O’Sullivan, Donnchadh

Background Mortality in adults with congenital heart disease (CHD) is strongly driven by disease complexity. Social determinants of health (SDOH) influence adult CHD (ACHD) health outcomes but their impact on mortality is unclear. This study examined the influence of clinical factors and SDOH on all‐cause mortality in patients with ACHD. Methods Single‐center retrospective cohort study of patients with ACHD in the Mayo ACHD Registry who had a verifiable residential address between January 1, 2004 and December 31, 2023. Clinical and SDOH indicators were extracted, including insurance type, language, rural–urban commuting area code, and a housing‐based socioeconomic index, an individual‐level measure of socioeconomic status derived from 4 objective housing characteristics and categorized into quartiles (Q1–Q4). Cox proportional‐hazards models were fitted to evaluate associations with mortality, incorporating CHD severity, arrhythmias, SDOH indicators, and other comorbidities. County of residence was included as a random effect, and model discrimination was assessed using the concordance statistic. Results Among 6134 patients with ACHD, the mean age was 38±16 years; 51% were male; 78.7% were White and 44.9% had rural residence. Independent predictors of mortality included cyanotic CHD (adjusted hazard ratio [aHR], 5.70 [95% CI, 2.90–11.23]), Fontan palliation (aHR, 4.98 [95% CI, 2.56–9.70]), ventricular tachycardia (aHR, 1.71 [95% CI, 1.16–2.52]), older age at first visit (aHR, 1.05 per year [95% CI, 1.04–1.05]), male sex (aHR, 1.19 [95% CI, 1.03–1.39]), public insurance (aHR, 1.60 [95% CI, 1.35–1.90]), rural residence (aHR, 1.25 [95%, CI 1.06–1.47]), and non‐English language (aHR 1.75 [95% CI 1.38–2.23]). The housing‐based socioeconomic index quartile was not associated with mortality. The final model achieved a concordance statistic of 0.77. Conclusions Mortality in patients with ACHD is strongly influenced by both clinical factors and SDOH, independent of socioeconomic status. Addressing barriers to care such as language, insurance, and geography is essential for improving ACHD survival particularly in those at increased mortality risk.

Artificial intelligence (AI) is revolutionizing healthcare by offering innovative solutions for diagnosis, treatment, and patient management. Only recently has the field of pediatric cardiology begun to explore the use of deep learning methods to analyze electrocardiogram (ECG) data, aiming to enhance diagnostic accuracy, expedite workflows, and improve patient outcomes. This review examines the current state of AI-enhanced ECG interpretation in pediatric cardiology applications, drawing insights from adult AI-ECG research given the progress in this field. It describes a broad range of AI methodologies, investigates the unique challenges inherent in pediatric ECG analysis, reviews the current state of the literature in pediatric AI-ECG, and discusses potential future directions for research and clinical practice. While AI-ECG applications have demonstrated considerable promise, widespread clinical adoption necessitates further research, rigorous validation, and careful consideration of equity, ethical, legal, and practical challenges.

Background Early detection of left and right ventricular systolic dysfunction (LVSD and RVSD respectively) in children can lead to intervention to reduce morbidity and death. Existing artificial intelligence algorithms can identify LVSD and RVSD in adults using a 12‐lead ECG; however, its efficacy in children is uncertain. We aimed to develop novel artificial intelligence–enabled ECG algorithms for LVSD and RVSD detection in pediatric patients. Methods and Results We identified 10 142 unique pediatric patients (age≤18) with a 10‐second, 12‐lead surface ECG within 14 days of a transthoracic echocardiogram, performed between 2002 and 2022. LVSD was defined quantitatively by left ventricular ejection fraction (LVEF). RVSD was defined semiquantitatively. Novel pediatric models for LVEF ≤35% and LVEF <50% achieved excellent test areas under the curve of 0.93 (95% CI, 0.89–0.98) and 0.88 (95% CI, 0.83–0.94) respectively. The model to detect LVEF <50% had a sensitivity of 0.85, specificity of 0.80, positive predictive value of 0.095, and negative predictive value of 0.995. In comparison, the previously validated adult data‐derived model for LVEF <35% achieved an area under the curve of 0.87 (95% CI, 0.84–0.90) for LVEF ≤35% in children. A novel pediatric model for any RVSD detection reached a test area under the curve of 0.90 (0.87–0.94). Conclusions An artificial intelligence–enabled ECG demonstrates accurate detection of both LVSD and RVSD in pediatric patients. While adult‐trained models offer good performance, improvements are seen when training pediatric‐specific models.

