BACKGROUND: The Fontan operation is associated with significant morbidity and premature mortality. Fontan cases cannot always be identified by International Classification of Diseases (ICD) codes, making it challenging to create large Fontan patient cohorts. We sought to develop natural language processing–based machine learning models to automatically detect Fontan cases from free texts in electronic health records, and compare their performances with ICD code–based classification. METHODS AND RESULTS: We included free-text notes of 10 935 manually validated patients, 778 (7.1%) Fontan and 10 157 (92.9%) non-Fontan, from 2 health care systems. Using 80% of the patient data, we trained and optimized multiple machine learning models, support vector machines and 2 versions of RoBERTa (a robustly optimized transformer-based model for language understanding), for automatically identifying Fontan cases based on notes. For RoBERTa, we implemented a novel sliding window strategy to overcome its length limit. We evaluated the machine learning models and ICD code–based classification on 20% of the held-out patient data using the F1 score metric. The ICD classification model, support vector machine, and RoBERTa achieved F1 scores of 0.81 (95% CI, 0.79–0.83), 0.95 (95% CI, 0.92–0.97), and 0.89 (95% CI, 0.88–0.85) for the positive (Fontan) class, respectively. Support vector machines obtained the best performance (P<0.05), and both natural language processing models outperformed ICD code–based classification (P<0.05). The sliding window strategy improved performance over the base model (P<0.05) but did not outperform support vector machines. ICD code–based classification produced more false positives. CONCLUSIONS: Natural language processing models can automatically detect Fontan patients based on clinical notes with higher accuracy than ICD codes, and the former demonstrated the possibility of further improvement.

BACKGROUND: The Centers for Disease Control and Prevention’s Surveillance of Congenital Heart Defects Across the Lifespan project uses large clinical and administrative databases at sites throughout the United States to understand population-based congenital heart defect (CHD) epidemiology and outcomes. These individual databases are also relied upon for accurate cod-ing of CHD to estimate population prevalence. METHODS AND RESULTS: This validation project assessed a sample of 774 cases from 4 surveillance sites to determine the positive predictive value (PPV) for identifying a true CHD case and classifying CHD anatomic group accurately based on 57 International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes. Chi-square tests assessed differences in PPV by CHD severity and age. Overall, PPV was 76.36% (591/774 [95% CI, 73.20–79.31]) for all sites and all CHD-related ICD-9-CM codes. Of patients with a code for complex CHD, 89.85% (177/197 [95% CI, 84.76– 93.69]) had CHD; corresponding PPV es-timates were 86.73% (170/196 [95% CI, 81.17– 91.15]) for shunt, 82.99% (161/194 [95% CI, 76.95– 87.99]) for valve, and 44.39% (83/187 [95% CI, 84.76– 93.69]) for “Other” CHD anatomic group (X2=142.16, P<0.0001). ICD-9-CM codes had higher PPVs for having CHD in the 3 younger age groups compared with those >64 years of age, (X2=4.23, P<0.0001). CONCLUSIONS: While CHD ICD-9-CM codes had acceptable PPV (86.54%) (508/587 [95% CI, 83.51– 89.20]) for identifying whether a patient has CHD when excluding patients with ICD-9-CM codes for “Other” CHD and code 745.5, further evaluation and algorithm development may help inform and improve accurate identification of CHD in data sets across the CHD ICD-9-CM code groups.

With increasing survival trends for children and adolescents with congenital heart defects (CHD), there is a growing need to focus on transition from pediatric to adult specialty cardiac care. To better understand parental perspectives on the transition process, a survey was distributed to 451 parents of adolescents with CHD who had recent contact with the healthcare system in Georgia (GA) and New York (NY). Among respondents, 90.7% reported excellent, very good or good health-related quality of life (HRQoL) for their adolescent. While the majority of parents (77.8%) had been told by a provider about their adolescent’s need to transition to adult specialty cardiac care, most reported concerns about transitioning to adult care. Parents were most commonly concerned with replacing the strong relationship with pediatric providers (60.7%), locating an appropriate adult provider (48.7%), and accessing adult health insurance coverage (43.6%). These findings may offer insights into transition planning for adolescents with CHD.

We present an adolescent male with a single intracardiac mass and pulmonary emboli, complicated by peripheral venous thrombosis and subsequent development of pulmonary pseudoaneurysms, leading to diagnosis of Hughes-Stovin syndrome. Remission was achieved with cyclophosphamide, corticosteroids, and pseudoaneurysm resection and maintained with infliximab and methotrexate.

