Machine Learning Quantification of Pulmonary Regurgitation Fraction from Echocardiography.

Assessment of pulmonary regurgitation (PR) guides treatment for patients with congenital heart disease. Quantitative assessment of PR fraction (PRF) by echocardiography is limited. Cardiac MRI (cMRI) is the reference-standard for PRF quantification. We created an algorithm to predict cMRI-quantified PRF from echocardiography using machine learning (ML). We retrospectively performed echocardiographic measurements paired to cMRI within 3 months in patients with ≥ mild PR from 2009 to 2022. Model inputs were vena contracta ratio, PR index, PR pressure half-time, main and branch pulmonary artery diastolic flow reversal (BPAFR), and transannular patch repair. A gradient boosted trees ML algorithm was trained using k-fold cross-validation to predict cMRI PRF by phase contrast imaging as a continuous number and at > mild (PRF ≥ 20%) and severe (PRF ≥ 40%) thresholds. Regression performance was evaluated with mean absolute error (MAE), and at clinical thresholds with area-under-the-receiver-operating-characteristic curve (AUROC). Prediction accuracy was compared to historical clinician accuracy. We externally validated prior reported studies for comparison. We included 243 subjects (median age 21 years, 58% repaired tetralogy of Fallot). The regression MAE = 7.0%. For prediction of > mild PR, AUROC = 0.96, but BPAFR alone outperformed the ML model (sensitivity 94%, specificity 97%). The ML model detection of severe PR had AUROC = 0.86, but in the subgroup with BPAFR, performance dropped (AUROC = 0.73). Accuracy between clinicians and the ML model was similar (70% vs. 69%). There was decrement in performance of prior reported algorithms on external validation in our dataset. A novel ML model for echocardiographic quantification of PRF outperforms prior studies and has comparable overall accuracy to clinicians. BPAFR is an excellent marker for > mild PRF, and has moderate capacity to detect severe PR, but more work is required to distinguish moderate from severe PR. Poor external validation of prior works highlights reproducibility challenges.

Cardiac problems in the fetus: a review for pediatric providers.

PURPOSE OF REVIEW: The aim of this study was to provide pediatric providers with a review of the diagnosis and management of fetal cardiac disease in the current era. RECENT FINDINGS: Prenatal detection of congenital heart disease (CHD) has improved but is still imperfect. In experienced hands, fetal echocardiography can detect severe CHD as early as the first trimester and a majority of more subtle conditions in the second and third trimesters. Beyond detection, a prenatal diagnosis allows for lesion-specific counseling for families as well as for development of a multidisciplinary perinatal management plan, which may involve in-utero treatment. Given the diversity of cardiac diagnoses and the rarity of some, collaborative multicenter fetal cardiac research has gained momentum in recent years. SUMMARY: Accurate diagnosis of fetal cardiac disease allows for appropriate counseling, pregnancy and delivery planning, and optimization of immediate neonatal care. There is potential for improving fetal CHD detection rates. Fetal interventions are available for certain conditions, and fetal and pediatric cardiac centers have developed management plans specific to the expected postnatal physiology.

Evaluation of self-calibrated non-linear phase-contrast correction in pediatric and congenital cardiovascular magnetic resonance imaging.

BACKGROUND: The need for background error correction in phase-contrast flow analysis has historically posed a challenge in cardiac magnetic resonance (MR) imaging. While previous studies have shown that phantom correction improves flow measurements, it impedes scanner workflow. OBJECTIVE: To evaluate the efficacy of self-calibrated non-linear phase-contrast correction on flows in pediatric and congenital cardiac MR compared to phantom correction as the standard. MATERIALS AND METHODS: We retrospectively identified children who had great-vessel phase-contrast and static phantom sequences acquired between January 2015 and June 2015. We applied a novel correction method to each phase-contrast sequence post hoc. Uncorrected, non-linear, and phantom-corrected flows were compared using intraclass correlation. We used paired t-tests to compare how closely non-linear and uncorrected flows approximated phantom-corrected flows. In children without intra- or extracardiac shunts or significant semilunar valvular regurgitation, we used paired t-tests to compare how closely the uncorrected pulmonary-to-systemic flow ratio (Qp:Qs) and non-linear Qp:Qs approximated phantom-corrected Qp:Qs. RESULTS: We included 211 diagnostic-quality phase-contrast sequences (93 aorta, 74 main pulmonary artery [MPA], 21 left pulmonary artery [LPA], 23 right pulmonary artery [RPA]) from 108 children (median age 15 years, interquartile range 11-18 years). Intraclass correlation showed strong agreement between non-linear and phantom-corrected flow measurements but also between uncorrected and phantom-corrected flow measurements. Non-linear flow measurements did not more closely approximate phantom-corrected measurements than did uncorrected measurements for any vessel. In 39 children without significant shunting or regurgitation, mean non-linear Qp:Qs (1.07; 95% confidence interval [CI] = 1.01, 1.13) was no closer than mean uncorrected Qp:Qs (1.06; 95% CI = 1.00, 1.13) to mean phantom-corrected Qp:Qs (1.02; 95% CI = 0.98, 1.06). CONCLUSION: Despite strong agreement between self-calibrated non-linear and phantom correction, cardiac flows and shunt calculations with non-linear correction were no closer to phantom-corrected measurements than those without background correction. However, phantom-corrected flows also demonstrated minimal differences from uncorrected flows. These findings suggest that in the current era, more accurate phase-contrast flow measurements might limit the need for background correction. Further investigation of the clinical impact and optimal methods of background correction in the pediatric and congenital cardiac population is needed.

