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.