Newborn Pulse Oximetry for Infants Born Out-of-Hospital

Newborn Screening for Critical Congenital Heart Disease: A New Algorithm and Other Updated Recommendations: Clinical Report

Critical congenital heart disease (CCHD) screening was added to the US Recommended Uniform Screening Panel in 2011 and adopted by all US states and territories by 2018. In addition to reviewing key developments in CCHD screening since the initial American Academy of Pediatrics (AAP) endorsement in 2011, this clinical report provides 3 updated recommendations. First, a new AAP algorithm has been endorsed for use in CCHD screening. Compared with the original AAP algorithm from 2011, this new algorithm a) has a passing oxygen saturation threshold of ≥95% in both pre- and post-ductal measurements; and b) has only 1 retest instead of 2 for infants who did not pass the first screen. Second, to continue to improve screening, state newborn screening programs should collect a recommended minimum uniform dataset to aid in surveillance and monitoring of the program. Finally, stakeholders should be educated on the limitations of screening, the significance of non-CCHD conditions, and the importance of protocol adherence. Future directions of CCHD screening include improving overall sensitivity and implementing methods to reduce health inequities. It will remain critical that the AAP and its chapters and members work with health departments and hospitals to achieve awareness and implementation of these recommendations.

Can machine learning methods be used for identification of at-risk neonates in low-resource settings? A prospective cohort study

INTRODUCTION

Timely identification of at-risk neonates (ARNs) in the community is essential to reduce mortality in low-resource settings. Tools such as American Academy of Pediatrics pulse oximetry (POx) and WHO Young Infants Clinical Signs (WHOS) have high specificity but low sensitivity to identify ARNs. Our aim was assessing the value of POx and WHOS independently, in combination and with machine learning (ML) from clinical features, to detect ARNs in a low/middle-income country.

METHODS

This prospective cohort study was conducted in a periurban community in Pakistan. Eligible live births were screened using WHOS and POx along with clinical information regarding pregnancy and delivery. The enrolled neonates were followed for 4 weeks of life to assess the vital status. The predictive value to identify ARNs, of POx, WHOS and an ML model using maternal and neonatal clinical features, was assessed.

RESULTS

Of 1336 neonates, 68 (5%) had adverse outcomes, that is, sepsis (n=40, 59%), critical congenital heart disease (n=2, 3%), severe persistent pulmonary hypertension (n=1), hospitalisation (n=8, 12%) and death (n=17, 25%) assessed at 4 weeks of life. Specificity of POx and WHOS to independently identify ARNs was 99%, with sensitivity of 19% and 63%,respectively. Combining both improved sensitivity to 70%, keeping specificity at 98%. An ML model using clinical variables had 44% specificity and 76% sensitivity. A staged assessment, where WHOS, POx and ML are sequentially used for triage, increased sensitivity to 85%, keeping specificity 75%. Using ML (when WHOS and POx negative) for community follow-up detected the majority of ARNs.

CONCLUSION

Classic screening, combined with ML, can help maximise identifying ARNs and could be embedded in low-resource clinical settings, thereby improving outcome. Sequential use of classic assessment and clinical ML identifies the most ARNs in the community, still optimising follow-up clinical care.

Providers' Attitudes to Proposed Changes in the Critical Congenital Heart Disease Screening Algorithm

Screening for critical congenital heart disease (CCHD) in newborns based on a 2009 Swedish study has become the standard of care despite the complexity of the algorithm. A simplified algorithm which might increase the false-positive rate was proposed in 2020 but not formally endorsed by the American Academy of Pediatrics. We sought to determine how the current protocol and the proposed changes are perceived by clinicians. We performed an anonymous survey of professionals involved in the care of newborns regarding their perception of the current and proposed CCHD screening algorithms. 335 responses were evaluated. Less than 2% of respondents were dissatisfied with the existing screening algorithm or felt it was difficult to perform. 47% endorsed and 12% opposed the adoption of the proposed modifications with those most familiar with the proposed changes more likely to endorse them. Although many providers would accept a higher false-positive rate in CCHD screening, those who would have to transfer a baby from the birth site for assessment after a failed CCHD screening were less tolerant of an increased false-positive rate. Although the existing CCHD screening mechanisms appear to be very well received, the proposed changes to the CCHD algorithm were viewed positively by many respondents. Changes in this algorithm would likely be better tolerated in those setting where the consequences of a failed CCHD screening are more easily addressed.