Trends in Resources for Neonatal Intensive Care at Delivery Hospitals for Infants Born Younger Than 30 Weeks' Gestation, 2009-2020

Racial, ethnic, and socio-economic disparities in neonatal ICU admissions among neonates born with cyanotic CHD in the United States, 2009-2018

INTRODUCTION

Disparities in CHD outcomes exist across the lifespan. However, less is known about disparities for patients with CHD admitted to neonatal ICU. We sought to identify sociodemographic disparities in neonatal ICU admissions among neonates born with cyanotic CHD.

MATERIALS & METHODS

Annual natality files from the US National Center for Health Statistics for years 2009-2018 were obtained. For each neonate, we identified sex, birthweight, pre-term birth, presence of cyanotic CHD, and neonatal ICU admission at time of birth, as well as maternal age, race, ethnicity, comorbidities/risk factors, trimester at start of prenatal care, educational attainment, and two measures of socio-economic status (Special Supplemental Nutrition Program for Women, Infants, and Children [WIC] status and insurance type). Multivariable logistic regression models were fit to determine the association of maternal socio-economic status with neonatal ICU admission. A covariate for race/ethnicity was then added to each model to determine if race/ethnicity attenuate the relationship between socio-economic status and neonatal ICU admission.

RESULTS

Of 22,373 neonates born with cyanotic CHD, 77.2% had a neonatal ICU admission. Receipt of WIC benefits was associated with higher odds of neonatal ICU admission (adjusted odds ratio [aOR] 1.20, 95% CI 1.1-1.29, p < 0.01). Neonates born to non-Hispanic Black mothers had increased odds of neonatal ICU admission (aOR 1.20, 95% CI 1.07-1.35, p < 0.01), whereas neonates born to Hispanic mothers were at lower odds of neonatal ICU admission (aOR 0.84, 95% CI 0.76-0.93, p < 0.01).

CONCLUSION

Maternal Black race and low socio-economic status are associated with increased risk of neonatal ICU admission for neonates born with cyanotic CHD. Further work is needed to identify the underlying causes of these disparities.

Accurate prediction of neurologic changes in critically ill infants using pose AI

Importance

Infant alertness and neurologic changes are assessed by exam, which can be intermittent and subjective. Reliable, continuous methods are needed.

Objective

We hypothesized that our computer vision method to track movement, pose AI, could predict neurologic changes.

Design

Retrospective observational study from 2021-2022.

Setting

A level four urban neonatal intensive care unit (NICU).

Participants

Infants with corrected age ≤1 year, comprising 115 patients with 4,705 hours of video data linked to electroencephalograms (EEG), including 46% female and 25.2% white non-Hispanic.

Exposures

Pose AI prediction of anatomic landmark position and an XGBoost classifier trained on one-minute variance in pose.

Main outcomes and measures

Outcomes were cerebral dysfunction, diagnosed from EEG readings by an epileptologist, and sedation, defined by the administration of sedative medications. Measures of algorithm performance were receiver operating characteristic-area under the curves (ROC-AUCs) on cross-validation and on two test datasets comprised of held-out infants and held-out video frames from infants used in training.

Results

Infant pose was accurately predicted in cross-validation, held-out frames, and held-out infants (respective ROC-AUCs 0.94, 0.83, 0.89). Median movement increased with age and, after accounting for age, was lower with sedative medications and in infants with cerebral dysfunction (all P<5×10-3, 10,000 permutations). Sedation prediction had high performance on cross-validation, held-out frames, and held-out infants (ROC-AUCs 0.90, 0.91, 0.87), as did prediction of cerebral dysfunction (ROC-AUCs 0.91, 0.90, 0.76).

Conclusions and Relevance

We used pose AI to predict sedation and cerebral dysfunction in 4,705 hours of video from a large, diverse cohort of infants. Pose AI may offer a scalable, minimally invasive method for neuro-telemetry in the NICU.

Transfer Patterns Among Infants Born at 28 to 34 Weeks' Gestation

BACKGROUND

Although postnatal transfer patterns among high-risk (eg, extremely preterm or surgical) infants have been described, transfer patterns among lower-risk populations are unknown. The objective was to examine transfer frequency, indication, timing, and trajectory among very and moderate preterm infants.

METHODS

Observational study of the US Vermont Oxford Network all NICU admissions database from 2016 to 2021 of inborn infants 280/7 to 346/7 weeks. Infants' first transfer was assessed by gestational age, age at transfer, reason for transfer, and transfer trajectory.

RESULTS

Across 467 hospitals, 294 229 infants were eligible, of whom 12 552 (4.3%) had an initial disposition of transfer. The proportion of infants transferred decreased with increasing gestational age (9.6% [n = 1415] at 28 weeks vs 2.4% [n = 2646] at 34 weeks) as did the median age at time of transfer (47 days [interquartile range 30-73] at 28 weeks vs 8 days [interquartile range 3-16] at 34 weeks). The median post menstrual age at transfer was 34 or 35 weeks across all gestational ages. The most common reason for transfer was growth or discharge planning (45.0%) followed by medical and diagnostic services (30.2%), though this varied by gestation. In this cohort, 42.7% of transfers were to a higher-level unit, 10.2% to a same-level unit, and 46.7% to a lower-level unit, with indication reflecting access to specific services.

CONCLUSIONS

Over 4% of very and moderate preterm infants are transferred. In this population, the median age of transfer is later and does not reflect immediate care needs after birth, but rather the provision of risk-appropriate care.