Hypoplastic Left Heart Syndrome: Exploring a Paradigm Shift in Favor of Surgery.

We hypothesized that enthusiasm for surgery increased for infants with hypoplastic left heart syndrome (HLHS) at Columbia University Medical Center (CUMC) between 1995 and 2012. We sought to identify factors that engendered this paradigm shift. Confidential surveys were distributed to providers at CUMC in 1995 and 2012 to measure enthusiasm for surgical intervention for HLHS. Surgical preference scores are presented as median [interquartile range]. Surveys were completed by 99/176 providers (56 % response rate) in 1995 and 153/267 (57 %) in 2012. The median surgical preference score for infants with HLHS increased from 35 [25-45] in 1995 to 45 [35-50] in 2012, P < 0.001. 53 %, 95 % CI [42, 64] of respondents recommended surgical intervention for a ward of the court in 1995 compared to 81 % [73, 89] in 2012, P < 0.001. In 2012, 64 % [53, 75] of respondents were more likely to recommend surgery than 10 years prior. The percentage of respondents who saw good outcomes following three-stage repair increased from 49 % [38, 60] in 1995 to 84 % [78, 90] in 2012, P < 0.001. The majority believed that parents should have the option of comfort care, 91 % [85, 97] in 1995 and 85 % [79, 91] in 2012, P = 0.06. In both eras, prematurity and additional surgical problems dissuaded providers from recommending surgical intervention. Despite the fact that most providers have seen good outcomes and now recommend surgery for infants with HLHS, the majority of providers still believe that the option of comfort care should be available to families.

Revisiting Wolff-Parkinson-White risk stratification: a malignant arrhythmia in a patient with intermittent pre-excitation.

It has been reported that the presence of intermittent pre-excitation indicates low risk of rapid conduction via the accessory pathway in atrial fibrillation. We report a case of a 10-year-old boy with a history of intermittent pre-excitation who presented with atrial fibrillation with very rapid conduction.

Impact of Social Determinants of Health on Predictive Models for Outcomes After Congenital Heart Surgery.

BACKGROUND: Despite documented associations between social determinants of health and outcomes post-congenital heart surgery, clinical risk models typically exclude these factors. OBJECTIVES: The study sought to characterize associations between social determinants and operative and longitudinal mortality as well as assess impacts on risk model performance. METHODS: Demographic and clinical data were obtained for all congenital heart surgeries (2006-2021) from locally held Congenital Heart Surgery Collaborative for Longitudinal Outcomes and Utilization of Resources Society of Thoracic Surgeons Congenital Heart Surgery Database data. Neighborhood-level American Community Survey and composite sociodemographic measures were linked by zip code. Model prediction, discrimination, and impact on quality assessment were assessed before and after inclusion of social determinants in models based on the 2020 Society of Thoracic Surgeons Congenital Heart Surgery Database Mortality Risk Model. RESULTS: Of 14,173 total index operations across New York State, 12,321 cases, representing 10,271 patients at 8 centers, had zip codes for linkage. A total of 327 (2.7%) patients died in the hospital or before 30 days, and 314 children died by December 31, 2021 (total n = 641; 6.2%). Multiple measures of social determinants of health explained as much or more variability in operative and longitudinal mortality than clinical comorbidities or prior cardiac surgery. Inclusion of social determinants minimally improved models' predictive performance (operative: 0.834-0.844; longitudinal 0.808-0.811), but significantly improved model discrimination; 10.0% more survivors and 4.8% more mortalities were appropriately risk classified with inclusion. Wide variation in reclassification was observed by site, resulting in changes in the center performance classification category for 2 of 8 centers. CONCLUSIONS: Although indiscriminate inclusion of social determinants in clinical risk modeling can conceal inequities, thoughtful consideration can help centers understand their performance across populations and guide efforts to improve health equity.

