Fetal circulatory physiology and brain development in complex congenital heart disease: A multi-modal imaging study.

OBJECTIVE: Fetuses with complex congenital heart disease have altered physiology, contributing to abnormal neurodevelopment. The effects of altered physiology on brain development have not been well studied. We used multi-modal imaging to study fetal circulatory physiology and brain development in hypoplastic left heart syndrome (HLHS) and d-transposition of the great arteries (TGA). METHODS: This prospective, cross-sectional study investigated individuals with fetal congenital heart disease and controls undergoing fetal echocardiography and fetal brain MRI. MRI measured total brain volume and cerebral oxygenation by the MRI quantification method T2*. Indexed cardiac outputs (CCOi) and vascular impedances were calculated by fetal echocardiography. Descriptive statistics assessed MRI and echocardiogram measurement relationships by physiology. RESULTS: Sixty-six participants enrolled (control = 20; HLHS = 25; TGA = 21), mean gestational age 33.8 weeks (95% CI: 33.3-34.2). Total brain volume and T2* were significantly lower in fetuses with cardiac disease. CCOi was lower in HLHS, correlating with total brain volume - for every 10% CCOi increase, volume increased 8 mm3 (95% CI: 1.78-14.1; p = 0.012). Echocardiography parameters and cerebral oxygenation showed no correlation. TGA showed no CCOi or aortic output correlation with MRI measures. CONCLUSIONS: In HLHS, lower cardiac output is deleterious to brain development. Our findings provide insight into the role of fetal cardiovascular physiology in brain health.

Enhanced Critical Congenital Cardiac Disease Screening by Combining Interpretable Machine Learning Algorithms.

Critical Congenital Heart Disease (CCHD) screening that only uses oxygen saturation (SpO2), measured by pulse oximetry, fails to detect an estimated 900 US newborns annually. The addition of other pulse oximetry features such as perfusion index (PIx), heart rate, pulse delay and photoplethysmography characteristics may improve detection of CCHD, especially those with systemic blood flow obstruction such as Coarctation of the Aorta (CoA). To comprehensively study the most relevant features associated with CCHD, we investigated interpretable machine learning (ML) algorithms by using Recursive Feature Elimination (RFE) to identify an optimal subset of features. We then incorporated the trained ML models into the current SpO2-alone screening algorithm. Our proposed enhanced CCHD screening system, which adds the ML model, improved sensitivity by approximately 10 percentage points compared to the current standard SpO2-alone method with minimal to no impact on specificity.Clinical relevance- This establishes proof of concept for a ML algorithm that combines pulse oximetry features to improve detection of CCHD with little impact on false positive rate.

Comparison of Management Strategies for Neonates With Symptomatic Tetralogy of Fallot.

BACKGROUND: Neonates with tetralogy of Fallot and symptomatic cyanosis (sTOF) require early intervention. OBJECTIVES: This study sought to perform a balanced multicenter comparison of staged repair (SR) (initial palliation [IP] and subsequent complete repair [CR]) versus primary repair (PR) treatment strategies. METHODS: Consecutive neonates with sTOF who underwent IP or PR at ≤30 days of age from 2005 to 2017 were retrospectively reviewed from the Congenital Cardiac Research Collaborative. The primary outcome was death. Secondary outcomes included component (IP, CR, PR) and cumulative (SR): hospital and intensive care unit lengths of stay; durations of cardiopulmonary bypass, anesthesia, ventilation, and inotrope use; and complication and reintervention rates. Outcomes were compared using propensity score adjustment. RESULTS: The cohort consisted of 342 patients who underwent SR (IP: surgical, n = 256; transcatheter, n = 86) and 230 patients who underwent PR. Pre-procedural ventilation, prematurity, DiGeorge syndrome, and pulmonary atresia were more common in the SR group (p ≤0.01). The observed risk of death was not different between the groups (10.2% vs 7.4%; p = 0.25) at median 4.3 years. After adjustment, the hazard of death remained similar between groups (hazard ratio: 0.82; 95% confidence interval: 0.49 to 1.38; p = 0.456), but it favored SR during early follow-up (<4 months; p = 0.041). Secondary outcomes favored the SR group in component analysis, whereas they largely favored PR in cumulative analysis. Reintervention risk was higher in the SR group (p = 0.002). CONCLUSIONS: In this multicenter comparison of SR or PR for management of neonates with sTOF, adjusted for patient-related factors, early mortality and neonatal morbidity were lower in the SR group, but cumulative morbidity and reinterventions favored the PR group, findings suggesting potential benefits to each strategy.