ( http://www.softmed.hacettepe.edu.tr/NEO-DEER/ ) in clinical practice.

Renal function in the third year among very low birth weight infants fed by supplemental proteins

Very Low Birth Weight (VLBW) infants have higher nutritional needs than term infants. Energy and protein are two important factors influencing their growth. Breastfeeding is not enough to meet VLBW infants' needs, for this reason, complementary protein is required by them. Hence, the present study aimed at investigation of renal function among VLBW infants receiving complementary proteins. The study was conducted on two groups of intervention and control (n= 18 in each group) (Case study: VLBW infants born in Akbarabadi hospital of Tehran in 2014 2015). The intervention group includes 3-year-old children who weighting less than 1200 grams at birth and have received protein supplementation at the course of NICU hospitalization, protein was added to maternal milk when the amount of milk reaches to 100 cc/kg/day, at this time parenteral nutrition was discontinued and the volume of feeding was increased 20cc/kg/day until reached to 150-180cc/kg/day. We also added the fortifier to breast milk at this time. The fortification and the protein supplementation were stopped when the weight of the baby reached to 1500 grams. The control group was fed similar to the intervention group but had received no complementary protein . The renal function was evaluated by measuring such criteria as BUN, Cr, ALB and U/A. After data collection, a statistical analysis was performed using SPSS software Ver. 22. Following to BUN evaluation, a significant correlation was seen between BUN and received protein (p-value=0.010). However, there was no significant correlation between Cr and received protein as well as mean values of the two groups (p-value=0.0766). Similarly, an insignificant correlation was found between the two groups following to investigation of ALB (p-value=0/257), while the mean values of the two groups were similar. The both groups were also equal in U/A. The complementary protein increased the BUN with no effect on Cr, ALB and U/A, providing no impact on renal function. Therefore, complementary protein intake made no conflict in renal function.

Bedside analysis of human milk for adjustable nutrition strategy

AIM

Mother's milk is optimum for preterm infants, but human milk fortifier is required at times, because some nutrients are sometimes insufficient for infant growth. It is important to measure the nutrients in breast milk at bedside so that the amount of nutrients that need to be supplemented can be determined. A human milk analyser (HMA, Miris) is currently available. We examined if the macronutrient values measured by human milk analyser are comparable with those measured by conventional methods. We also sought to discover whether we could dilute the milk sample used for the human milk analyser measurement if the amount of milk available for testing was insufficient.

SUBJECTS AND METHODS

First, the results of protein, fat and lactose content in breast milk samples obtained using the human milk analyser and conventional methods were compared. Second, we measured diluted samples and compared the values with nondiluted samples.

RESULTS

When comparing the human milk analyser and conventional methods, all three nutrients exhibited a significantly positive correlation (p < 0.001); lactose content was reliable on the condition that it is 6-7 g/dL. The lactose content measured by the HPLC method was obtained by 3.05 x human milk analyser value - 13.4. When comparing diluted and nondiluted samples, fat and protein had expected values after dilution whereas lactose did not.

CONCLUSION

The human milk analyser can inform us about the amount of major nutrients in breast milk: fat, protein and lactose. However, when human milk is diluted, the lactose content measured by the human milk analyser is overestimated.