Atypical glomerulopathy associated with the cblE inborn error of vitamin B12 metabolism.

BACKGROUND: The cblE disorder is an inherited disorder of vitamin B12 metabolism that results in elevated levels of homocysteine and decreased methionine in body fluids. Renal complications have been reported in patients with cblC disease, but not in those with cblE disease. The renal complications of cblC disease include thrombotic microangiopathy (TMA), neonatal hemolytic uremic syndrome, chronic renal failure, tubulointerstitial nephritis and proximal renal tubular acidosis. Previously, we reported a patient with cblC disease who had an atypical glomerulopathy that manifested with proteinuria and progressive renal insufficiency. CASE-DIAGNOSIS/TREATMENT: Studies were done on cultured fibroblasts. Renal biopsy tissue was examined by light and electron microscopy. There was decreased incorporation of labeled methyltetrahydrofolate and decreased synthesis of methylcobalamin. Complementation analysis placed the patient into the cblE complementation group. The findings from the histological and ultrastructural studies of renal biopsy were similar, but not identical, to those of idiopathic membranoproliferative glomerulonephritis (MPGN) and overlapped with those of TMA. CONCLUSIONS: We describe a patient with cblE disease who had an atypical glomerulopathy similar to MPGN. Additional findings included migraine headaches, hypothyroidism and livedo reticularis.

Long-Term Health Care Utilization After Cardiac Surgery in Children Covered Under Medicaid.

BACKGROUND: Understanding the longitudinal burden of health care expenditures and utilization after pediatric cardiac surgery is needed to counsel families, improve care, and reduce outcome inequities. OBJECTIVES: The purpose of this study was to describe and identify predictors of health care expenditures and utilization for Medicaid-insured pediatric cardiac surgical patients. METHODS: All Medicaid enrolled children age <18 years undergoing cardiac surgery in the New York State CHS-COLOUR database, from 2006 to 2019, were followed in Medicaid claims data through 2019. A matched cohort of children without cardiac surgical disease was identified as comparators. Expenditures and inpatient, primary care, subspecialist, and emergency department utilization were modeled using log-linear and Poisson regression models to assess associations between patient characteristics and outcomes. RESULTS: In 5,241 New York Medicaid-enrolled children, longitudinal health care expenditures and utilization for cardiac surgical patients exceeded noncardiac surgical comparators (cardiac surgical children: $15,500 ± $62,000 per month in year 1 and $1,600 ± $9,100 per month in year 5 vs noncardiac surgical children: $700 ± $6,600 per month in year 1 and $300 ± $2,200 per month in year 5). Children after cardiac surgery spent 52.9 days in hospitals and doctors' offices in the first postoperative year and 90.5 days over 5 years. Being Hispanic, compared with non-Hispanic White, was associated with having more emergency department visits, inpatient admissions, and subspecialist visits in years 2 to 5, but fewer primary care visits and greater 5-year mortality. CONCLUSIONS: Children after cardiac surgery have significant longitudinal health care needs, even among those with less severe cardiac disease. Health care utilization differed by race/ethnicity, although mechanisms driving disparities should be investigated further.

Chronic Medication Burden After Cardiac Surgery for Pediatric Medicaid Beneficiaries.

BACKGROUND: Congenital heart defects are the most common and resource-intensive birth defects. As children with congenital heart defects increasingly survive beyond early childhood, it is imperative to understand longitudinal disease burden. OBJECTIVES: The purpose of this study was to examine chronic outpatient prescription medication use and expenditures for New York State pediatric Medicaid enrollees, comparing children who undergo cardiac surgery (cardiac enrollees) and the general pediatric population. METHODS: This was a retrospective cohort study of all Medicaid enrollees age <18 years using the New York State Congenital Heart Surgery Collaborative for Longitudinal Outcomes and Utilization of Resources database (2006-2019). Primary outcomes were total chronic medications per person-year, enrollees per 100 person-years using ≥1 and ≥3 medications, and medication expenditures per person-year. We described and compared outcomes between cardiac enrollees and the general pediatric population. Among cardiac enrollees, multivariable regression examined associations between outcomes and clinical characteristics. RESULTS: We included 5,459 unique children (32,131 person-years) who underwent cardiac surgery and 4.5 million children (22 million person-years) who did not. More than 4 in 10 children who underwent cardiac surgery used ≥1 chronic medication compared with approximately 1 in 10 children who did not have cardiac surgery. Medication expenditures were 10 times higher per person-year for cardiac compared with noncardiac enrollees. Among cardiac enrollees, disease severity was associated with chronic medication use; use was highest among infants; however, nearly one-half of adolescents used ≥1 chronic medication. CONCLUSIONS: Children who undergo cardiac surgery experience high medication burden that persists throughout childhood. Understanding chronic medication use can inform clinicians (both pediatricians and subspecialists) and policymakers, and ultimately the value of care for this medically complex population.

