Aim: To systematically summarise the current evidence of employing clinical decision support algorithms (CDSAs) using non-invasive parameters for sepsis prediction in neonates. Methods: A comprehensive search in PubMed, CENTRAL and EMBASE was conducted. Screening, data extraction and risk of bias were performed by two authors. The certainty of the evidence was assessed using GRADE. PROSPERO ID: CRD42020205143. Results: After abstract and full-text screening, 36 studies comprising 18,096 infants were included. Most CDSAs evaluated heart rate (HR)-based parameters. Two publications derived from one randomised-controlled trial assessing HR characteristics reported significant reduction in 30-day septicaemia-related mortality. Thirty-four non-randomised studies found promising yet inconclusive results. Conclusion: Heart rate-based parameters are reliable components of CDSAs for sepsis prediction, particularly in combination with additional vital signs and demographics. However, inconclusive evidence and limited standardisation restricts clinical implementation of CDSAs outside of a controlled research environment. Further experimentation and comparison of parameter combinations and testing of new CDSAs are warranted.

No abstract

<p> In this original study, we investigate the performances of machine learning algorithms on a neonatal sepsis detection task. We consider this work to be of great interest to both engineers and clinicians, as it uses non-invasive, already existing, vital signs monitoring signals in a population of very low birth weight infants at high risk of sepsis. Vital sign variability may indeed represent a general indicator of health and wellbeing and be helpful in the early detection of systematic inflammation such as sepsis. We used state of the art feature extraction technics and evaluate a large variety of binary classification models among which a neural network based generative model. The models were chosen from two main families: discriminative and generative. This enables a comprehensive study of different kinds of traditional and advanced binary classification algorithms.</p> <p> Our study reveals that advanced machine learning models are more robust to changes in the feature extraction pipeline, although linear classifiers have a comparable performance when the feature extraction is tuned. The advanced model performing the best is a neural network based generative model which is a hybrid generative and discriminative model. A large window length when computing the features is beneficial to almost all algorithms, indicating the relevance of frequency domain related features for the neonatal sepsis detection task.</p> <p> Overall we obtain a classification AUROC above 0.85, which makes our prediction models potentially relevant in clinical practice. This will enable earlier therapeutic interventions and thereby reduce morbidity and mortality in infants.</p>

No abstract

Nitrogen multiple-breath washout (N2MBW) is increasingly used in patients with cystic fibrosis. The current European Respiratory Society/American Thoracic Society consensus statement for MBW recommends the rejection of measurements with leaks. However, it is unclear whether this is necessary for all types of leaks. Here, our aim was to 1) model and 2) apply air leaks, and 3) to assess their influence on the primary MBW outcomes of lung clearance index and functional residual capacity.We investigated the influence of air leaks at various locations (pre-, intra- and post-capillary), sizes, durations and stages of the washout. Modelled leaks were applied to existing N2MBW data from 10 children by modifying breath tables. In addition, leaks were applied to the equipment during N2MBW measurements performed by one healthy adolescent.All modelled and applied leaks resulted in statistically significant but heterogeneous effects on lung clearance index and functional residual capacity. In all types of continuous inspiratory leaks exceeding a certain size, the end of the washout was not reached. For practical application, we illustrated six different “red flags”, i.e. signs that enable easy identification of leaks during measurements.Air leaks during measurement significantly influence N2MBW outcomes. The influence of leaks on MBW outcomes is dependent on the location, relation to breath cycle, duration, stage of washout and size of the leak. We identified a range of signs to help distinguish leaks from physiological noise.

In infants, the diagnostic performance of MBW strongly depends on the point of analysis. The cut-off with the highest discriminative power to detect ventilation inhomogeneity in infants with cystic fibrosis and after preterm birth was at 1.5% tracer gas concentration. Pediatr Pulmonol. 2016;51:1373-1381. © 2016 Wiley Periodicals, Inc.

Limited evidence of low-to-moderate quality suggests that prophylactic administration of oral beta-blockers might reduce progression towards stage 3 ROP and decrease the need for anti-VEGF agents or laser therapy. The clinical relevance of those findings is unclear as no data on long-term visual impairment were reported. Adverse events attributed to oral propranolol at a dose of 2 mg/kg/d raise concerns regarding systemic administration of this drug for prevention of ROP at the given dose. There is insufficient evidence to determine the efficacy and safety of beta-blockers for prevention of ROP due to high risk of bias in two included trials and the lack of long-term functional outcomes. We would encourage researchers to conduct large, well-designed trials to confirm or refute the role of beta-blockers for prevention and treatment of ROP in preterm infants. Trials should report on long-term visual impairment. Researchers should consider dose-finding studies of systemic beta-blockers and topical administration of beta-blockers, in order to optimise drug delivery and minimise adverse events.

No abstract