Identifying High-risk Fontan Phenotypes Using K-means Clustering of CMR-based Dyssynchrony Metrics.

BACKGROUND: Individuals with a Fontan circulation encompass a heterogenous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiac magnetic resonance (CMR)-derived dyssynchrony metrics can separate ventricles in the Fontan circulation from normal control left ventricles and identify prognostically distinct subgroups within the Fontan cohort. MATERIALS AND METHODS: This single-center, retrospective study used 503 CMR studies from Fontan patients (median age 15y) and 42 from age-matched controls from January 2005 to May 2011. Feature tracking on short-axis cine stacks assessed radial and circumferential strain, strain rate, and displacement. Unsupervised K-means clustering was applied to 24 mechanical dyssynchrony metrics derived from these deformation measurements. Clusters were compared for demographic, anatomical, and composite outcome of death, or heart transplantation. RESULTS: Four distinct phenotypic clusters were identified. Over a median follow-up of 4.2y (IQR 1.7-8.8y), 58 (11.5%) patients met the composite outcome. The highest risk cluster (largely comprised of right or mixed ventricular morphology and dilated, dyssynchronous ventricles) exhibited a higher hazard for the composite outcome compared to the lowest-risk cluster while controlling for ventricular morphology (HR 6.4; 95% CI 2.1-19.3; P value 0.001) and higher indexed end-diastolic volume (HR 3.2; 95% CI 1.04-10.0; P value 0.043) per 10ml/m2. CONCLUSIONS: Unsupervised machine learning using CMR-derived dyssynchrony metrics identified four distinct clusters of patients with Fontan circulation and healthy controls with varying clinical characteristics and risk profiles. This technique can be used to guide future studies and identify more homogeneous subsets of patients from an overall heterogeneous population.

Mitral valve orifice area predicts outcome after biventricular repair in patients with hypoplastic left ventricles.

BACKGROUND: Identification of risk factors for biventricular (BiV) repair in children with hypoplastic left ventricles (HLV) has been challenging. We sought to identify preoperative cardiovascular magnetic resonance (CMR) predictors of outcome in patients with HLVs who underwent BiV repair, with a focus on the mitral valve (MV). METHODS: Single-center retrospective analysis of preoperative CMRs on patients with HLV (≤50 mL/m2) and no endocardial fibroelastosis who underwent BiV repair from 2005-2022. CMR measurements included MV orifice area in diastole. The primary composite outcome included time to death, transplant, BiV takedown, heart failure admission, left atrial decompression, or unexpected reoperation; and the secondary outcome included more than or equal to moderate mitral stenosis and/or regurgitation. RESULTS: Median follow-up was 0.7 (interquartile range 0.1, 2.2) years. Of 122 patients [59 atrioventricular canal (AVC) and 63 non-AVC] age 3 ± 2.8 years at the time of BiV repair, freedom from the primary outcome at 2 years was 53% for AVC and 69% for non-AVC (log rank p = 0.12), and freedom from the secondary outcome at 2 years was 49% for AVC and 79% for non-AVC (log rank p < 0.01). Independent predictors of primary outcome for AVC patients included MV orifice area z-score <-2 and transitional AVC; for non-AVC patients, predictors included MV orifice area z-score <-2, abnormal MV anatomy, and conal-septal ventricular septal defect. Independent predictors of secondary outcome for AVC patients included older age at surgery, transitional AVC, and transposition of the great arteries. CONCLUSION: In children with HLV, low MV orifice area and pre-existing MV pathology are risk factors for adverse outcome after BiV repair.

Ventricular dyssynchrony late after the Fontan operation is associated with decreased survival.

BACKGROUND: Ventricular dyssynchrony and its relationship to clinical outcomes is not well characterized in patients following Fontan palliation. METHODS: Single-center retrospective analysis of cardiac magnetic resonance (CMR) imaging of patients with a Fontan circulation and an age-matched healthy comparison cohort as controls. Feature tracking was performed on all slices of a ventricular short-axis cine stack. Circumferential and radial strain, strain rate, and displacement were measured; and multiple dyssynchrony metrics were calculated based on timing of these measurements (including standard deviation of time-to-peak, maximum opposing wall delay, and maximum base-to-apex delay). Primary endpoint was a composite measure including time to death, heart transplant or heart transplant listing (D/HTx). RESULTS: A total of 503 cases (15 y; IQR 10, 21) and 42 controls (16 y; IQR 11, 20) were analyzed. Compared to controls, Fontan patients had increased dyssynchrony metrics, longer QRS duration, larger ventricular volumes, and worse systolic function. Dyssynchrony metrics were higher in patients with right ventricular (RV) or mixed morphology compared to those with LV morphology. At median follow-up of 4.3 years, 11% had D/HTx. Multiple risk factors for D/HTx were identified, including RV morphology, ventricular dilation, dysfunction, QRS prolongation, and dyssynchrony. Ventricular dilation and RV morphology were independently associated with D/HTx. CONCLUSIONS: Compared to control LVs, single right and mixed morphology ventricles in the Fontan circulation exhibit a higher degree of mechanical dyssynchrony as evaluated by CMR-FT. Dyssynchrony indices correlate with ventricular size and function and are associated with death or need for heart transplantation. These data add to the growing understanding regarding factors that can be used to risk-stratify patients with the Fontan circulation.