AbstractObjectivesEosinophilic esophagitis (EoE) is often diagnosed in school‐age children between 6‐ and 9‐year‐old. There is less known about those who are diagnosed with EoE that are younger than 6 years old. The objective of this study is to compare clinical presentation, comorbidities, and outcomes based on age at diagnosis of EoE.MethodsSingle‐center retrospective chart review of children (<18 years) diagnosed with EoE between 2005 and 2020. We recorded demographics, clinical presentation, family history, past medical history, treatment, and endoscopic findings. Children in this cohort were classified based on age into three age groups: <2 years, 2−<6 years, and 6−<18 years.ResultsWe identified 256 children with EoE, the mean age (SD) at the time of diagnosis was 9 (5.2) years and 184 (72%) were male. We had 164 (64%) patients with available follow‐up esophagogastroduodenoscopies (EGDs) data (495 EGDs in total) of those 99/164 (60%) reached mucosal remission. In the very young children (<2 years) vomiting was the most common presentation, while poor weight gain was seen more in the 2−<6‐year group in comparison to the >6‐years. Food impaction and abdominal pain were most likely to present in older children 6−18 years. Combination therapy, as opposed to a single therapy, induced remission at a higher frequency in the <6‐year group in comparison to the 6−<18‐year group (85% vs. 66%).ConclusionEoE should be considered in younger children presenting with feeding difficulty and poor weight gain. Combination therapy seems to be more effective in younger children with EoE, but further studies with bigger sample size are needed to study the efficacy of the different combination therapies.

Background: Atrial septal defects (ASD) and ventricular septal defects (VSD) are among the most common forms of congenital heart disease (CHD). Early detection and intervention for these defects are crucial to prevent complications. Given advancements in AI technology, the development of AI-enabled ECG models for detecting these defects is of significant interest. Aims: This study aimed to create AI models using pediatric ECG data for the detection of ASD, VSD, and a combined model detecting either ASD or VSD. Methods: We analyzed a dataset of 7,795 pediatric patients from Mayo Clinic who had undergone echocardiography between 2002 and 2022, with corresponding 10-second, 12-lead surface ECGs taken within 14 days of echocardiography. This dataset included 259 patients with ASDs and 139 patients with VSDs (single or multiple). The control group was comprised of 7,397 patients without significant or complex CHD. For cases and controls, we included patients with all forms of electrocardiographic abnormalities and those with valvular lesions who had less than moderate stenosis or regurgitation. The dataset was divided into training, validation, and testing subsets to develop convolutional neural network (CNN) models for ASD, VSD, and either ASD or VSD detection. Results: Our ASD and VSD detection models achieved test AUCs of 0.82 (95% CI 0.76, 0.88) and 0.80 (95% CI 0.70, 0.90), respectively. Meanwhile, a combined model that detected either ASD or VSD demonstrated a test AUC of 0.81 (95% CI, 0.76, 0.86), sensitivity of 0.73, specificity of 0.76, PPV of 0.14, and NPV of 0.98 (Figure 1). Conclusions: AI-enabled ECG models demonstrate promising performance in detecting ASD and VSD in pediatric patients. A combined model that detects either ASD or VSD also shows robust results. Future research should focus on multi-center validation of these models, refining their diagnostic capacities, and investigating their potential for early intervention in CHDs.

Introduction: Left and right ventricular systolic dysfunction (LVSD and RVSD respectively) contribute to considerable pediatric morbidity. Both LVSD and RVSD can occur in children before symptom onset, emphasizing the need for early detection. Existing deep-learning algorithms can identify LVSD in adults using 12-lead ECG; however, their efficacy in children is uncertain. Aims: We aimed to create a deep-learning model for LVSD and RVSD detection in pediatric patients using an AI-enabled ECG and compare novel pediatric models to a previously validated adult LVSD model. Methods: We identified 10,214 pediatric patients at the Mayo Clinic with a transthoracic echocardiogram (TTE) and a 10-second, 12-lead surface ECG within 14 days of TTE, performed from 2002 -2022. Our cohort comprised the first TTE-ECG pair from each patient, totaling 138 with EF ≤ 35%, 312 with EF ≤ 50%, 482 with RVSD, and 9,567 without any LVSD or RVSD. The cohort was split into training, validation, and testing datasets to develop neural networks for systolic dysfunction detection. Results: The cohort was 52.3% male, with an average age of 10.3 years. Novel models generated in the pediatric cohort demonstrated excellent performance in systolic dysfunction detection (Figure 1). Pediatric models for EF ≤ 35% and EF ≤ 50% achieved test AUCs of 0.92 (95% CI 0.89, 0.95) and 0.89 (95% CI 0.85, 0.94) respectively. The RVSD model reached a test AUC of 0.91 (95% CI 0.88, 0.94). A combined model for EF ≤ 35% or RVSD exhibited a test AUC of 0.90 (95% CI 0.87, 0.93), sensitivity 0.88, specificity 0.82, PPV 0.20, and NPV 0.95. A combined model for EF ≤ 50% or RVSD exhibited a test AUC of 0.88 (95% CI 0.85, 0.91). The previously validated adult data-derived model achieved an AUC of 0.86 (95% CI 0.83, 0.89) for EF ≤ 50% in children. Conclusions: AI-enabled ECGs demonstrate efficient detection of both LVSD and RVSD in pediatric patients. Future multi-site validation is needed to further establish the reliability of these models.

