Validating the early phototherapy prediction tool across cohorts.

Background: Hyperbilirubinemia of the newborn infant is a common disease worldwide. However, recognized early and treated appropriately, it typically remains innocuous. We recently developed an early phototherapy prediction tool (EPPT) by means of machine learning (ML) utilizing just one bilirubin measurement and few clinical variables. The aim of this study is to test applicability and performance of the EPPT on a new patient cohort from a different population. Materials and methods: This work is a retrospective study of prospectively recorded neonatal data from infants born in 2018 in an academic hospital, Regensburg, Germany, meeting the following inclusion criteria: born with 34 completed weeks of gestation or more, at least two total serum bilirubin (TSB) measurement prior to phototherapy. First, the original EPPT-an ensemble of a logistic regression and a random forest-was used in its freely accessible version and evaluated in terms of the area under the receiver operating characteristic curve (AUROC). Second, a new version of the EPPT model was re-trained on the data from the new cohort. Third, the predictive performance, variable importance, sensitivity and specificity were analyzed and compared across the original and re-trained models. Results: In total, 1,109 neonates were included with a median (IQR) gestational age of 38.4 (36.6-39.9) and a total of 3,940 bilirubin measurements prior to any phototherapy treatment, which was required in 154 neonates (13.9%). For the phototherapy treatment prediction, the original EPPT achieved a predictive performance of 84.6% AUROC on the new cohort. After re-training the model on a subset of the new dataset, 88.8% AUROC was achieved as evaluated by cross validation. The same five variables as for the original model were found to be most important for the prediction on the new cohort, namely gestational age at birth, birth weight, bilirubin to weight ratio, hours since birth, bilirubin value. Discussion: The individual risk for treatment requirement in neonatal hyperbilirubinemia is robustly predictable in different patient cohorts with a previously developed ML tool (EPPT) demanding just one TSB value and only four clinical parameters. Further prospective validation studies are needed to develop an effective and safe clinical decision support system.

Nutritional interventions to reduce rates of infection, necrotizing enterocolitis and mortality in very preterm infants.

Observational studies demonstrating reduced rates of infections, necrotizing enterocolitis (NEC), and mortality in preterm infants fed their own mother's milk, as opposed to formula, have prompted endeavors to achieve similar effects with the right choice of food and food additives. In a systematic review of meta-analyses and randomized controlled trials (RCTs), we considered nutritional interventions aimed at reducing the rates of infections, NEC, or mortality in very preterm infants. The overall effects of particular interventions were presented as risk ratios with 95% confidence intervals. In RCTs, pasteurized human donor milk, as opposed to formula, reduced NEC but not infections or mortality. No differences emerged between infants receiving human or bovine milk-based fortifiers. Pooled data of small trials and a recent large RCT suggested that bovine lactoferrin reduced rates of fungal sepsis without impact on other infections, NEC, or mortality. Pooled data of RCTs assessing the use of prebiotic oligosaccharides found reduced infection but not mortality. Enteral L-glutamine (six RCTs) lowered infection rates, and enteral L-arginine (three RCTs) reduced NEC. A meta-analysis sensitivity approach found multiple-strain (but not single-strain) probiotics to be highly effective in reducing NEC and mortality. Thus, selected food components may help to improve outcomes in preterm infants.

Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning.

BACKGROUND: Machine learning models may enhance the early detection of clinically relevant hyperbilirubinemia based on patient information available in every hospital. METHODS: We conducted a longitudinal study on preterm and term born neonates with serial measurements of total serum bilirubin in the first two weeks of life. An ensemble, that combines a logistic regression with a random forest classifier, was trained to discriminate between the two classes phototherapy treatment vs. no treatment. RESULTS: Of 362 neonates included in this study, 98 had a phototherapy treatment, which our model was able to predict up to 48 h in advance with an area under the ROC-curve of 95.20%. From a set of 44 variables, including potential laboratory and clinical confounders, a subset of just four (bilirubin, weight, gestational age, hours since birth) suffices for a strong predictive performance. The resulting early phototherapy prediction tool (EPPT) is provided as an open web application. CONCLUSION: Early detection of clinically relevant hyperbilirubinemia can be enhanced by the application of machine learning. Existing guidelines can be further improved to optimize timing of bilirubin measurements to avoid toxic hyperbilirubinemia in high-risk patients while minimizing unneeded measurements in neonates who are at low risk.