Cardiac arrest and cardiopulmonary resuscitation in pediatric patients with cardiac disease: a narrative review.

Children with cardiac disease are at a higher risk of cardiac arrest as compared to healthy children. Delivering adequate cardiopulmonary resuscitation (CPR) can be challenging due to anatomic characteristics, risk profiles, and physiologies. We aimed to review the physiological aspects of resuscitation in different cardiac physiologies, summarize the current recommendations, provide un update of current literature, and highlight knowledge gaps to guide research efforts. We specifically reviewed current knowledge on resuscitation strategies for high-risk categories of patients including patients with single-ventricle physiology, right-sided lesions, right ventricle restrictive physiology, left-sided lesions, myocarditis, cardiomyopathy, pulmonary arterial hypertension, and arrhythmias. Cardiac arrest occurs in about 1% of hospitalized children with cardiac disease, and in 5% of those admitted to an intensive care unit. Mortality after cardiac arrest in this population remains high, ranging from 30 to 65%. The neurologic outcome varies widely among studies, with a favorable neurologic outcome at discharge observed in 64%-95% of the survivors. Risk factors for cardiac arrest and associated mortality include younger age, lower weight, prematurity, genetic syndrome, single-ventricle physiology, arrhythmias, pulmonary arterial hypertension, comorbidities, mechanical ventilation preceding cardiac arrest, surgical complexity, higher vasoactive-inotropic score, and factors related to resources and institutional characteristics. Recent data suggest that Extracorporeal membrane oxygenation CPR (ECPR) may be a valid strategy in centers with expertise. Overall, knowledge on resuscitation strategies based on physiology remains limited, with a crucial need for further research in this field. Collaborative and interprofessional studies are highly needed to improve care and outcomes for this high-risk population. What is Known: • Children with cardiac disease are at high risk of cardiac arrest, and cardiopulmonary resuscitation may be challenging due to unique characteristics and different physiologies. • Mortality after cardiac arrest remains high and neurologic outcomes suboptimal. What is New: • We reviewed the unique resuscitation challenges, current knowledge, and recommendations for different cardiac physiologies. • We highlighted knowledge gaps to guide research efforts aimed to improve care and outcomes in this high-risk population.

Nucleated Red Blood Cells Are Predictive of In-Hospital Mortality for Pediatric Patients.

PURPOSE: We sought to establish whether nucleated red blood cells (NRBCs) are predictive of disposition, morbidity, and mortality for pediatric patients presenting to the emergency department (ED). METHODS: A single-center retrospective cohort study examining all ED encounters from patients aged younger than 19 years between January 2016 and March 2020, during which a complete blood count was obtained. Univariate analysis and multivariable logistic regression were used to test the presence of NRBCs as an independent predictor of patient-related outcomes. RESULTS: The prevalence of NRBCs was 8.9% (4195/46,991 patient encounters). Patient with NRBCs were younger (median age 4.58 vs 8.23 years; P < 0.001). Those with NRBCs had higher rates of in-hospital mortality (30/2465 [1.22%] vs 65/21,741 [0.30%]; P < 0.001), sepsis (19% vs 12%; P < 0.001), shock (7% vs 4%; P < 0.001), and cardiopulmonary resuscitation (CPR) (0.62% vs 0.09%; P < 0.001). They were more likely to be admitted (59% vs 51%; P < 0.001), have longer median hospital length of stay {1.3 (interquartile range [IQR], 0.22-4.14) vs 0.8 days (IQR, 0.23-2.64); P < 0.001}, and median intensive care unit (ICU) length of stay (3.9 [IQR, 1.87-8.72] vs 2.6 days [IQR, 1.27-5.83]; P < 0.001). Multivariable regression revealed presence of NRBCs as an independent predictor for in-hospital mortality (adjusted odds ratio [aOR], 2.21; 95% confidence interval [CI], 1.38-3.53; P < 0.001), ICU admission (aOR, 1.30; 95% CI, 1.11-1.51; P < 0.001), CPR (aOR, 3.83; 95% CI, 2.33-6.30; P < 0.001), and 30-day return to the ED (aOR, 1.15; 95% CI, 1.15-1.26; P < 0.001). CONCLUSIONS: The presence of NRBCs is an independent predictor for mortality, including in-hospital mortality, ICU admission, CPR, and readmission within 30 days for children presenting to the ED.