Introduction: Biologic sex and hormonal concentrations shape ECG parameters due to sex hormone effects on cardiac function. AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. Aims: We aimed to test the ability of AI-enabled ECGs to predict pediatric patient sex and explore the influence of pubertal development. Methods: Two AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead surface ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 89,063 pediatric patients (aged <19 years) recorded from 1988-2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0-7 years), pubertal (8-14 years), and post-pubertal (15-18 years) patients. Results: The cohort consisted of 46.6% males, with 21,434 prepubertal, 26,300 pubertal, and 41,329 post-pubertal children. No significant performance difference was observed between the two models. Both models demonstrated 81% accuracy and an overall AUC of 0.91 in the testing cohorts, with high discriminatory ability in post-pubertal teenagers (AUC = 0.98). (Figure 1) Conclusions: AI-ECG predicts pediatric patient sex with varying performance across pubertal stages. The highest discriminatory ability is observed post-puberty, decreasing in pubertal and prepubertal children. The results suggest hormonal and physiological changes during puberty may influence cardiac electrophysiology measurably. More research is required to interpret CNN-predicted sex discordance with actual sex and its implications for future cardiovascular risk.

Abstract Background Pulmonary embolism (PE) in the pediatric population is uncommon, and due to a silent presentation often unrecognized entity that remains one of the most challenging medical conditions in the emergency department (ED). Risk factors for PE in children include nephrotic syndrome, immobility, obesity, congenital heart disease, and malignancy. In patients with PE, thromboembolism has been reported to occur at unusual venous sites including the veins within the central nervous system and abdomen. Although penile pain is a rare presenting symptom in the ED, in patients with hypercoagulability, it can herald a life threating event such as PE prompting further evaluation. Case presentation A 15-year-old male with a history of B-cell acute lymphoblastic leukemia who presented to the ED with an 18-hour history of penile pain. In the ED, the patient was in acute distress and rated his pain as 9/10. Initial vital signs were within normal limits, except mild tachypnea. On physical examination, his penile shaft was erythematous, indurated, and tender to palpation. He received fentanyl and morphine for pain. A complete blood cell count revealed pancytopenia with a platelet count of 73 x 109/L (139–320 x 109/L). A work-up for sexually transmitted diseases, urolithiasis, urinary tract infection, deep venous thrombosis (DVT), and priapism was negative. Approximately two hours after morphine administration, his saturations started dropping to mid-70’s. A computed tomography pulmonary angiogram (CTPA) revealed bilateral segmental acute pulmonary embolism involving multiple segmental right and left lower lobe pulmonary arteries. Penile pain and hypoxia have resolved with heparin. Conclusions PE is easily missed diagnosis among children who present to the ED and can be potentially fatal. A high index of suspicion is required in asymptomatic and oligo-symptomatic children with prothrombotic risk factors who develop thromboembolism-related symptoms at unusual sites as well as hypoxia in the ED setting.

AbstractDisorders affecting smooth muscle structure/function may require technologies that can generate large scale, differentiated and contractile smooth muscle cells (SMC) suitable for cell therapy. To date no clonal precursor population that provides large numbers of differentiated SMC in culture has been identified in a rodent. Identification of such cells may also enhance insight into progenitor cell fate decisions and the relationship between smooth muscle precursors and disease states that implicate differentiated SMC. In this study, we used classic clonal expansion techniques to identify novel self-renewing Islet 1 (Isl-1) positive primitive progenitor cells (PPC) within rat bone marrow that exhibited canonical stem cell markers and preferential differentiation towards a smooth muscle-like fate. We subsequently used molecular tagging to select Isl-1 positive clonal populations from expanded and de novo marrow cell populations. We refer to these previously undescribed cells as the PPC given its stem cell marker profile, and robust self-renewal capacity. PPC could be directly converted into induced smooth muscle cells (iSMC) using single transcription factor (Kruppel-like factor 4) knockdown or transactivator (myocardin) overexpression in contrast to three control cells (HEK 293, endothelial cells and mesenchymal stem cells) where such induction was not possible. iSMC exhibited immuno- and cytoskeletal-phenotype, calcium signaling profile and contractile responses similar to bona fide SMC. Passaged iSMC could be expanded to a scale sufficient for large scale tissue replacement. PPC and reprogramed iSMC so derived may offer future opportunities to investigate molecular, structure/function and cell-based replacement therapy approaches to diverse cardiovascular, respiratory, gastrointestinal, and genitourinary diseases that have as their basis smooth muscle cell functional aberrancy or numerical loss.