Background: As the population of adults with congenital heart disease (CHD) grows, cardiologists continue to encounter patients with complex anatomies that challenge the standard treatment of care. Single ventricle Fontan palliated patients are the most complex within CHD, with a high morbidity and mortality burden. Factors driving this early demise are largely unknown. Methods and Results: We analyzed biomarker expression in 44 stable Fontan outpatients (29.2 ± 10.7 years, 68.2% female) seen in the outpatient Emory Adult Congenital Heart Center and compared them to 32 age, gender and race matched controls. In comparison to controls, Fontan patients had elevated levels of multiple cytokines within the inflammatory pathway including Tumor Necrosis Factor-α (TNF-α) (p<0.001), Interleukin-6 (IL-6) (p<0.011), Growth Derived Factor-15 (GDF-15) (p<0.0001), β2-macroglobulin, (p=0.0006), stem cell mobilization: SDF-1α (p=0.006), extracellular matrix turnover: Collagen IV (p<0.0001), neurohormonal activation: Renin (p<0.0001), renal dysfunction: Cystatin C (p<0.0001) and Urokinase receptor (uPAR) (p=0.022), cardiac injury: Troponin-I (p<0.0004) and metabolism: Adiponectin (p=0.0037). Within our baseline -stable- Fontan patients, 50% had hospitalizations, arrhythmias and worsening hepatic function within 1 year. GDF-15 was significantly increased in Fontan patients with clinical events (p<0.0001). In addition, GDF-15 moderately correlated with longer duration of Fontan (r=0.55, p=0.01) and was elevated in atriopulmonary (AP) Fontan circulation. Finally, in a multivariate model, VEGF-D and Collagen IV levels were found to be associated with a change in MELDXI, a marker of liver function. Conclusion: Multiple clinical and molecular biomarkers are upregulated in Fontan patients, suggesting a state of chronic systemic dysregulation.

Objectives: The aim of this study was to test the hypothesis that narrowing the landing zone using commercially available endografts would enable transcatheter pulmonary valve replacement (TPVR) using commercially available transcatheter heart valves. Background: TPVR is challenging in an outsized native or patch-repaired right ventricular outflow tract (RVOT). Downsizing the RVOT for TPVR is currently possible only using investigational devices. In patients ineligible because of excessive RVOT size, TPVR landing zones were created using commercially available endografts. Methods: Consecutive patients with native or patch-repaired RVOTs and high or prohibitive surgical risk were reviewed, and this report describes the authors’ experience with endograft-facilitated TPVR (EF-TPVR) offered to patients ineligible for investigational or commercial devices. All EF-TPVR patients were surgery ineligible, with symptomatic, severe pulmonary insufficiency, enlarged RVOTs, and severe right ventricular (RV) enlargement (>150 ml/m2). TPVR and surgical pulmonary valve replacement (SPVR) were compared in patients with less severe RV enlargement. Results: Fourteen patients had large RVOTs unsuitable for conventional TPVR; 6 patients (1 surgery ineligible) received investigational devices, and 8 otherwise ineligible patients underwent compassionate EF-TPVR (n = 5 with tetralogy of Fallot). Three strategies were applied on the basis of progressively larger RVOT size: single-barrel, in situ fenestrated, and double-barrel endografts as required to anchor 1 (single-barrel and fenestrated) or 2 (double-barrel) transcatheter heart valves. All were technically successful, without procedure-related, 30-day, or in-hospital deaths. Two late complications (stent obstruction and embolization) were treated percutaneously. One patient died of ventricular tachycardia 36 days after EF-TPVR. Compared with 48 SPVRs, RV enlargement was greater, but 30-day and 1-year mortality and readmission were no different. The mean transvalvular pressure gradient was lower after EF-TPVR (3.8 ± 0.8 mm Hg vs. 10.7 ± 4.1 mm Hg; p < 0.001; 30 days). More than mild pulmonary insufficiency was equivalent in both (EF-TPVR 0.0% [n = 0 of 8] vs. SPVR 4.3% [n = 1 of 43]; p = 1.00; 30 days). Conclusions: EF-TPVR may be an alternative for patients with pulmonic insufficiency and enlarged RVOTs ineligible for other therapies.

Multisystem inflammatory syndrome in children (MIS-C) can cause a myriad of cardiac manifestations, including coronary dilation and aneurysms; giant aneurysms are infrequent. We describe 3patients with giant coronary aneurysms associated with MIS-C, including the youngest case reported to date, treated with intravenous immunoglobulin, corticosteroids, and biologic agents. (Level of Difficulty: Intermediate.)