A primer on artificial intelligence for the paediatric cardiologist.

The combination of pediatric cardiology being both a perceptual and a cognitive subspecialty demands a complex decision-making model which makes artificial intelligence a particularly attractive technology with great potential. The prototypical artificial intelligence system would autonomously impute patient data into a collaborative database that stores, syncs, interprets and ultimately classifies the patient's profile to specific disease phenotypes to compare against a large aggregate of shared peer health data and outcomes, the current medical body of literature and ongoing trials to offer morbidity and mortality prediction, drug therapy options targeted to each patient's genetic profile, tailored surgical plans and recommendations for timing of sequential imaging. The focus of this review paper is to offer a primer on artificial intelligence and paediatric cardiology by briefly discussing the history of artificial intelligence in medicine, modern and future applications in adult and paediatric cardiology across selected concentrations, and current barriers to implementation of these technologies.

Adolescent Attitudes Toward Sexually Transmitted Infection Screening in the Emergency Department.

OBJECTIVES: Adolescents who seek care in emergency departments (EDs) are often at high risk for sexually transmitted infections (STIs). The objective of this study was to assess adolescent attitudes toward ED-based STI screening. METHODS: We conducted a secondary analysis of a cross-sectional study that evaluated STI screening acceptability and prevalence when STI testing was universally offered to asymptomatic adolescents presenting to the ED for care. Adolescents 14 to 21 years old completed a computerized survey and answered questions regarding attitudes toward ED-based STI screening and sexual behavior. We performed multivariable logistic regression to compare differences in attitudes toward ED-based STI screening among patients who agreed versus declined STI testing. RESULTS: Of 553 adolescents, 326 (59.0%) agreed to be tested for STIs. Most (72.1%) believed the ED was an appropriate place for STI screening. Patients who agreed to be tested for STIs were more likely to positively endorse ED-based STI screening than those who declined STI testing [77.0% vs 64.8%; adjusted odds ratios, 1.6; 95% confidence interval (CI), 1.1-2.4]. Most (82.6%) patients stated they would feel comfortable getting tested for STIs in the ED. There was no difference in the comfort level of ED-based STI testing between those who agreed and declined STI testing (83.5% vs 81.4%; adjusted odds ratios, 1.1; 95% CI, 0.7-1.8). CONCLUSION: Our results suggest that adolescents view the ED as an acceptable location for STI screening. Therefore, the ED may serve a role in increasing the accessibility of STI detection and prevention resources for adolescents.

Echocardiographic MRI: an innovative fusion of functional and anatomic assessment strategy for CHD.

We present a pilot case using an innovative fusion of echocardiogram and MRI achieved with a MATLAB-based imaging programme to explore the feasibility of this imaging strategy in the functional and anatomic assessment of a patient with repaired tetralogy of Fallot requiring pulmonary valve intervention. Echocardiogram and MRI neutralises the disadvantages and limitations of each individual imaging modality and yields important anatomic and haemodynamic information crucial to the treatment decision-making process. Future image fusion strategies can apply to three-dimensional images and image-directed therapy for CHD.

2 Cases of Spontaneous Coronary Artery Dissection in Neonates.

Spontaneous coronary artery dissection in infants is a rare phenomenon. We present 2 neonates with severe ventricular dysfunction due to coronary artery dissection. Neither patient had evidence of extracardiac fibromuscular dysplasia or other comorbidities that would explain the presentation. (Level of Difficulty: Advanced.).

Single Ventricular Torsional Mechanics After Fontan Palliation and Their Impact on Outcomes.

