Neonatal sepsis prediction through clinical decision support algorithms: A systematic review

Abstract

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.

Infectious aetiologies of neonatal illness in south Asia classified using WHO definitions: a primary analysis of the ANISA study

“…Research suggests that biomarkers (such as C-reactive protein and certain toll-like receptors 28 ), and new metagenomic sequencing to rapidly identify pathogens from normally sterile fluids, could help to diagnose infection. New neonatal sepsis predictive algorithm tools have also been developed, 29 , 30 , 31 but it is unlikely that physicians would have this information or technology available in low-resource public health settings.…”

Classification and feature extraction for neonatal sepsis detection

“…a) Logistic regression (LR): Logistic regression (LR) is a model that is often used for neonatal sepsis prediction algorithms [20]. LR models the relationship between x and it's label using a sigmoid function and a weighted sum of the components in x.…”

“…The interpretability of prediction algorithms is often required by clinicians to motivate their actions based upon a classification result [19]. This often leads to the choice of linear prediction algorithms to build feature based classifiers [20]. Linear prediction algorithms can yield an importance score for each input feature which directly explains the classification result to clinicians [14], [15].…”

Issue highlights December 2021

“…Persad et al evaluated the use of clinical decision support algorithms that assess non‐invasive parameters to predict neonatal sepsis 8 . Their systematic review indicated that heart rate‐based parameters were reliable components of clinical decision support algorithms that predicted sepsis, particularly when they were combined with other vital signs and demographics.…”