Background: Adults with congenital heart disease (CHD) have been considered potentially high risk for novel coronavirus disease-19 (COVID-19) mortality or other complications. Objectives: This study sought to define the impact of COVID-19 in adults with CHD and to identify risk factors associated with adverse outcomes. Methods: Adults (age 18 years or older) with CHD and with confirmed or clinically suspected COVID-19 were included from CHD centers worldwide. Data collection included anatomic diagnosis and subsequent interventions, comorbidities, medications, echocardiographic findings, presenting symptoms, course of illness, and outcomes. Predictors of death or severe infection were determined. Results: From 58 adult CHD centers, the study included 1,044 infected patients (age: 35.1 ± 13.0 years; range 18 to 86 years; 51% women), 87% of whom had laboratory-confirmed coronavirus infection. The cohort included 118 (11%) patients with single ventricle and/or Fontan physiology, 87 (8%) patients with cyanosis, and 73 (7%) patients with pulmonary hypertension. There were 24 COVID-related deaths (case/fatality: 2.3%; 95% confidence interval: 1.4% to 3.2%). Factors associated with death included male sex, diabetes, cyanosis, pulmonary hypertension, renal insufficiency, and previous hospital admission for heart failure. Worse physiological stage was associated with mortality (p = 0.001), whereas anatomic complexity or defect group were not. Conclusions: COVID-19 mortality in adults with CHD is commensurate with the general population. The most vulnerable patients are those with worse physiological stage, such as cyanosis and pulmonary hypertension, whereas anatomic complexity does not appear to predict infection severity.

Background: Total cavopulmonary connection (TCPC) is associated with a lower risk of incident atrial arrhythmias as compared to atriopulmonary Fontan, but the risk of recurrent atrial arrhythmias is unknown in this population. The purpose of this study was to determine the incidence and risk factors for recurrent atrial arrhythmias and thromboembolic complications in patients with TCPC. Methods: This is a retrospective multicenter study conducted by the Alliance for Adult Research in Congenital Cardiology (AARCC), 2000–2018. The inclusion criteria were TCPC patients (age > 15 years) with prior history of atrial arrhythmia. Results: A total of 103 patients (age 26 ± 7 years; male 58 [56%]) met inclusion criteria. The mean age at initial arrhythmia diagnosis was 13 ± 5 years, and atrial arrhythmias were classified as atrial flutter/tachycardia in 85 (83%) and atrial fibrillation in 18 (17%). The median duration of follow-up from the first episode of atrial arrhythmia was 14.9 (12.1–17.3) years, and during this period 64 (62%) patients had recurrent atrial arrhythmias (atrial flutter/tachycardia 51 [80%] and atrial fibrillation 13 [20%]) with annual incidence of 4.4%. Older age was a risk factor for arrhythmia recurrence while the use of a class III anti-arrhythmic drug was associated with a lower risk of recurrent arrhythmias. The incidence of thromboembolic complication was 0.6% per year, and the cumulative incidence was 4% and 7% at 5 and 10 years respectively from the time of first atrial arrhythmia diagnosis. There were no identifiable risk factors for thromboembolic complications in this cohort. Conclusions: Although TCPC provides superior flow dynamics and lower risk of incident atrial arrhythmias, there is a significant risk of recurrent arrhythmias among TCPC patients with a prior history of atrial arrhythmias. These patients may require more intensive arrhythmia surveillance as compared to other TCPC patients.

Objective: Risk factors for major adverse events late after Fontan palliation are unknown. Prior studies have suggested ventricular function and morphology as important risk factors. The aim of this study is to (1) characterize the late major adverse event profile in adult Fontan patients and (2) identify additional risk factors that may contribute to adverse outcomes. Design and Setting: A retrospective review of all adult patients >15 years post-Fontan seen at a tertiary academic center was conducted. Clinical, laboratory, cardiac data, and abdominal imaging were collected via chart review. Major adverse events (death, cardiac transplantation, or listing) were identified, and timing of events was plotted using Kaplan-Meier methods. Univariate and multivariate logistic regression was used to determine independent predictors of late-term events. Results: A total of 123 adult Fontan patients were identified (mean time post-Fontan 22.4 years [±4.4]). Major adverse events occurred in 19/123 patients (15%). In this 15-year survivor cohort, transplant-free survival rates were 94.6%, 82.9%, and 59.8% at 20, 25, and 30 years postoperation, respectively. Modes of death were Fontan failure with preserved function (4), congestive heart failure with decreased function (2), sudden death (2), thromboembolic event (1), post-Fontan conversion (2), and posttransplant (2). No differences in adverse outcomes were found based on morphology of the systemic ventricle, Fontan type, or systolic ventricular function. On the other hand, features of portal hypertension (OR 19.0, CI 4.7-77.3, P < .0001), presence of a pacemaker (OR 13.4, CI 2.6-69.8, P=.002), and systemic oxygen desaturation (OR 0.86, CI 0.75-0.98, P=.02) were risk factors for major adverse events in the multivariate analysis. Conclusions: In adult Fontan patients surviving >15 years post-Fontan, portal hypertension, oxygen desaturation, and need for pacemaker were predictive of adverse events. Traditional measures may not predict late-term outcomes in adult survivors; further study of the liver's role in late outcomes is warranted.