Risk Stratification for Congenital Heart Surgery for ICD-10 Administrative Data (RACHS-2).

BACKGROUND: As the cardiac community strives to improve outcomes, accurate methods of risk stratification are imperative. Since adoption of International Classification of Disease-10th Revision (ICD-10) in 2015, there is no published method for congenital heart surgery risk stratification for administrative data. OBJECTIVES: This study sought to develop an empirically derived, publicly available Risk Stratification for Congenital Heart Surgery (RACHS-2) tool for ICD-10 administrative data. METHODS: The RACHS-2 stratification system was iteratively and empirically refined in a training dataset of Pediatric Health Information Systems claims to optimize sensitivity and specificity compared with corresponding locally held Society of Thoracic Surgeons-Congenital Heart Surgery (STS-CHS) clinical registry data. The tool was validated in a second administrative data source: New York State Medicaid claims. Logistic regression was used to compare the ability of RACHS-2 in administrative data to predict operative mortality vs STAT Mortality Categories in registry data. RESULTS: The RACHS-2 system captured 99.6% of total congenital heart surgery registry cases, with 1.0% false positives. RACHS-2 predicted operative mortality in both training and validation administrative datasets similarly to STAT Mortality Categories in registry data. C-statistics for models for operative mortality in training and validation administrative datasets-adjusted for RACHS-2-were 0.76 and 0.84 (95% CI: 0.72-0.80 and 0.80-0.89); C-statistics for models for operative mortality-adjusted for STAT Mortality Categories-in corresponding clinical registry data were 0.75 and 0.84 (95% CI: 0.71-0.79 and 0.79-0.89). CONCLUSIONS: RACHS-2 is a risk stratification system for pediatric cardiac surgery for ICD-10 administrative data, validated in 2 administrative-registry-linked datasets. Statistical code is publicly available upon request.

Improving Longitudinal Outcomes, Efficiency, and Equity in the Care of Patients With Congenital Heart Disease.

BACKGROUND: Longitudinal follow-up, resource utilization, and health disparities are top congenital heart research and care priorities. Medicaid claims include longitudinal data on inpatient, outpatient, emergency, pharmacy, rehabilitation, home health utilization, and social determinants of health-including mother-infant pairs. OBJECTIVES: The New York Congenital Heart Surgeons Collaborative for Longitudinal Outcomes and Utilization of Resources linked robust clinical details from locally held state and national registries from 10 of 11 New York congenital heart centers to Medicaid claims, building a novel, statewide mechanism for longitudinal assessment of outcomes, expenditures, and health inequities. METHODS: The authors included all children <18 years of age undergoing cardiac surgery in The Society of Thoracic Surgeons Congenital Heart Surgery Database or the New York State Pediatric Congenital Cardiac Surgery Registry from 10 of 11 New York centers, 2006 to 2019. Data were linked via iterative, ranked deterministic matching on direct identifiers. Match rates were calculated and compared. Proportions of the linked cohort trackable over 3, 5, and 10 years were described. RESULTS: Of 14,097 registry cases, 59% (n = 8,322) reported Medicaid use. Of these, 7,414 were linked to New York claims, at an 89% match rate. Of matched cases, the authors tracked 79%, 74%, and 65% of children over 3, 5, and 10 years when requiring near-continuous Medicaid enrollment. Allowing more lenient enrollment criteria, the authors tracked 86%, 82%, and 76%, respectively. Mortality over this time was 7.7%, 8.4%, and 10.0%, respectively. Manual validation revealed ∼100% true matches. CONCLUSIONS: This establishes a novel statewide data resource for assessment of longitudinal outcome, health expenditure, and disparities for children with congenital heart disease.