Background: Abnormal left ventricular (LV) rotational mechanics in biventricular hearts are associated with adverse outcomes; however, these are less well characterized for hearts with functionally single ventricles. Objectives: The purpose of this study was to characterize ventricular rotational mechanics in the Fontan circulation and their relationship to outcomes. Methods: Single-center, retrospective analysis of magnetic resonance examinations for 329 Fontan patients (15 [IQR: 10-21] years) and 42 controls. The ventricular cine short-axis stack was analyzed to derive torsion metrics. Torsion calculated as the difference between apical and basal rotation normalized to ventricular length. Results: Fontan patients had higher indexed ventricular end-diastolic volume (97 mL/body surface area1.3 vs 72 mL/body surface area1.3), lower ejection fraction (53% vs 60%), and lower proportion of basal clockwise rotation (62% vs 93%), apical counterclockwise rotation (77% vs 95%), and positive torsion (82% vs 100%); P < 0.001 for all. A composite outcome of death or heart transplant-listing occurred in 31 (9%) patients at a median follow-up of 3.9 years. Torsion metrics were associated with the outcome; although, on multivariate analysis only right ventricular (RV) morphology and indexed ventricular end-diastolic volume were independently associated. LVs with negative torsion, and RVs regardless of torsional pattern, had worse outcomes compared to LVs with positive torsion (P = 0.020). Conclusions: Single ventricles in a Fontan circulation exhibit abnormal torsional mechanics, which are more pronounced for RV morphology. Abnormal torsion is associated with death or need for heart transplantation. Fontan patients with LV morphology and preserved torsion exhibit the highest transplant-free survival and torsion may offer incremental prognostic data in this group of patients.

An Automated View Classification Model for Pediatric Echocardiography Using Artificial Intelligence.

BACKGROUND: View classification is a key step toward building a fully automated system for interpretation of echocardiograms. However, compared with adult echocardiograms, creating a view classification model for pediatric echocardiograms poses additional challenges, such as greater variation in anatomy, structure size, and views. The aim of this study was to develop a computer vision model to autonomously perform view classification on pediatric echocardiographic images. METHODS: Using a training set of 12,067 echocardiographic images from patients aged 0 to 19 years, a convolutional neural network model was trained to identify 27 preselected standard pediatric echocardiographic views which included anatomic sweeps, color Doppler, and Doppler tracings. A validation set of 6,197 images was used for parameter tuning and model selection. A test set of 9,684 images from 100 different patients was then used to evaluate model accuracy. The model was also evaluated on a per study basis using a second test set consisting of 524 echocardiograms from children with leukemia to identify six preselected views pertinent to cardiac dysfunction surveillance. RESULTS: The model identified the 27 preselected views with 90.3% accuracy. Accuracy was similar across age groups (89.3% for 0-4 years, 90.8% for 4-9 years, 90.0% for 9-14 years, and 91.2% for 14-19 years; P = .12). Examining the view subtypes, accuracy was 78.3% for the cine one location, 90.5% for sweeps with color Doppler, 82.2% for sweeps without color Doppler, and 91.1% for Doppler tracings. Among the leukemia cohort, the model identified the six preselected views on a per study basis with a positive predictive value of 98.7% to 99.2% and sensitivity of 76.9% to 94.8%. CONCLUSIONS: A convolutional neural network model was constructed for view classification of pediatric echocardiograms that was accurate across the spectrum of ages and view types. This work lays the foundation for automated quantitative analysis and diagnostic support to promote efficient, accurate, and scalable analysis of pediatric echocardiograms.

Artificial Intelligence in Congenital Heart Disease: Current State and Prospects.

The current era of big data offers a wealth of new opportunities for clinicians to leverage artificial intelligence to optimize care for pediatric and adult patients with a congenital heart disease. At present, there is a significant underutilization of artificial intelligence in the clinical setting for the diagnosis, prognosis, and management of congenital heart disease patients. This document is a call to action and will describe the current state of artificial intelligence in congenital heart disease, review challenges, discuss opportunities, and focus on the top priorities of artificial intelligence-based deployment in congenital heart disease.

Toxocara Myopericarditis and Cardiac Magnetic Resonance Imaging in a Young Girl.

Cardiac infection with Toxocara is rarely diagnosed, especially in children, and corresponding cardiac magnetic resonance imaging (CMR) has not been reported. We present a probable case, a 9-year-old girl with myopericarditis, eosinophilia, positive Toxocara serology, and CMR findings consistent with myocardial edema.

The Next Frontier in Pediatric Cardiology: Artificial Intelligence.

Artificial intelligence (AI) in the last decade centered primarily around digitizing and incorporating the large volumes of patient data from electronic health records. AI is now poised to make the next step in health care integration, with precision medicine, imaging support, and development of individual health trends with the popularization of wearable devices. Future clinical pediatric cardiologists will use AI as an adjunct in delivering optimum patient care, with the help of accurate predictive risk calculators, continual health monitoring from wearables, and precision medicine. Physicians must also protect their patients' health information from monetization or exploitation.